POST-MIDTERM Flashcards

Question

What are the 4 potential purpose of a survey ?

Answer 1

- Exploration - Observation - Explanation - Generate data of a large range of items

Answer 2

The Tri-Council Policy Statement on the ethics of research involving humans demands: - respect for human dignity; - respect for free and informed consent; - respect for vulnerable persons; - respect for privacy and confidentiality; - respect for justice and inclusiveness; - balancing harms and benefits; - minimizing harms. - Universities that wish to receive funding from one of the councils must develop procedures that are consistent with these broad principles, including ethics review committees

Answer 3

Advantages: - Less expensive than probability - Often the only feasible method - Can yield info that may not be available in probability sample with a moderate size. For example, we can illuminate information on: deviant/unusual cases, cases of people whootherwise would’ve been impossible to collect through probability sampling, cases of people who represent minorities

Answer 4

Quasi-filter: Here is a statement about another country: “The Russian leaders are basically trying to get along with America.” Do you agree, disagree, or have no opinion on that?

Answer 5

**Simple random sampling/equal probability of selection:** Participants are randomly selected **Systematic sampling:** Potential participants are on a list. Every kth participant is included in the sample. **Stratified:** Researcher divides sample into separate groups (strata). Then, a probability sample (often random) is drawn from each group. Ensures that your sample proportions are equivalent to population proportions. **Cluster:** Researcher divides population into separate groups (cluster). Then a simple random sample of clusters is selected from the population.

Answer 6

A research example (1)Milgram, Obedience to Authority (1969) - Recruited men to participate in a study ostensibly on memory and learning. - Research subject was assigned the role of ‘teacher’: asked to test learners’ memory of word lists and to apply electric shocks of varying severity when the learner gave the wrong answer. - The learner was, in fact, an actor.The ‘learner’ was not visible to the ‘teacher’ but could be heard by him. The ‘learner’/actor signalled discomfort and pain in response to the shocks. - Most of the ‘teachers’ accepted the instruction to apply shocks up to levels marked as dangerous on the gauge of the equipment they were using. - Evidently, this is experimental research, not a focus group. Gamson, Fireman, and Rytina, Encounters with Unjust Authority (1982 - The researchers presented themselves as market researchers and recruited participants for their study. - The participants were read a summary of a legal case said to be before the courts. - The case put an oil company in a highly unfavourable light. - But the coordinator pressured the participants to “give false opinions (favourable to the sponsoring oil company) for the videotape being made for a potential legal proceeding“. - Many of the participants refused to do so. - What was the difference with Milgrom‘s experiment? Its focus group-like character meant that social support led many participants to resist the authority of the (apparent) researche

Answer 7

Range: Maximum value – minimum value Standard deviation: Average of the squared deviations from the mean

Answer 8

Open coding illustrated (1)Robson studied the long-term effects of being bullied as a child. When she open coded her interview transcripts the following themes emerged: distrust of intimate relationships in adulthood; empathy toward other people; awkwardness in social settings Here are responses that were open coded awkward in social settings.“I try to avoid group situations out of habit ... Not that I fear anymore that I am going to get teased or harassed or fucked with, but I just have these habits that are hard to break. Avoiding groups, avoiding being the centre of attention, because when I was the centre of attention when I was growing up, it was for bad things, so now it’s hard to be centre of attention even though it might be for something positive.” (male, mid 20s) It’s only been since I’ve been married that I’ve started to form good solid relationships with women ... I’m still not really confident in social situations around people that I don’t know very well, I’m not confident ... I think that the friends I do have are a lot more deeper and more meaningful because I knew how to form those when I was a kid – deeper more meaningful relationships.” (female, mid 20)

Answer 9

f we assign 51%, we will make fewer errors

Answer 10

Where possible, randomization is always better than matching because random assignment deals with unobservable as well as observables. When matching, there might be unobservable characteristics not part of the matching process which influence the result, you get a distribution within the two groups taking into account both kinds of characteristics.

Answer 11

The project involved the following components: - HRSDC provided $30,000 in planning funds to each community; - communities mobilized local project sponsors to identify community projects that might usefully be implemented; - unemployed community members could be hired to carry out the projects and were paid wages from $280 per week early in the project to $325 per week later in the project, and were covered by EI and Nova Scotia Workers’ Compensation; - they worked for up to 35 hours per week; - they could be hired for up to three years;they could switch between the CEIP work and other employment; - compensation included statutory holidays and ‘personal days’ that could be used for vacations or sick leave; - projects included local beautification, services for the poor, support for seniors, support for youth, services to the disabled, the arts

Answer 12

when the addition of the control/test variable causes the zero-order relationship to disappear and it does so because the original relationship was spurious **Relationship between regular breakfast consumption and the teenage pregnancy** The percentage point difference is 25; there is clearly a zero-order relationship between breakfast consumption and pregnancy. Does the table settle the issue of causation? It is possible that the relationship is spurious. For example, regular breakfast consumption may be associated with a stable home life. So: control for time spent at home For parents who spent both high and low amounts of time at home the percentage point differences between breakfast pattern and teenage pregnancy effectively disappear. The percentage point difference before controlling for occupation was 25. Evidently, the partial relationships differ from the zero-order relationship The result of adding the test variable (parents’ time at home) has the same effect on the relationship between breakfast habits and pregnancy as did adding occupation on the relationship between gender and pay.

Answer 13

the distance between the point and the line

Answer 14

Systematic Sample: you work with a list and takes every kth element from the list , Implies sampling interval equal to population sample size. ( the sampling interval = Sample ratio = sample size/population size = 100/1000= 1/10)

Answer 15

after adding the test variable the association between the two variables of interest disappears i) adding a test variable eliminates the relationship between the independent and dependent variables in partial tables and ii) the test variable can be considered to be caused by the independent variable but prior to the dependent variable, within the elaboration model that is called interpretation **Income, gender, and medical occupation** The percentage point difference is 18; there is clearly a zero-order relationship between gender and income. Does the table settle the issue of causation? It is possible that the relationship is spurious. For example, male medical professionals may be in different, and differently paid, occupations from female medical professionals. So: control for occupation The percentage point differences for both doctors and nurses effectively disappear. The percentage point difference before controlling for occupation was 25 We know that occupation does not cause gender; that is to say, any causal connection must go from gender to occupation, rather than vice versa. It is also most likely that occupation causes income rather than vice versa. So, occupation must be an intervening variable, between gender and pay

Answer 16

Experiments Surveys Qualitative interviews Observation Unobtrusive Research

Answer 17

A study of a marijuana legalization group in Western Canada generated the following open codes: distrust, partying, and marginalized people. Then the researcher attempted to connect these coded observations. The use of marginalization was linked to distrust of various entities – the government, the police, for example. The researchers conclusion: marginalization led to distrust of institutions. But distrust also led respondents to marginalize themselves, as did their models of ‘partying’; both distrust and partying led to marginalization

Answer 18

se programs involve expenditures. This raises the question: Are the expenditures worthwhile?

Answer 19

Researchers may be interested in the extent of knowledge of something or other. Such questions may be threatening to respondents who are reluctant to reveal their ignorance.

Answer 20

- Official statistics are the result of a social process (reporting and recording a crime, deciding which crimes to report, court decisions on the fact and character of a sexual assault). - Statistics agencies have different practices (StatsCan versus US Census Bureau). - What statistics means depends on institutional design and practices (high school graduation rates in Australia, drop-out rates in Quebec) - Different data sources have different strengths and weaknesses (inequality – the Census versus survey data) - Crime, Rape, Australia graduation, Cannabis income, income inequality in canada (who tend to undercount the very poor) The unit of analysis is usually an aggregate; there is the problem of the ecological fallacy. - Using already collected data means that the validity of the measures may be problematic (e.g., the unemployment rate and the state of the labour market). - Reliability may be problematic – for example, changes in the definition of rape/sexual assault over time (and no doubt across countries). - Conclusion: for the purposes of research, official statistics are often flawed. Therefore, use them cautiously! For example, use multiple indicators of the state of the labour mark

Answer 21

R O1 XO2R O3O4 - This is a true experimental design. We can compare O2-O1 with O4-O3. - Equivalence of the groups at the first point of observation is achieved through randomization, not through matching - Solves issues of internal validity

Answer 22

Mutually exclusive. The respondent can plausibly fit into one, and only one, of the response options, which is not the case if the categories overlap. Exhaustive. The categories that all respondents can fit themselves into one of the categories provided. “Are you working or unemployed?” is unsatisfactory because it excludes the category “not in the labour force”. Balanced. Usually, it is better to allow responses that range between equal, polar, opposites – say, from very satisfied to very unsatisfied – as in a typical Likert scale

Answer 23

1. Pre-test, Post-test, control group design 2. Post-test only control group design 3. Solomon four group design

Answer 24

R= randomization which deals with how we constitute the groups we study. Randomization= number table and assign people based on the number generate

Answer 25

Interaction ## Footnote You have two things present, the stimulus and the conditions of experiment and its the interaction of the two that creates a treat to generalizability.

Answer 26

advantages: ## Footnote They provide the social context for judgments that exist in real life. - Group dynamics may bring out unanticipated issues – that might have been hidden had individuals alone been interviewed. - There is high face validity – what is being measured is identified through discussion among group participants. - Relatively low cost. disadvantages: The social dynamics of the group may be hard to control. Some members may dominate the discussion. - Taped discussions are challenging to analyze - How differences across focus groups in conclusions or views should be interpreted is not always obvious. That may indicate a problem of reliability

Answer 27

In **probability sampling methods**, each population element has a fixed and known (non-zero) chance of being chosen for the sample. In other words, subjects in a population have a random and therefore equal opportunity to be selected as a representative sample. In **non-probability sampling methods**, we do not know the probability that each population element will be chosen, and/or we cannot be sure that each population has a non-zero chance of being chosen. The basis of selection is likely to be arbitrary and opposed to random, so the opportunity of being selected is not specified and is unknown.

