Research Methods Midterm 2 (ch. 6,7,9,10)

Question 0

Yea-saying (acquiescence)

Answer 0

1. Saying ‘yes’ or ‘strongly agree’ to every item instead of thinking carefully about each one.

Question 1

Response sets

Answer 1

1. Type of shortcut respondents can take when answering a survey (sets of related questions only, not single questions).
2. Respondents adopt consistent ways of answering, either all positive, all negative or right in the middle.
3. Hurts construct validity, respondents are not saying what they really think.

Question 2

Nay-saying

Answer 2

1. When the respondent disagrees with every item.

2. Threatens construct validity, survey would be measuring the construct of people laziness or agreeableness