Answer 28

- How valid are the measures of benefits (or costs) that don‘t usually have dollar values? - What interest rate should be used to discount to a present value? The Community Employment Innovation Project used a 5% discount rat

Answer 29

Statement: “I regularly get enough sleep at night” - Likert scale Question: “How many hours do you regularly sleep at night” - 1-5, 6-7, 8-9 \*Choice between question and statement- best of all is that you ask both to get more information -Ask them both to get information about how they sleep and how they feel about it

Answer 30

We want to explore the causal relationship between two variables. We know that other factors might influence one or both of the variables. The elaboration model specifies: i) how we might go about analyzing the relationships between three or more variables; ii) identifies different possible ways of interpreting tables after a third variable has been adde

Answer 31

Questionnaire construction: Questions versus statements How many hours do you regularly sleep at night? Less than 4 5-6 7-8 9 or more How do you feel about the following statement: “I regularly get enough hours of sleep at night” Strongly disagree, disagree, agree, strongly agree If you include both, you can compare the responses using the two different measures

Answer 32

**History :** it is possible that between o1 and o2 , x might not have been the only thing that happened. Other evens might of happened that explain the change between o2 and o1 **Maturation :** time passes between o1 and o2 , the subjects might change, the difference may not produced by x but by changes in subjects produced by time **Testing:** If there is a pre-test, is possible that the post pre-test results are determined by the pre-test rather than the experimental effect. Initial observation could change attitudes or behaviours of the subjects for the second observation, may not be do by the intervening variable. the first observation may change the second of x ( o1 may produce o2) **Instrumentation:** does the measurement instruments remain the same between the observations **Statistical regression towards the mean:** If you select members on the basis of some extreme performance it is likely that their performance will change overtime with or without experimental effect. When you have an extreme score, it is produced by what we are trying to measure AND random factors, the score at a second point in time is likely to get closer to the mean _Low end of the distribution example:_ those who did badly are given a coaching program, they are tested again, their scores go up, can we infer it is because of the program ? If you observe the scores of a test , two things influence : 1. Cognitive ability 2. Ability and Radom factors. So we looking at the bottom 20%, the random factors will most likely be negative. You cant infer causation here because the low scores of this selected group had an accumulation of negative factors and It is unlikely they will experience the same negative factors. For the lower ground, it is likely that their performance will improve regardless because they were subject to negative factors. _Higher end of distribution example:_ How do you chose an advisor ? Rating based on previous performance. But this not valid, because the random factors came into play- they will probably come back down again, they are likely to do worse because their first performance was based on luck. Those who did well tend to regress towards the mean. The high ranking are produced by 1. Ability knowledge 2. Luck. So mostly firms who did well will do worst later, those who did worst will do better later Index Funds: buy a distribution of share that represent the distribution of the market as a whole. (Instead of having someone picking shares for you) So your performance is based on the market not on individuals, plus saving the fees. **Differential Selection :** If you have two groups, can you be confident the two groups are constituted from the same population. **Experimental Mortality:** Do people disappear more frequently in one group than the other.

Answer 33

By social revolutions Skocpol means: i) a change in state structures – a political revolution; and ii) a change in social structures by which she means which class is dominant. There are two sufficient causes of a social revolution: i) a crisis of the state (military defeat, sovereign default); ii) a pattern of class dominance which determines who will lead the revolution

Answer 34

**Times-series experiment** - common in workplace experiments - O1, O2, O3, O4 x O5, O6, O7, O8 \_\_\_\_\_\_\_\_ \_\_\_\_\_\_\_\_\_/ **Equivalent time sample design** - x0 O0 x1 O1 x0 O0 x1 O1 ….. - x is introduced then reduced, then introduced and so on

Answer 35

**Are Internal Validity issues adressed ?** - History: yes. Because you are comparing to a control group. Whatever other factor that could influence must have been present for both groups. - Maturation: yes. The two groups mature at the same rate. - Testing: yes. Both groups have a pre-test so there should not be differences between the two groups resulting from testing. - Instrumentation: yes. The observer mature at the same time. - Regression towards the mean: yes. there should be regression towards the mean in both but if one is larger we can see the size of that effect is. - Differential selection: yes. Because we’ve randomly selected the members and we’ve dealt with the sample error using inferential statistics. - Experimental Mortality: no. x might have an effect on the willingness of people to remain in the study (positive or negative)

Answer 36

The bivariate equation is yi= a+bx Where: yi = the values of a dependent variable a = the intercept b = the regression coefficient xi = the values of an independent variable The equation for two independent variables isyi = a+b1x1i+b2x2i

Answer 37

**Open:** What is your favourite TV program ? (factual question) Whats the most important issue in Canada today ? (judgment question) **Close:** respondent is asked to provide an answer based on a list designed by researcher (answer structured by the list) Close ended = 1 to 5 and list (+other)

Answer 38

- Of those who attended the information session, 1006 out of 1620 EI recipients signed the enrolment form while 516 of the 557 IA recipients did so. Note the self-selection into samples this implies. - The samples differed: EI 58% males, IA 62% females; EI mean age 40, IA mean age 35; EI 69% high school diploma; IA 60% high school diploma; EI more likely to live in two person household; EI household incomes on average higher than IA household incomes; IA sample reported somewhat lower health. Note that these differences in personal characteristics may influence the extent to which the program affects those enrolled in it. )As compared to the control groups: employment rates for both EI and IA participants during the period of the program were higher, then dropped to the same when the program finished; 14 months post program, EI and IA participants earned about the same as controls; their earnings had fallen back to pre program levels. immediately at program end, more EI and IA participants collected EI (of course, during the program fewer of them collected EI), then the prevalence of EI collection fell back to the same level as the controls. As compared to the control groups: both EI and IA participants tended to have somewhat more highly skilled post-program jobs (this raises the questions: why was their pay not higher?); both EI and IA participants had about the same attitudes towards work (“I like going to work“) and welfare (“It‘s wrong to stay on welfare“); EI participants developed somewhat more social ties that might be used to find jobs, but only if they had a high school diploma or equivalent; IA participants did not develop more useful social ties.10 Findings (4)As compared to the control groups: both EI and IA participants were more likely to have engaged in unpaid volunteer work while in the program (providing information or help educating the public, teaching or coaching for an organization, office or administrative work, collecting serving or delivering food, volunteer driver); volunteering was not associated with enhanced social capital among the EI participants; volunteering was associated with enhanced social capital among the IA participants.11 The researchers also looked for community effects through “a quasi-experimental, comparison sites design“ – matching the six communities studied with similar communities. They found: there were improvements in the performance of the organizations for which program participants worked;there were some increases reported in the average social capital in the communities studied; some attitudinal evidence of greater ‘social cohesion‘ – trust in police officers, trust in close friends, trust that a wallet would be returned; more or less no statistically significant differences in employment rates, wages, income, or economic activity

Answer 39

Interval Validity : to what degree of confidence we can infer a causal relationship between the variables External Validity: to what degree are the relationships we find are representative

Answer 40

There are differences between the observations on the scatterplot and the regression line. The regression line is calculated to minimize the squared differences between the observations and the line. The regression procedure is commonly called ordinary least squares(OLS). The larger the distances between the observations and the line, the poorer the line is as a description of the relationship. Pearson’s product-moment correlation is based on these distances. The larger the distances, the smaller the correlation coefficient; the smaller the distances, the larger the correlation coefficien In this case r= -0.84. The square of r (r2) = 0.71 and is interpreted as the proportion of the variance in the dependent variable (number of children) explained by the independent variable (years of education). You can think of it as a measure of the reduction in error in predicting the dependent variable score as a result of knowing the independent variable scale

Answer 41

- Within the six CEIP communities, recruit potential participants from people on EI (Employment Insurance) and IA (Income Assistance) by: - randomly selecting from an HRSDC list of EI recipients; - recruiting IA recipients from a list provided by the Nova Scotia Department of Community Services of those interested in participating; - inviting those selected to an information meeting;those selected from each group were randomly assigned to experimental and control groups. - A “multi-methods" approach to program evaluation: - individual impacts using i) a baseline survey, ii) three follow-up surveys; iii) administrative data files; iv) CEIPs Project Management Information System; - community effects using i) a three wave longitudinal survey administered to community residents from the six CEIP communities; ii) local administrative data (for example, on crime); iii) in-depth interviews and focus groups with "key community stakeholders“; iv) local observations (e.g., had the attractiveness of the community improved?); v) scans of local medi

Answer 42

The mean will diverge greatly from the median in the circumstance of outlying cases (for example, a median salary for a Country X is $70,000, but the mean income is over $100,000 because a small sect of the population makes over $500, 000).

Answer 43

The research design. The specification of outputs – that is, program consequences The issue of costs and benefits. Measuring costs and benefits over tim

Answer 44

Sampling errors requires processes that respond to them, which is inferential statistics.

Answer 45

It’s problem should be obvious: we have no idea whether or not the stimulus produced any change at all. There is, of course, an implicit comparison with other events, unsystematically observed. For example, the owner of the restaurant may have a sense of likely tip amounts based on previous experie

Answer 46

R X O1 R O2 This is a true experimental design The pretest in the pretest-posttest control-group design makes it possible to establish the initial scores of the experimental and control groups. But randomization should accomplish the same thing as a pretest (combined with the use of inferential statistics). In fact this design meets the internal validity issues about as well as the pretest-posttest control-group design And, evidently, the absence of a pretest removes the possibility of the challenge to external validity from reactive effects of testing. The other two possible sources of external invalidity – selection biases and experimental artificiality - remain. Still, being able to quantify any change in the score of the experimental group is an advantage of the pretest-posttest control group design

Answer 47

Omnivous character 1. Multiple item may be needed to construct indexes and scales 2. Hypothesis may be formulated without sharply definite operational framing \*\*\* , a survey that contains multiple items allows the exploration of different operationalization. 3. once you find a collaborative respondent, you want to get the more of it

Answer 48

**Internal Validity** Hstory: As the number of occasions on which the stimulus is provided is increased the problem of history diminishes. That is, if the same effect is observed on 51 different occasions it is unlikely to be explained by extraneous events. Maturation: Where the application of the stimulus is relatively short lived aging isn’t a problem. If the experiment were carried out over a long enough time period it might become a problem. If the durations of periods when the stimulus is provided and not provided are the same, then fatigue, etc., shouldn’t be a factor. Testing: There is no pretest Instrumentation: Again, the same observations are made during the periods when the stimulus is being applied and when it isn’t being applied; there is no obvious systematic bias from, say, observer fatigue. Regression towards the mean. Suppose the stimulus is applied to employees selected because of poor performance. Regression toward the mean would cause their scores to go up when they are observed after X1. But since the same group is consecutively studied random negative effects should be consecutively averaged out. This should not be a problem Selection: There is no control group, so differential selection into the two groups cannot be a problem. Mortality: A given work group under study is likely to lose current members and gain new ones. But if the stimulus is applied multiple times and the effect is present each time, and absent when the stimulus is not applied, mortality can’t be a problem **External Validity** There may well be reactive effects of testing. That is to say, the provision of repeated stimuli may modify the reactions to subsequent stimuli. Where a natural group is selected – a work group, a class in a school, say - there is always a possibility that any effect of the stimulus may only be produced for subjects of the kind of group being studied. There is likely to be, then, an interactionbetween selection biases and the experimental variable. Providing and withdrawing music (the example we considered) is a highly artificial experience. There may, then, be reactive effects of experimental arrangement

Answer 49

-7.85 is the intercept (the point where the line crosses the Y axis; --0.35 is the reduction in the number of children associated with one extra year of education. That is, on average, each extra year of education reduced the number of children by about a third. - Evidently, this is simply the formula for a straight line. - The relationship is negative – hence the minus

Answer 50

Modest cost – printing and mailing expenses, not hiring or training interviewers. People may feel more comfortable giving truthful answers to sensitive questions. But this isn’t clear in the data reviewed earlier. The characteristics of an interviewer will not affect the respondent’s answer. It allows more time to give well thought-out answers.

Answer 51

History: As the number of occasions on which the stimulus is provided is increased the problem of history diminishes. That is, if the same effect is observed on 51 different occasions it is unlikely to be explained by extraneous events. Maturation: Where the application of the stimulus is relatively short lived aging isn’t a problem. If the experiment were carried out over a long enough time period it might become a problem. If the durations of periods when the stimulus is provided and not provided are the same, then fatigue, etc., shouldn’t be a factor. Testing: There is no pretest Instrumentation: Again, the same observations are made during the periods when the stimulus is being applied and when it isn’t being applied; there is no obvious systematic bias from, say, observer fatigue. Regression towards the mean. Suppose the stimulus is applied to employees selected because of poor performance. Regression toward the mean would cause their scores to go up when they are observed after X1. But since the same group is consecutively studied random negative effects should be consecutively averaged out. This should not be a proble Selection: There is no control group, so differential selection into the two groups cannot be a problem. Mortality: A given work group under study is likely to lose current members and gain new ones. But if the stimulus is applied multiple times and the effect is present each time, and absent when the stimulus is not applied, mortality can’t be a problem.

Answer 52

## Footnote Open coding, whether used with grounded theory or not:try to identify as many themes as possible that emerge from the data; In doing so, delay considerations of connections between themes until later. Focussed coding: - having previously identified topics/categories of interest read through the data to note occurrences; - discard codes that don’t yield interesting information

Answer 53

Want to % on the independent variable. Do you % by row or by column

Answer 54

The Tuskegee experiment A study of the evolution of syphilis among a sample of Afro-American sharecroppers in Tuskegee, Alabama, began in 1932. The study was conducted by the U.S. Public Health Service. There were 399 subjects, all of whom had previously contracted syphilis. They were offered free medical care, meals, and burial insurance. The men were not told that they had syphilis. There were 201 non syphilitic controls.Subject consent to spinal taps (seeking evidence of neurosyphilis) was secured by describing the procedure as a free treatment.The study continued to follow the development of the disease in the men until 1972.2 **ethical issues** Deception was used – for example, the spinal tap procedure. At the point the study began there was no reliable treatment for syphilis; so simply following the disease implied no harm for subjects. (Before the 1940s treatments for syphilis involved the use of some highly toxic substances.) In the 1940s penicillin, an effective treatment for syphilis, was discovered. This treatment was not made available to the study subjects. During WWII 250 of the subjects registered for the draft, were diagnosed with syphilis, and ordered to get treatment. The researchers prevented them from getting treatment, preventing them from serving in the military and benefitting from the provisions of the G.I. Bill, passed after the war From 1946 to 1948 there was an extension of the experiment in Guatemala. There, 696 men and women – prisoners, soldiers, mental hospital patients – were deliberately infected with syphilis and, in some cases, gonorrhea. After infection they were provided antibiotic treatmen

Answer 55

Estimate a regression line = line that best fits this data Line that minimize the distance between the observations and the line estimated Squared values have a large effect on lines Effect of square = Increasing the weight of extreme values So that line is influenced by extreme values if there are any What methodical practices does that suggest one should adopt ? Looking at the scatter plot allows us to see extreme valuables. Before you decide to drop cases, you need to look at the scatter plot. Implications of the results you get. When you start to look at data , look at the scatter plots

Answer 56

pretest-posttest control group design posttest-only control group design

Answer 57

Adding a 3rd variable What happen to associate when we had a 3rd variable The model specifies the ways the relationship may change

Answer 58

History: not a problem. Anything that happens before X will happen to both Maturation : not a problem.you have the same conditions under two groups Testing: not a problem. because there is not pre-test. Instrumentation: not a problem , you have the same conditions under two groups. Regression towards the mean : not a problem. Selection: not a problem, we use randomization Mortality: maybe but its not due to the variable

Answer 59

- Evidently, these do not use the simple, predetermined, categories that dominate questionnaire design. - Rather, the interviewer has a list of topics which can be addressed in no particular order. The flow of conversation with the subject including, the advantage of developing an empathetic relationship with that subject, will determine the order of the questions. - In addition, subjects not anticipated may be explored in response to the things said by the subject during the interview. This capacity to seize on and explore issues raised during an interview is a considerable strength of this method. This is a major advantage of this method. - Usually all questions/issues are address

Answer 60

Tables : nominal or ordinal data Scatter : interval or ratio data (super important because you will see something you would not understand)

Answer 61

This is a very common method of collecting survey data. The interviewer calls the respondent (often at home), asks questions and records the answers. Respondents sampled from lists, phone directories or random digital dialling. Computer assisted telephone interviewing (CATI) can reliably move the interviewer through complex questionnaires involving contingent questions and skips.

Answer 62

Mean: statistical average, found by adding up all given data and dividing by number of entries. Median: the middle number, found by ordering all data points and selecting the one that falls in the middle Mode: The most frequent number.

Answer 63

**History:** Might events likely to influence the dependent variable but unrelated to the experiment have occurred in addition to the experimental variable? **Maturation:** Do the subjects change over time, simply as a function of the passage of time – for example, aging, getting hungry, getting tired? **Testing:** Might the experience of a first test change responses at a second test? **Instrumentation:** Might the measuring instrument , or people doing the measuring, change in ways likely to influence measurements? For example, do observations become less accurate when observers are tired **Statistical regression (regression towards the mean):** Suppose a sample is deliberately drawn from part of a distribution – say, for example, all those who scored poorly on a test. Did random factors influence those scores, random factors that are unlikely to be (as) present for the group selected in a retest? This was identified as a problem in educational research where poor performers on tests were selected to receive some sort of remedial training. It also observed in cases of financial advisers. **Differential selection of respondents to comparison groups:** Where there is an experimental and a control group, might the method of assignment of respondents to groups cause the groups to differ in ways that might bias our experimental results? **Experimental mortality:** Where there is an experimental and a control group, is there differential attrition from the control and the experimental group

Answer 64

In the marijuana legalization group study the researcher went through her notes and identified marginalization as a major theme. This was partly because she observed that both partying and distrust were linked to marginalization, but not to each other. Having identified marginalization as a core theme she went through her notes to look for explicit links between marginalization and her other coded characteristics. She found that under the category distrust, group members talked about encounters with police, views on conspiracy theories, clashes with family members, experiences of harassment by the public. She concluded that there was mutual causation between distrust and marginalization

Answer 65

In the US, respondents were twice as likely to favour spending “to help the poor” than “welfare” (Smith, Public Opinion Quarterly, 1987). In Canada there is a difference, but it is smaller (Neumann and Robson, Basics of Social Research, 2009). Many respondents asked whether they thought television news impartial appear to have ignored the word ‘impartial’, perhaps it wasn’t part of their standard vocabulary. Evidently, possible wording effects need to be considered and explored.

Answer 66

3 challenges **1. Reactive Effect of Testing :** design includes pre-test, members were test which causes a possible problem because it is possible that the stimulus only operates where the pre-test in present. Our results don’t allow us to exclude the possibility that the interval validity operates because of a pre-test. Clearly that does not allowed to a general population that did not experience a pre-test. The causal factor depends upon the pre-test. **2. The interaction effects of selection biases and the experimental variables:** For example, if I’m interested in teaching styles in schools. One would take the classes most available, would not usually draw a sample across Canada. Supposing for that classroom, I present an internally valid result, can we generalized what happened in a Montreal classroom to classrooms across the general population? If we were looking at language, the effect found might have been resting entirely on the kind of classroom in our sample- the same results may not be possible in a Toronto classroom. **3. Reactive Effects of experimental arrangements:** Results might only be present where artificial characteristics of the experiments are present. (ex: observers in a classroom undermines the potential generalizably of the research )

Answer 67

Surveys are expensive. Consequently, once the data have been collected it is typically archived so that further work can be done on them. A problem with this is that the issues to which the survey was directed, and the questions used in it, may not coincide precisely with the issues that interest a particular researcher.

Answer 68

what degree to out capacity to predict results improves by knowing scores on the independent variables?

Answer 69

Advantages: - It is relatively inexpensive. But content analysis can require a large enough number of documents to require several paid assistants. - It is hard to correct errors built into a survey or experiment. It is relatively easy to go back to the data in content analysis. - It permits both cross-sectional and panel analysis – the latter over long periods. - It is non reactive. The analyst has no effect on the object studied Disadvantages: - Evidently, it is limited to recorded communications. Speech may be of considerable interest, but unrecorded. - There are trade-offs in terms of validity and reliability, depending on the method used. But the possibility of returning to the material limits this weakness. - It should be easy for someone else to replicate the resea

Answer 70

They suggest ideas that the respondent would not otherwise have had. For some respondents, listing gay marriage as an “issue” may induce them to think of the matter as an issue for the first time. Some respondents with neither opinion nor knowledge of an issue may respond. Respondents may be irritated (and less likely to continue cooperating) if their desired answer is not a choice. They may have conditional attitudes on what constitutes an issue: for example whether or not they think national unity is an issue may depend on whether or not the Parti québécois is in office. It may be difficult to tell if a question is being misinterpreted. They force respondents to give simple (simplistic?) answers to complex issues. They force people to make choices they would not make in the real world

Answer 71

One of the major forms of research in the social sciences. They involve observations in a context where there are limits on experimental manipulation – for example, a lack of close control over the scheduling and targets of experimental stimuli; and/or where there is little control over the composition of groups so that randomization is impossible Common in workplace Time-series and equivalent time sample

Answer 72

Face-to-face interviews: advantages Higher responses rates than those produced by the other methods. There is likely to be a reduced number of “don’t knows” and “no answers” – interviewer training can reduce these. Questions can be clarified for respondents. There is the possibility of probing, to clarify responses. They can be used to reach a population without telephone or fixed residence. The interviewer can observer respondents and the setting in which the interview takes place – for example, the quality of accommodation. Face-to-face interviews: disadvantages This is a costly and time consuming method. Interviewer characteristics may cause bias. With respect to at least one person, there is no anonymity for the respondent.

Answer 73

a) Purposive (or judgemental) sampling: A sample that is selected based on the characteristics of a population and the objective of the study. Example: interviewing bankers to collect data on a study regarding banking. b) Snowball sampling: Relying on research participants to recruit other participants in the event that potential participants are hard to find. c) Deviant case sampling: Selecting or searching for highly unusual cases. Example: in the early days of HIV/AIDS research when infection almost always resulted in death, a small number of people infected did not die. We would use deviant case sampling to use these people in a study HIV/AIDS progression. d) Quota sampling: The assembled sample has the same proportion of individuals as the entire population with respect to known characteristics, traits, or phenomenon. Example: A researcher wants to compare academic performance of high school males and females across socioeconomic levels. Needs to create a sample that has proportions of males, females, and all socioeconomic statuses that reflect the true population (instead of randomly sampling in the high school). e) available subjects - eg students

Answer 74

We identify certain characters of a population and we sample to ensure that we get specified proportions of the population. Remember we divide the population into different parts. Possibility to over sample (if we want to say something about different languages- example we take 1000 adults, 10% of sample will be anglophone so our sample will include 100 anglophones, 200 allophones, 700 francophones- but because we can’t ensure we have that these numbers will be our sample because of the sampling error , so we will stratified the sample by language to make sure that our final sample includes the right proportions and get enough cases from the population group that is small). The next step is to oversample the smaller group - so 200 anglos, 200 allos, 600 Franco. Which improves the estimate of the anglophones, but makes the 600 less representative BUT **we gain more in precision from adding to the smaller group than we loose from taking away from the large group. If you look at all surveys, they are all stratified in a way that leads to the overrepresentation of smaller groups in the final sample**.)

Answer 75

Disadvantages: researcher bias. They suggest issues to people who previously did not consider those things to be issues. Respondent might respond about an issue they have no idea about. Research Methods is an extremely practical area so need avoid irritating the respondent, which could happen if an issue is missing on the list

Answer 76

a large part of the bread and butter

Answer 77

1. creating a data matrix 2. Cleaning the data 3. Preparation of a codebook for each question

Answer 78

Is there are no benefits, why should one agree to have any risk incurred ? Benefits might be just “understanding things better”- in that case you want to approve research that has little risks Does the research generate ‘benefits’? Clinical trials may yield an improved drug to treat one or another disease. Research on training programs may lead to better designed programs. What is the benefit of research on the causes of social revolutio

Answer 79

Disadvantages: - Not able to estimate the extent to which sample statistics are likely to differ from population parameters. We are limited in the ways that we can use the findings from the sample to say something about the broader population (unrepresentative). Relatedly, non- probability samples may also be biased in their estimates. However, non-probability samples may have considerable value.

Answer 80

Look up the characteristics to the people who drop out and then adjust the results according to that.

Answer 81

* *Advantages of phone surveys** - The cost tends to be moderate. There are hiring and training costs, but there are no transportation costs. - The personal characteristics of the interviewer are less likely to be identifiable – and to influence responses. - Respondents may be more likely to give socially disapproved answers over the phone than in person (but compare slide 23). - If the interviewer is located in a central office their work can be supervised, including the possibility that supervisors can answer interviewer questions. - Interviewers’ safety isn’t compromised. * *Disadvantages of phone surveys** - Evidently, the sample is limited to people with phones. For some time many samples were restricted to those with land lines. (The lack of cell phone numbers in most surveys in 2008 seems to have led to an underestimate of the vote for Obama in the US presidential election.) - Response rates are falling - When the telephone book was used to generate the sample, ex-directory telephones were excluded. Evidently, random digit dialing deals with this problem. - There is increasing suspicion of phone surveys because they are often used as a vehicle for telemarketing. - Hanging up is easier for respondents than the apparent face-to-face rudeness involved in refusing an interview in person. - The proliferation of answering machines and call screening devices makes it harder to get through to a respondent.

Answer 82

Is **history** a problem? No because there are no pretests between which external events can influence the observations. Is **maturation** a problem? Probably not, unless there are systematic differences in the two groups in terms of the time between the experimental effect and observations. Is testing a problem? No, because there is no pretest. Is **instrumentation** a problem? No, because the instrument ought to be used at the same time, in both groups. (So observers ought not to get more fatigued, etc. – though those in one group could be more fatigued to start with) Is **regression towards the mean a problem**? No. There is no pretest the results of which could have been influenced by random factors. Is **selection** a problem? It’s a big problem. The absence of pretests means that we have no way of knowing that the two groups were identical before the experimental effect. Is **mortality** a problem? It may be. Suppose we are interested in the effects of a college education on attitudes. We compare the attitudes of freshman and seniors. In other words, X is enrolment in college, O1 is attitudes of a sample of seniors, O2 is attitudes of a sample of freshman. Evidently, the composition of the groups is likely to have changed since some students are likely to have dropped o

Answer 83

Internal Validity: H: not addressed. Clearly, subsequent observations may be influenced by extraneous events. This would be a particular problem if the extraneous events occurred between O4 and O5 M: may be a problem. But mostly it wont be a problem because the relevant changes should show up at other consecutive points T: It could but the effect would not show up suddenly at O5 I :It could but the effect would not show up suddenly at O5 RTM: no because they would do better on O2 but also on O3 and on O4 S: not a problem because there is one group M: possible if you take a workgroup, some may quit and be replaced External Validity: All 3 factors are a problem

Answer 84

**Reactive Effect of Testing :** design includes pre-test, members were test which causes a possible problem because it is possible that the stimulus only operates where the pre-test in present. Our results don’t allow us to exclude the possibility that the interval validity operates because of a pre-test. Clearly that does not allowed to a general population that did not experience a pre-test. The causal factor depends upon the pre-test. **The interaction effects of selection biases and the experimental variables**: For example, if I’m interested in teaching styles in schools. One would take the classes most available, would not usually draw a sample across Canada. Supposing for that classroom, I present an internally valid result, can we generalized what happened in a Montreal classroom to classrooms across the general population? If we were looking at language, the effect found might have been resting entirely on the kind of classroom in our sample- the same results may not be possible in a Toronto classroom. **Reactive Effects of experimental arrangements:** Results might only be present where artificial characteristics of the experiments are present. (ex: observers in a classroom undermines the potential generalizably of the research )

Answer 85

Advantages: Save on transportation costs (consecutive sampling in order to focus the cases within the limited areas) Deal with the issue of list

Answer 86

Normatively approved behaviour is substantially overreported. Normatively disapproved behaviour is strongly underreported. Interview method has little association with over- and underreporting. The only reasonably clear result on underreporting suggests that self-administered questionnaires yield a bit more underreporting than the other two methods.

Answer 87

- Evidently, memory is a problem; people may be being asked about things that occurred some very significant period of time previously. - The availability of alternative sources helps in this respect. - The perceptions and evaluations of the respondent may be more important than the facts. - The selection of cases is often problematic. Consider Studs Terkel‘s Hard Times. Cases were selected consistent with Terkel‘s broader world view, and to be interesting. - Where oral history is constructed for the purposes of a court case it is reasonable to expect some confusion between the interests of the person from whom information is collected and the accounts provided

Answer 88

What issue does it raise ? Reliability vs Validity Taking the number of time a certain word comes up in a movie- simply counting words can be misleading because a horror film can have “romantic” words in it Embedding of the word may change what they mean

Answer 89

In research, we want to know assess population parameters (the true value of a population’sattribute). To do this, we must gather data from samples. This inherently means there is going to be some sort of sampling error (i.e. what we find in our samples is not going to perfectly reflect what is happening in the true population). Inferential statistics (inferring population properties using sampling data) constitutes an attempt to account for sampling error. One such method is using confidence intervals which represent a range of values that bracket the true population parameter.

Answer 90

x0 O0 x1 O1 x0 O0 x1 O1 ….. -x is introduced then reduced, then introduced and so on .- For example, in a study of the effects on output of adding music to a work environment, the music was introduced then withdrawn 51 times. -In principle, the effect should be introduced at random intervals to avoid coinciding periodicities.

Answer 91

One on one – semistructured interviews. One on one – structured interviews. Focus groups. Oral history. **Strengths** Respondents play a larger role in determining the content of the interview. This means that their views are more likely to be faithfully represented. There is the possibility of unexpected topics being raised. These unexpected topics may provide the basis for new theorizing **Weaknesses** The very rich, descriptive, data yielded by the interviews is often hard to analyse. Software described by B&R considerably helps with this. Since each interview is a different conversation reliability is an issue. The ‘measurements’ (so to speak) of other researchers examining the same subject are unlikely to tap exactly the same thing. Nor, for that matter, need consecutive interviews by the same researcher. Qualitative interviewing necessarily involves small samples, so generalization is likely to be a problem

Answer 92

**Are internal validity issues addressed?** History: yes. there is no pre-test Maturation: yes. there is no pre-test Testing: yes. no pre-test Instrumentation: yes. instruments are used at the same time in both groups. Regression towards the mean: yes. there no pre-test so cant select ends of the distribution. Differential selection: no. we don’t know if the two groups are the same. Experimental mortality: no. \*example: x(liberal college), O1( seniors- progressive attitudes), O2 ( freshman- diverse views) - can’t infer because maybe the conservative students simply left the college.

Answer 93

The challenge is to structure the research in a way that allows analysis ... - Read the literature to get ideas about what to expect in one’s findings. - Take extensive notes (pictures, maps, whatever) which constitute your data. - A way to analyses these data: so-called ‘grounded theory

Answer 94

Coding responds to this by taking 2 forms : Manifest coding — simply counting words Latent coding — identify meanings \*problem of reliability in terms of latent coding but somehow higher validity Using both as a solution

Answer 95

In contrast to experimentation, they typically gather data on a large range of subjects, allowing exploration, description, or the testing of explanations for a range of subjects (sometimes within some broad theme) Why do they gather data on a large range of subjects? **i)** multiple items may be needed to construct indexes and scales; **ii)** hypotheses may be formulated without sharply defined operationalizations – a survey that contains multiple items allows the exploration of alternative operationalizations of concepts and the development of Guttman scales; **iii)** once you’ve contacted a respondent and got his or her agreement to answer questions it makes sense to get as much interesting information from the respondent as possible Depending on the character of the survey, they can be used for each of the research purposes we discussed earlier: they can be exploratory, descriptive, or explanatory

Answer 96

Have to come to terms with the fact you are dealing with multiple sample errors. It is likely that the acuteness of the problem varies across sampling units which is related to the dispersal in the underlying population. We address that problem by oversampling of the level where there is most heterogeneity. That level is most often at the primary sampling level. (Sampling error in a cluster is 3 compare to a EPSEM - one sampling error)

Answer 97

**Are Internal Validity issues adressed ?** History: no. did outcome from X or from something else ? Maturation: no. no way of knowing wether the change in the observations was produced by some change in the subjects Testing: no. nothing tells us if the pre-test produced the result Instrumentation: no. Regression towards the mean: unless we had other conditions to the design (taking not only extremes), no. Differential selection: not relevant because only 1 group Experimental mortality: not relevant because only 1 group **\*\* so the design is vulnerable to every single threat to internal validity**

Answer 98

reactive effects of testing : It **may** be that the effectiveness of the training depended on the previous testing experience. That is, X only produced a change from O1 to O2 because it was introduced after O1 interaction effects of selection biases and the experimental variable : we cannot rule out the possibility that the experimental effect will only be present for students of the sort contained in the study reactive effects of experimental arrangement: artifical characteristics are still present. for example, the specialness of the context leads participants to try harder, or less hard. To the extent that this is the case it would make the generalization to the wider (comparable) population problemati

Answer 99

They use existing data: Hamilton – voting records by district. Reitz – the Census. Little – colonial records, the Census manuscripts, church records. They take rather general claims (middle class panic and support for the far right, immigration policy and migrant performance, culture and behaviour) and test them, exploiting historical or international comparisons. There are methodological problems: Hamilton – ecological fallacy; Reitz, the limits of the Census for the estimation of wage determination; Little – the fragmentariness of records (the Scots may not always have involved the Church in burials, a church burned and with it some recor

Answer 100

One on one – semistructured interviews. One on one – structured interviews. Focus groups. Oral history

Answer 101

She analysed the rationalization of the health care system “from the viewpoint of the nursing assistants“. That is to say, she started having observed cost-cutting in the health care system deciding to examine its implications for nursing assistants responsible for long-term care residents – a poorly paid group of employee

Answer 102

R O1 x O2 R O3 O4 R x O5 R O6 -Allows to compare the size of the effect but allows the challenge of reactive effects to be eliminated

Answer 103

A sampling method refers to the way that observations are selected from a population to be in the sample for a sample survey. The quality of a sample statistic (accuracy, precision, representativeness) is strongly affected by the way that observations are chosen (i.e., the sampling method).

Answer 104

Personal characteristics: e.g., gender, marital status, educational level, religious affiliation, income. How people classify themselves: e.g., self rated class, political affiliation. Individual’s behaviours (e.g., church attendance, purchases by consumers, alcohol consumption) , attitudes (e.g., authoritarian attitudes, social distance, the EU flag) and beliefs (about the causes of inequality, the behaviour of minorities, the Expectations: e.g., expectations of senior managers with respect to future sales. Knowledge of an issue: e.g., what do people know about their government

Answer 105

Low response rate. There may be bias: only people who feel strongly about an issue may be answering. It is not possible to probe in order to clarify respondents answers. Questions cannot be explained. They do not yield information about the physical or psychological condition in which the person filled out the survey.

Answer 106

you ignore issues of dispersal

Answer 107

Was it worth it? Benefit-cost analysis _Benefits and costs to governments_ Administration costs: head office, MIS, employability assessments, job matching, job-readiness and generic skills training, administration of transitional jobs and the economic resource centre, support for the planning and development of community boards plus the payments to participants along with their EI and Worker's Compensation contributions. _Benefits_: taxes and premium revenue - increases in taxes paid by program participants and EI, CPP premiums paid for them. _Benefits:_ transfer payments - the incomes of participants meant that less of them qualified for Canadian Child Tax Benefits, Child Benefit Supplements, Nova Scotia Child Benefits, and GST credits. The program had benefits and costs for governments, communities, individuals, and the non profit organizations for whom the participants worked. The ratio of benefits to costs needs to be calculated across this set of entities/individuals affected by the program. _Benefits and costs to individuals:_ Total income Income stability Expanded social networks Minus foregone leisure time _Benefits to communities:_ Increased volunteering Increases in social capital Increases in social cohesion

Answer 108

- History: yes. Because you are comparing to a control group. Whatever other factor that could influence must have been present for both groups. - Maturation: yes. The two groups mature at the same rate. - Testing: yes. Both groups have a pre-test so there should not be differences between the two groups resulting from testing. - Instrumentation: yes. The observer mature at the same time. - Regression towards the mean: yes. there should be regression towards the mean in both but if one is larger we can see the size of that effect is. - Differential selection: yes. Because we’ve randomly selected the members and we’ve dealt with the sample error using inferential statistics. - Experimental Mortality: no. x might have an effect on the willingness of people to remain in the study (positive or negative)

Answer 109

Put sensitive questions in the latter part of a questionnaire, on the assumption that the respondent will by then have developed a rapport with the interviewer and/or has becoming committed to completing the interview. Formulate the question in a way that might put the respondent at ease. If the issue is homosexuality, instead of “Have you ever had sex with another male?”, “In past surveys, many have reported that at some point in their lives they have had some type of sexual experience with another male. This could have happened before adolescence, during adolescence, or as an adult. Have you ever had sex with another male?” Make an action seem less deviant by embedding a question about it in questions about other, more serious, issues. For example, people may be more likely to report shoplifting if the question on shoplifting comes after a question on armed robbery or burglary.

Answer 110

Institutional ethnography - looking at people in disadvantaged position is political -take side or literally help (with participatory research)

Answer 111

The reason for conducting a sample survey is to estimate the value of some attribute of the population. A population parameter is the true value of a population attribute. A sample statistic is an estimate (e.g. mean, standard deviation, etc.), based on sample data, of a population parameter. We use a sample as a way to estimate the attribute of the population.

Answer 112

The square of r (r2) = 0.71 and is interpreted as the proportion of the variance in the dependent variable (number of children) explained by the independent variable (years of education). You can think of it as a measure of the reduction in error in predicting the dependent variable score as a result of knowing the independent variable score

Answer 113

Social organization in a public housing projet 1. It provided an in-depth understanding of the social relations in the low income area. 2. The researcher either did not (or didn’t need to) impose her presuppositions on the subjects. 3. This is true because relevant concepts and theories could be developed during research. 4. It was possible for her to develop empathy with her subjects which is likely to increase the range of subjects on which information can be elicited. 5. The validity of the measurements should be high. The rich documentation should make it possible to establish very strong links between concepts and observations. 6. Some research can only be done using qualitative methods (e.g., on biker gangs, religious groups that feel stigmatized, closed communities like prisons). It would be difficult to shed light on welfare fraud, as the researcher did, using quantitative method

Answer 114

a) The sampling distribution will have the same mean as the population from which it is drawn b) The dispersal of the sampling distribution \< dispersal of the population from which samples were drawn c) Distribution of sampling distribution tends to normality, even if the population from which is it drawn is non-normal

Answer 115

article 21 of Quebec civil code says not children or incompetent ad

Answer 116

-Imperial China collapsed in 1911. It had been weakened by i) foreign intrusions in the 19th century and a loss to Japan in the 1895-96 war; ii) an incapacity to increase tax revenues; iii) a growth of population that weakened the grip of a static Imperial bureaucracy; iv) related to the previous points, an Imperial army that had been incapable of putting down local revolts, which encouraged local elites to create their own militias.- The Imperial government was not replaced by an effective alternative. In fact, China was divided among warlords.38 - There were social bases for two rival, national, political movements: the urban areas for the Kuomintang (KMT) and the rural areas for the Communist Party (CCP). - Chiang Kai-shek was incapable of consolidating KMT control (a split between the left and the right of the party, the decision to turn over important tax revenues to local and provincial rulers). - The Japanese invasion in 1937 undercut the KMT because the Japanese occupied the urban areas. - After the defeat and withdrawal from China of Japan the CCP was the best organized alternative centre of pow

Answer 117

Used when you want to ask several questions that have the same set of answer categories (e.g., course evaluations). Advantages : Saves questionnaire space. Saves respondent’s time and prevents respondent fatigue. Disadvantage : Respondents may provide a response set: that is, they might stop reading the questions carefully and answer all questions in a general pattern.

Answer 118

in the elaboration model : after adding the test variable the partial relationships become different from the zero-order relationships. **Grades, note-taking method, and Facebook participation** percentage point difference is 25; there is clearly a zero-order relationship between note-taking method and grades. Does the table settle the issue of causation? People who use a computer for note-taking may also use it for other purposes – say, social networking. So: control for Facebook users The percentage point difference for Facebook users is 32. The percentage point difference for Facebook non-users is 7. The percentage point difference before controlling for Facebook use was 25. Adding the control generates partial relationships that differ from the zero-order relationship: the relationship between grades and note-taking method gets stronger for Facebook users and weaker for non-users

Answer 119

Concordance means that, for any given pair of cases, one of the pair ranks higher on both variables and the other ranks lower on both variables. Discordance means that, for any given pair of cases, one of the pair ranks higher on one of the two variables but lower on the other and the other of the pair also ranks higher on one of the two variables and lower on the other

Answer 120

The series of pretests might well influence the effect of the stimulus. **Reactive effects of testing**, then, may be a problem. A study of schoolchildren involving repeated observations of behaviour may have to be limited to those who had perfect attendance records. They are unlikely to be typical of the school population. There is, then, a risk of **interaction effects between selection biases and the experimental variable.** Quasi-experimental designs tend to involve groups that are naturally created (a class, a workgroup, etc.). As such, they imply less artificiality than experiments. However, the stimulus may have an artificial character; so there is a **possibility of reactive effects of experimenta**l arrangement

Answer 121

Life satisfaction scale : 1. Income increases life satisfaction (each 1000$ increase satisfaction by 1 scale unit) 2. More social capital increased life satisfaction (1 scale unit of social capital increased life satisfaction by 1 scale unit) Found that social capital also increased life satisfaction 1 scale unit of social capital increases life satisfaction as much as 1000$ income increase What can we conclude : try to find ways to transfer with values that are not in dollars in dollars

Answer 122

Different kinds of respondent give different degrees of detail in answers (the articulateness/literacy issue). Responses may be irrelevant or contain useless detail. Coding responses is time-consuming and costly. The range of responses, and forms of responses, may make difficult comparison across respondents. If the questionnaire is administered by an interviewer it may be difficult for the interviewer to write down the answer (accurately)

Answer 123

Do interaction effects of selection biases and the experimental variables? Yes a problem. The effect might just be for the members of the experiment. [But if you have a well constructed sample ( no instance of Montreal/Toronto issue), it can be avoided.] Did the Pre-test influence the result ? Not a problem. No pre-test. Artificial context of the experiment? Yes a problem. The artificial characteristics are present.

Answer 124

They allow respondents to raise issues that the researcher didn’t think of – that is, they make possible unanticipated findings. Respondents can answer in detail and include conditionalinformation. They may reveal a respondent’s logic, thinking process, and frame of reference. (But this may depend on respondent articulateness/literacy.)

Answer 125

Use the interest rate to adjust future income to a present value. Assume that the interest rate is 10% year 1 2 3 4 Costs 50 0 0 0 Benefits 50 150 150 150 In year 1 = benefits are 50 In year 2 = 50 reduced by 10% so 50 x0.9 In year 3 = 50 x 0.9 x 0.9 In year 4 = 50 x 0.9 x 0.9x 0.9 Total benefits before discounting = 500 SO 500/450=1.1 Total benefits after discounting = 415.85 What have we done by discounting ? Benefits no longer exceed the costs. They fall behind

Answer 126

- Personal characteristics(age, gender ..) - How people classify themselves (self-rated class), - Personal characteristics(age, gender ..) - Behaviour (purchase, attitudes[social distance, authoritarian leaders..] , church attendance), - Beliefs - Knowledge of an issue - Expectations

Answer 127

Grounded theory. “the attempt to derive theory from an analysis of the patterns, themes, and common categories discovered in observational data”. The theory, then, is built out of the observations. (This may be a bit inaccurate. It is hard to imagine a researcher going into the field with no expectations about what might be found or literature-inspired ideas about what information to look for.) Grounded theory has a set of tools: 1. theoretical saturation - stop making observations when the most recent series of observations add nothing to the researcher’s capacity to construct an explanation. 2. constant comparison – each time a form of behaviour is assigned to a category compare it with the other behaviours in the category to make it possible to produce a theoretical interpretation of the category; 3. coding – the categories to which data are assigned emerge from the observations (but are these groupings possible without initial ideas?)

Answer 128

elaboration model in which, after adding the test variable the association between the two variables of interest is little changed **Political affiliation influences attitude to gay marriage** The percentage point difference is 27; there is clearly a zero-order relationship between political orientation and attitude towards gay marriage. Does the table settle the issue of causation? It is possible that the relationship is spurious. For example, men and women may differ in both their party preferences and in their attitudes to issues related to gays. So: control for gender The percentage point difference for men is 27. The percentage point difference for women is 23. The percentage point difference before controlling for gender was 27. The association between political orientation and attitude remains the same or about the same after controlling for gender (though women do have more favourable attitudes than men) – that is to say the partial relationship after adding a test variabl

Answer 129

Post-test only control group design adresses all the problems of internal validy and reactive effect of testing

Answer 130

- It is unobtrusive! This eliminates problems like, interviewer effects (interviewer characteristics), and role effects (respondent decisions on how to present himself or herself to the interviewer). - But there may be the problem of which traces survive. What persists longest in middens (shells!)? To what degree are survivals different in tropical and Arctic middens? - Physical evidence alone does not tell us about the population leaving the traces. Did children cause the tile wear at the chick exhibit? Were the Wellesey liquor bottle totals produced by a large number of people producing a small number of bottles or a small number of people producing a large number?

Answer 131

Scatter plot helps us to notice outliers Orderly square values have a disproportionate effect of the analysis you will generate Are your results produced by extreme values ?

Answer 132

all the problem internal validit the problem of reactive effect of testing

Answer 133

The competing risks are that not including them will force respondents who don’t have an opinion on something to express an opinion versus allowing respondents who do have an opinion to opt for one of these ‘non attitude’ or ‘middle’ responses. The alternative ways of approaching this issue involve standard format questions, quasi-filter questions, and full filter questions.

Answer 134

R= randomization which deals with how we constitute the groups we study. Randomization= number table and assign people based on the number generate

Answer 135

correlation has the same character as gamma: it varies from +1 (perfect positive association) through 0 (no association) to -1 (perfect negative association

Answer 136

Are interaction **effects of selection biases and the experimental variables** addressed? no. The effect might just be for the members of the experiment. Is the pre-test influence on the result addressed ? Yes. necessarily because it is present in both groups. Are the artificial context of the experiment addressed ? no. The artificial characteristics are present.

Answer 137

Open coding - this is the first attempt to make sense of a body of data. It develops themes from observations. Axial coding – “a set of procedures whereby observations are put back together in new ways after open coding, by making connections between categories” (Strauss and Corbin, Basics of Qualitative Research, 1990). So, coded behaviour might be linked to contexts, consequences, and causes. Selective coding – “the procedure of selecting the core category, systematically relating it to other categories that need further refinement and development” (Strauss and Corbin, ibid.)

Answer 138

unobtrusive (or non-reactive) research methods - Analysis of existing statistics. - Content analysis. - Historical and comparative research. - To these can be added various kinds of unobtrusive observations

Answer 139

**1.** Avoid jargon, slang, and abbreviations. Target the vocabulary and grammar of the respondents sampled. (Evidently, the vocabulary used might vary with the educational level of the population being studied.) **2. A**void ambiguity, confusion, and vagueness. (eg: What is your income? (Time period? Before or after tax?) Do you exercise or play sports regularlly .. ) **3.** Emotional language. “What do you think about a policy to pay murderous terrorists who threaten to steal the freedoms of peace loving peoples?” tends to invite a negative response. 4. Prestige bias. “Most doctors say that cigarette smoke causes lung disease for those near a smoker. Do you agree?” may elicit agreement because people defer to the judgment of doctors rather than because they have any views on the effects of second hand smoke. 5. Being double-barrelled. “Does this company have pension and health benefits?” should generate yes answers from people whose company have both, no answers from people whose company has neither, and confusion from people whose company has one but not the other. 6. Confusing beliefs with reality. A researcher hypotheses that teachers who tell jokes get rated higher. The question “Do you rate a teacher higher if the teacher tells many jokes?” asks the respondent to express a belief about the basis for their rating of teachers. But the hypothesis is better tested with two questions: “How do you rate teacher X?” and “How many jokes does teacher X tell in class?” 7. Leading questions. “Should the mayor spend even more tax money trying to keep the streets in top shape?” invites a negative response whereas “Should the mayor fix the pot-holed and dangerous streets in our city?” invites a positive response. 8. Exceeding respondents’ capabilities. Few respondents will feel comfortable answering this question: “How many litres of gasoline did you buy last year for your car?” They might do better with a question on “gasoline purchases in a typical week” the response to which can be multiplied to get annual consumption. 9. False premises. “The post office is open too many hours. Do you want it to open four hours later or close four hours earlier each day?” A respondent may not share the premise contained in the first sentence. A better formulation might be: “If the post office has to cut back its operating hours, which would you find more convenient, opening four hours later or closing four hours earlier each day?” 10. Soliciting intentions in the distant future. “Suppose a new grocery store opened down the road in three years. Would you shop at it?” is unlikely to generate a useful response. 11. Double negatives. Suppose you have the following statement: “Students should not be required to take a comprehensive exam to graduate”, followed by a strongly disagree to strongly agree Likert Scale. This implies a double negative: those who would prefer the comprehensive examination have to disagree with the statement, because it contains not. 12. Overlapping response categories. These numerical categories overlap: 5-10, 10-20, 20-30, and so on. A verbal equivalent is the following: “Are you satisfied with your job or are there things you don’t like about it?” because a respondent may be able to check both of these options 13. Unbalanced response categories. “What kind of a job is the mayor doing: outstanding, excellent, very good, or satisfactory?” excludes a range of negative judgments.

Answer 140

Web surveys: advantages The cost of data collection is very low. If the web site is set up appropriately the data can be very cheaply extracted and analyzed. People may feel more confident giving truthful answers to sensitive questions. Web surveys: disadvantages Response rates are very low. Samples are restricted to the online population and therefore unrepresentative – but this problem is diminishing over time. Respondent privacy will be vulnerable unless the person designing the web site or sending the e-mail messages takes steps to prevent it – by encrypting information and designing a secure web site. The effectiveness of questionnaire design may be compromised by the equipment and software used by the respondent. Nonetheless, there is some evidence of improved performance in recent voting intention surveys.

Answer 141

Government statistics - Large government bureaucracies collect data. - Durkheim found national statistics on suicide. - Governments keep records on the incidence of different kinds of crimes. - Most governments have Censuses that publish data, mainly on web sites now. - The same is true of the results from the many Statistics Canada surveys that we listed in the previous section (as well as many other Statistics Canada surveys). These yield information on, for example, health, the state of the labour market, educational levels, and so

Answer 142

Standard Format: Here is a question about another country. Do you agree or disagree with this statement? The Russian leaders are basically trying to get along with America. Agree or disagree?

Answer 143

- The movie Valkyrie - based on historical research by Peter Hoffman – dealt with a 1943-1944 plot to kill Hitler. - Claus von Stauffenberg, one of the leaders was about 40 as the plot was developed and implemented. - Had he not been executed, he would have been in his early 80s by the late 1970s, early 1980s. - The same would have been true of some of the others involved in the plot. - Due to the large number of executions when the plot failed, the plotters did not survive. - But some family members did survive – and they could be interviewed to supplement information from official and personal documents

Answer 144

History. We’re focussing on changes after X. The members of the two groups should be influenced by the same events between the first and second observation Maturation. The two groups should have experienced the same natural changes – aging, getting more fatigued, or whatever. Testing. Each group experiences a pretest. So a difference in scores from pretest to posttest in one group that isn’t present in the other can’t be a result of test experience. Instrumentation. The time lags are the same for the two groups. So, for example, observers, test readers, should have the same experience between the two points in time Regression towards the mean. Even if the groups are selected from extreme cases (those who failed a test, for example), there should be equal amounts of regression towards the mean in the two groups. So a difference between the groups in the change in test score can be attributed to the stimulus. Selection. This is not a problem because the comparison groups are populated randomly. (Evidently, there is a role for inferential statistics here. Mortality. There may be differential mortality between the two groups, possibly influenced by the experimental effect. The pretest makes it possible to examine the effect of mortality by looking at the characteristics of drop-outs. For example, did they have systematically lower test scores than did non drop-outs? If they did, we can consider how that might have influenced the results. The pretest makes this possible

Answer 145

- **Physical harm to subjects is uncommon**, but possible. For example: i) research on ‘rough and tumble’ play in schools; ii) if a study causes stress, there is the possibility of adverse effects, including a heart attack; iii) if the identity of an informant is released it might provoke physical retaliation from someone who feels that the information provided by the informant harms that person in one way or another. - **Psychological abuse, stress, or loss of subject self-esteem** are a more common problem. Here are examples of procedures used in social research: i) the exposure of subjects to gruesome photos; ii) falsely telling male subjects that they had strong feminine personalities; iii) falsely telling students that they had failed; iv) creating a situation of high fear (e.g., smoke entering into a room with a locked door); v) asking participants to harm others (Milgram); vi) placing people in situations where they were pressured to deny their convictions (Gamson and Rytina) - There is the possibility of **legal harm to subjects**.Research on the police has turned up evidence of police beatings of people arrested, illegal behaviour, and irregular procedures.Russell Ogden, a Master’s student at Simon Fraser University, studied assisted suicides among people suffering from AIDS. His research protocol, approved by the SFU Ethics Committee, guaranteed participant confidentiality. He was subpoenaed by the Coroner’s Court to give evidence on a particular case and threatened with a contempt of court charge if he didn’t give evidence. - Other harms to participants.Suppose a researcher found poor morale in a department in a firm. When the result is published the **career of the supervisor of the department may have been damaged**. Foster’s study of a British housing estate revealed some amount of welfare fraud. Suppose that the relevant **government department became aware of the results** and tightened the administration of welfare rules - There is the issue of **deception**.Some experimental research depends on deception. This was true of Milgram’s work as well as Gamson and Rytina’s. Also, access to a research site may be impossible without deception – as in Lauder’s study of an extreme right wing group, the Heritage Front.Subject’s are supposed to give informed consent. How can their consent be informed if deception is involved? The usual answer is provide a broad discussion of the objectives of the research then debrief after the research is completed.Deception may damage social science by bringing it into disreput

Answer 146

it lacks a pre-test ?

Answer 147

Gama = comparing concordant and discordant pairs of cells scores ``` Concordant = For any pair a case ranks higher on both variables or lower on both variables Discordant= Ranking lower on one and higher on the other ``` Employment experiences shape people’s attitudes We want to identity concordant and discordant pairs. What is the total number of concordant pairs ? 65 ( 2+3+6+3) + 14 (3+3) + 14(6+3) +2 (3) = 1126 concordant pairs in the table 54 (2+14+3+26) + 14(14+26) + 6(3+26) + 2(26) = 3216 discordant pairs Gama = (c-d)/(c+d) = -0.481 What does a negative number tell us ? There is negative relationship, as the number of weeks rise, so does the hostility towards revolution. If there are more concordant pairs, we get a positive value We get a score that reflect the relationship in the table If the number of c and d are the same, it means that knowing scores on the independent variables doesn’t not help us knowing scores on the dependent 1= perfect negative 0 = no relation 1= perfect relationship

Answer 148

Landa : (E1-E2)/E1 E1= number of errors without knowledge of the independent variables E2 =number of errors with knowledge of the independent variables E1= 55 E2 = 24 55-24/55= 0.564 Supposing we made 0 classification error knowing scores , what is E2 ? 0 so Lanhda=1 If the variables are perfectly associated, Lanhda = 1 Suppose that number of classification does not change so E1=E2 , what happens ? Landa = 0, if there is not association, landa=0 Measure association that tells us 0= not association, 1 = associate 0.564 = reduction of error from knowing independent variables

Answer 149

Where possible is always better than matching because random assignment deals with unobservable as well as observables. When matching, there might be unobservable characteristics not part of the matching process which influence the result, you get a distribution within the two groups taking into account both kinds of characteristics.

Answer 150

positive relation negative relationship to the extend that they cluster along a diagonal

Answer 151

The more traditional research model i) implies a gap between the researcher and the subject of the research – each has separate objectives; and ii) usually aspires to something like objectivity. (Evidently, institutional ethnography diverges from this latter aspiration.) An alternative approach: allow the subjects of the research to define the object of research – which will usually be concerned with something they define as a problem to be solved or objective to be attained; then, in consultation and collaboration with the subjects the researcher designs the research in a way that is designed to help the group achieve its objective(s). This may be considered an explicitly political form of research

Answer 152

Replication : when we end up with the same results (same % point differences) in the two tables Specification : when different patterns for different levels of the controls We can add a control and a relationship might disappear -\> either interpretation or explanation x and z + control variable If Interpretation : x —\> y —\> z Explanation : Y—\>x \ y

Answer 153

- They all intrude to some degree in the subject of study. - The concerns with experimentation are challenges to internal and external validity, each of which may be compromised by the experimental intervention. - Similar concerns are posed by survey research: Do questions cause someone to think about a problem for the first time? Do closed-ended questions, without filters, force respondents to express opinions that they don’t actually hold? Are responses shaped by concerns about conforming (registering to vote) or reporting norm violations (drunk driving)? If an interviewer develops rapport with a respondent, will that rapport influence the answers provided? - It is likely that gang members, those living in public housing units, and work groups change their behaviour when in the company of a qualitative research

Answer 154

pre-experimental designs, characterized by the absence of an adequate control group lack of randomization

Answer 155

A normal distribution with a mean of 0, standard deviation of 1.

Answer 156

Ewan Cameron and ‘brainwashing’ experiments - During the Korean War the CIA became concerned with alleged Soviet, Chinese, and North Korean use of ‘mind control’ techniques on captives. - During the 1950s and early 1960s it funded psychological research that it thought might improve its capacity to understand these techniques – including research by Ewan Cameron, at the Allan Memorial Institute. - The research took the form of a series of aggressive treatments applied to patients with a range of psychiatric conditions, including depression, designed to clear a person’s memory and introduce new content. - The treatments included: i) more intensive than usual electroshocks, administered more frequently than usual; ii) administering drugs to induce prolonged periods of sleep (up to three weeks); iii) taped messages were played to patients while they slept – criticizing the problematic personality traits, sometimes providing an electric shock at the end of the message, and then, later, praising positive traits. **The ‘brainwashing’ experiments: ethical issues** - Cameron was using patients as research subjects without securing their informed consent. - As a result of this, treatments were much more radical than warranted by the condition of the patient were adopted. - There is a fairly widespread view that the science that led to the treatments was flawe

Answer 157

Method of agreement : - ABCD wxyz - AEFG wtuv What can we conclude : A is associated with W (A is causal to W) If A is a state collapse and W is a social revolution- A is cause to W Method of difference -ABCD wxyz -BCD xyz What can we conclude : causal relation between A and W explained by difference Studies to explain chinese revolution - French revolution **Problems:** Falsification. The test itself is not very powerful. Reduced by the very small number of cases. is it likely that the only thing different is A ? Great difficulty controlling for anything where we only have two cases. Historians may well have operationalized concepts in ways that are different from each other. Who is the gentry, the middle class, the proletariate, an urban versus a rural resident? The historian probably used documents as a data source. How he or she sampled/selected them may not be clear

Answer 158

Yes, by looking up the characteristics to the people who drop out and then adjust the results according to that.

Answer 159

Full filter: Here is a statement about another country. Not everyone has an opinion on this. If you do not have an opinion, just say so. Here’s the statement: “The Russian leaders are basically trying to get along with America.” Do you have an opinion on that? If yes, do you agree or disagree?

Answer 160

Example of the use of the experirentntal method in sociology : Employment and Incarceration - Pajer - effect of incarceration and employment (the likelihood of finding a job) - effect of race on the incarceration and the likelihood of finding a job How to look at it with an experimental methods ? - generate new data by putting people in “situations” of unemployment - get a bunch of people put together cvs and observe how many call back they get 1. college age male tester 2. they applied for entry level jobs, advertised in newspapers 3. Divide two race categories (white, black) and two categories ( incarcerated, non-incarcerated) 4. matched the 4 samples in terms of appearance, presentation, style and so on People with a criminal record are less likely to be offered a job Blacks were less likely to be offered a job White tester with a Criminal record were more likely to get a job than black without one

Answer 161

Problem with Systematic Sampling: Are there periodicities built into the list ? suppose we select every 4th person on the list with a random start of 2, you only gets wives because they are even number.

Answer 162

nominal variables= Lamdda Ordinal Measure= Gama Interval or ratio = Correlation and Regression

Answer 163

And, even more extreme, if a relationship is apparent in the zero-order table and that relationship is reversed in the partial tables, the relevant test variable is a distorter.

Answer 164

Pre-experimental design #2 (o1, x, o2) o1= pre-test o2= post-test

Answer 165

In aboriginal community in the Northwest Territories sought to i) document traditional justice practices and principles of the Dene Nation with ii) the possibility of reviving it and using it to replace the Canadian justice system. The research highlighted the differences between Dene and Canadian justice: the former emphasized i) group harmony and ii) harmony of the group with the environment; the latter emphasized individual rights. An interesting example of the clash of legal systems was presented by the ‘not guilty‘ plea. In the small aboriginal communities studies whether or not someone was guilty was pretty clear. In addition, the objective of the community was to resolve the conflict rather than to punish. In contrast, in the Canadian justice system lawyers would emphasize clients’ individual rights, often by getting their clients to plead not guilty at the beginning of a trial Widespread alcohol abuse would have to be dealt with were the traditional justice system to have a chance of success. Presumably this was because the solution of various alcohol-related problems required withdrawal from alcohol; mediation could not produce a satisfactory outcome without that. A community justice committee should be established to examine the relative effectiveness of Dene and Canadian legal principles in dealing with community problems. Insofar as participatory action research involves real actions (as opposed to recommendations) it might be considered a kind of pre-experimental design – the one group pretest-posttest design, but with rich data

Answer 166

It does not deal with the other two sources of external invalidity: interaction effects of selection biases and the experimental variable and reactive effects of experimental arrangements

Answer 167

Interviews involve the creation of a social relationship. Evidently, the interviewer attempts to encourage cooperation, which will normally require that he or she be non judgmental . The interview process will involve the use of probes – neutral requests to clarify ambiguous answers, to complete an incomplete answer, or to get a relevant response. Some interviewing is now conducted using computers as a source of questions, with responses being directly entered. This brings the advantage of CATI to face-to-face interviews. It is reported that only about 35% of the interviewer’s time is spent interviewing. 40% is spent locating the correct respondent, 15% travelling, and 10% dealing with survey materials and dealing with administrative and recording details (Moser and Kalton, Survey Methods in Social Investigation, 1972).

Answer 168

- An advantage of questionnaires administered face-to-face or by telephone is that both methods allow clarification and probes. - Clearly, this is even more the case for qualitative interviewing. - Beyond this, the interview can allow subjects to emerge: that is, the questions don’t have to be predetermined. The interviewer can improvise questions in response to what the respondent says. - This does not mean that the interview has no structure even though some qualitative interviews are described as ‘unstructured’

Answer 169

Respondent satisfaction (and cooperation): they’re easier for respondents to answer. The data are easy to code and analyze. Forcing responses into a standard format makes responses easier to compare. The response choices themselves may clarify the meaning of a question – for example, by providing a list of issues the meaning of the word “issue” in the example in the previous slide is made clear to the respondent. There is some evidence that, in this format, respondents are more likely to answer questions on sensitive issues. Less articulate/literate respondents are not as disadvantaged. Replication and comparison in future surveys is easier

Answer 170

A normal distribution, sometimes called the bell curve, is a distribution that occurs naturally in many situations. - Symmetrical - Bell-shaped (i.e. unimodal, has one curve) - Mean, median, mode are all equal and are located at its peak - Can having varying standard deviations (smaller standard deviation = narrower bell) - Tails are asymptotic to x-axis (they approach the axis but never touch)

Answer 171

Equal property of selection (EPSEM): SRS without replacement which is more suited to social sciences Ways to generate this kind of sample: Table of random numbers (we assign numbers to the population we are interested in, make a list and use computer to generate random numbers , we discard the numbers that don’t fit sample size, we discard the same cases)

Answer 172

R O1 x O2 R O3 O4 R x O5 R O6 -Allows to compare the size of the effect and deals with the challenge to external validity posed by reactive effects of testing

Answer 173

Ask people who go to museums which exhibits most interested them? The records of the Chicago Museum of Science and Industry showed that the vinyl tiles around the exhibit containing live, hatching, chicks had to be replaced much more frequently than tiles around other exhibits ‘Unobtrusive’ observation revealed that people stood looking at the exhibit for longer periods. These two sources of information leave open the question: was the tile wear caused by the fact that more people look at the chicks or by those people who look at them spending longer doing so, or both.44 How to measure the economic rise and fall of ancient Greece over time? Map the area over which vases have been found that contained Greece’s chief exports, dating the vases found. Middens are dumps for domestic refuse of prehistoric settlements. They are often a major data source for archeologists. They may contain animal bone, faeces, shells, botanical material, and other useful information. How to study liquor consumption in Wellesley, Massachusetts? Apparently there were no liquor stores there, so sales receipts couldn’t be used. A researcher responded by counting empty liquor bottles in trash carted from Wellesley homes

Answer 174

- The idea – theory – that underlay the program was that: i) those supported could do useful community work and ii) their long term employability could be improved through increases in the social capital of those not adequately engaged with employment. - Specifically: - communities are good at identifying worthwhile development projects that will provide meaningful work to the jobless; - the experience of planning for these projects will strengthen the capacity of communities to cooperate for community development in the long term - the unemployed often cannot find jobs because they lack social capital; community engagement will increase their social capit

Answer 175

Replication Specification Interpretation Explanation Suppressor effects Distorter effects

Answer 176

**Survey research in general: strengths.** It is useful for describing the characteristics of a large population It can be used to generate large samples. It makes it possible to ask many questions on a given topic It tends to be reliable – standardized questions get developed that can be used across surveys and will tend to generate similar responses. Note, however, that interviewer characteristics and small differences in wording may be a source of response differences. **Survey research in general: weaknesses** It can be argued that standardized questions fail to get at the complexities of people’s attitudes and behaviour. For example, the need to formulate questions in a way that everyone will understand, irrespective of their level of education, may mean that we lose the nuance that some respondents might usefully provide. Or, one cannot capture attitudes adequately with a ‘very satisfied’ to ‘very dissatisfied’ range. There is a problem of validity. The issues addressed by questions do not provide very much information on the broader social context of the respondent – the sort of information that can be garnered from, say, participant observation. Once a survey is in the field it is difficult to change it. Researcher improvisation, in light of initial findings, is severely limited. The response to the interview is likely to be influenced by the fact of being asked the question. Think about the testing effect in experimental research. Subject to artificiality

Answer 177

R X O1 R O2 -Subject to sampling error, we should have groups with similar characteristics. If thats the case, do we need a pre-test ? No.

Answer 178

Pre-experimental design ( x, O) x= training program O= performance outcome [value of tips] Whats the problem with this design ? We don’t wether or not the training changed the outcome.

Answer 179

**The one-shot case study** X O For example: i) take 40 new waiters and waitresses; ii) give them a 2 hour training session on demonstrating concern for customers; iii) set the participants to work; iv) measure consumer satisfaction by the amount of tips they collect in the following month. **One-group pretest-posttest design** O1 X O2 o1= pre-test o2= post-test **Static-group comparison** X O1 (control group) O2 [lacks a pre-test]

Answer 180

Collecting standard qualitative data but “treating those data not as the topic or object of interest, but as ‘entry‘ into the social relations of the setting“. And, "its political nature“. _Its political nature means:_ identifying a subordinated group; using interviews and observations of the group to uncover the forms and sources of its oppressio

Answer 181

Historical and comparative research - The use of historical records and accounts to examine issues. - The comparison of institutions and practices in different societies. - A combination of the two Who voted for Hitler? Historical research: who voted for Hitler To test this: examine voting records from German cities, supplemented by some data on voting by people on cruise ships. Findings: People from all social classes voted for Hitler. People from upper and middle class districts voted disproportionately for Hitler. The votes for the National Socialists on cruise ships were above the national average. In farming districts, votes for Hitler were higher in Protestant than in Catholic region

Answer 182

Cluster Sampling: Way of coming to terms with the absence of a list and reduce the cost of data collection. _Example:_ Population= University students in fraternities (no list) 1. We take the provinces and territories from that list, we sample 5 (primary sample unit) 2. Compile a list of fraternities in those 5 jurisdictions and pick sample of 5 fraternities from each list (secondary sampling unit) 3. Approach those fraternities and sample within the fraternities, finding cases

Answer 183

Tuskegee experiment : Found a number for afro-americans all of whom were infected with syphillis , they were offered medical care, housing and food but they did not know they were not aware they were infected. When the experiment began, they were no treatment. Lied to the subject, the study continued but treatment and withheld. Some of the subject tried entering the military (issue = medical exam) so the firm prevented them from being drafted (which interfered with them getting benefits). Guetemala (1946-48) : 69 men and women (prisoners, soldiers, mental hospital patients) got infected and cured - what are the issues : funded by the US health service, led by researchers from past experiment, major universities etc). What was the goal ? To test the effect of treatment. Not all of the subject were provided treatment. Why did it take place in Guatemala : because could not be conducted in the US - offshore to avoid issues. Inform consent was absent. Subjects risked to experienced harm (if the medication did not work) Risk of long term consequences of contracting the diseases Control group untreated 2. Ewen Cameron Project : during the Korean War, the CIA became concerned of mindwashing so they funded research Series of really aggressive treatment - using technique to clear the memories/minds of these people : electric shocks, drugs to produce prolonged period of sleep, playing messages while the patient slept What can we say ? Using patients without inform consent (did not agree to the treatment) Treatment appeared to be much more radical than the conditions of the patients needed , using techniques going beyond what the conditions warranted

Answer 184

relationships that differ from the zero-order relationship: the relationship between earnings and gender disappears after adding the test variable, occupation

Answer 185

Ecological Fallacy : rich district voted for Hitler but what if it was the poor people of the district who voted ?

Answer 186

Appropriate topics :Communications: Who says what, to whom, why, how, and (when connected to other observations) with what effect? For example: - Are popular French novels more concerned with love than Canadian ones? - Was the popular British music of the 1960s more politically cynical than the popular German music during that period? - Do political candidates who mainly address ‘bread and butter’ issues get elected more often than those who address issues of larger principle

Answer 187

There may well be reactive effects of testing. That is to say, the provision of repeated stimuli may modify the reactions to subsequent stimuli. Where a natural group is selected – a work group, a class in a school, say - there is always a possibility that any effect of the stimulus may only be produced for subjects of the kind of group being studied. There is likely to be, then, an interactionbetween selection biases and the experimental variable. Providing and withdrawing music (the example we considered) is a highly artificial experience. There may, then, be reactive effects of experimental arrangement

Answer 188

**History:** not a problem. Anything that happens before X will happen to both **Maturation :** not a problem.you have the same conditions under two groups **Testing:** not a problem. because there is not pre-test. **Instrumentation:** not a problem , you have the same conditions under two groups. **Regression towards the mean :** not a problem. **Selection:** not a problem, we use randomization **Mortality:** maybe but its not due to the variable **Do interaction effects of selection biases and the experimental variables?** Yes a problem. The effect might just be for the members of the experiment. [But if you have a well constructed sample ( no instance of Montreal/Toronto issue), it can be avoided.] **Reactive Effect of Testing?** Not a problem. No pre-test. **Artificial context of the experiment?** Yes a problem. The artificial characteristics are present.

Answer 189

Costs and benefits were estimated over 54 months. Evidently, program outcomes vary in the ease with which a dollar value can be attributed to them. Payments per participant (cost) and reduced need for transfers to participants are straightforward. What about: foregone leisure? social capital? reduced hardship

Answer 190

- effect of incarceration and employment (the likelihood of finding a job) - effect of race on the incarceration and the likelihood of finding a job How to look at it with an experimental methods ? - generate new data by putting people in “situations” of unemployment - get a bunch of people put together cvs and observe how many call back they get METHODS : college age male tester they applied for entry level jobs, advertised in newspapers Divide two race categories (white, black) and two categories ( incarcerated, non-incarcerated) matched the 4 samples in terms of appearance, presentation, style and so on People with a criminal record are less likely to be offered a job Blacks were less likely to be offered a job White tester with a Criminal record were more likely to get a job than black without one

Answer 191

Addresses all the problem internal validity of reactive effect of testing.

Answer 192

Study of recorded human communications **Steps involved:** Decide what to observe Operationalize variables and decide how to code them Record observations Analyze data

Answer 193

structure observations in such a way that causal relations can be inferred – this is internal validity; ability to generalize the results beyond the experimental context – this is external validity

Answer 194

**History.** Clearly, subsequent observations may be influenced by extraneous events. This would be a particular problem if the extraneous events occurred between O4 and O5. **Maturation.** Probably not a problem. This should show up as progressive change rather than as a sudden change in observed behaviour. This shouldn’t be a problem. There may, however, be relatively abrupt changes associated with maturation – puberty? **Testing**. This should not be a problem. If there were to be a testing effect it should show up between O1 and O2, as well as subsequently **Instrumentation.** This may not be a problem. Why would the effect only show up between O4 and O5? However, if the observers are aware of the experimental design and interest that might modify their observations between precisely those observations. **Regression towards the mean.** Suppose the subjects of interest were drawn from people who had performed poorly on a test. They are observed four times before the stimulus is applied. The average of their pre-stimulus scores provides a baseline that attenuates the effect of the extreme score on a single test. The design allows a comparison of the O4 to O5 difference with each of the differences between O1 and O4. **Selection**. This cannot be a problem since there is only one group being studied. **Mortality.** This may be a problem if the group under study is ‘naturally composed’. Suppose absenteeism in a work group is being studied. If some work group members quit and are replaced then, if the quits and hires approximately coincided with the experimental effect, that might account for a change in observations between O4 and O5

Answer 195

What does this complexity imply ? One problem : Someone needs to decides what it means “to touch someone sexually”, need to decide whether or not someone is injured. Debates over what this language means. Who decides ? Judge in response to lawyers. Second problem : definition changed in 1980s so we cant look at data overtime because the entire law is different Other issues : 1. we know there has been variably in willingness for victims to report the crime, which probably increases. Which mean that rape numbers go up but maybe just because people report more. Male can get rate but they usually don’t report 2. Police not immune to public opinion (the extend to which police pursue complaints is subject to social pressure (news example) ) 3. As workload varies, they might be less likely to report these crimes 4. Report keeping practices vary in effectiveness

Answer 196

1. Experiments 2. Surveys 3. Qualitative interviews 4. Observation 5. Unobtrusive Research

Answer 197

- reveal patterns that are present in the data; - construct explanations of the patterns; - as a step in doing this, to construct typologies of behaviourswhich really means categories into which data can be grouped; - And to link the observations to theory – either constructing new theory of drawing conclusions about existing theor

Answer 198

Aso possible (but not very frequent) is that the test variable is a suppressor. This is the case when adding the control causes a relationship to appear in the partial table when no relationship was apparent in the zero-order table.

Answer 199

O1, O2, O3, O4 x O5, O6, O7, O8 \_\_\_\_\_\_\_\_\_\_\_\_ \_\_\_\_\_\_\_\_\_\_\_/ Evidently, there should be a clear shift in the observed behaviour from O4 to O5, if the experimental intervention has an effect

POST-MIDTERM Flashcards

(229 cards)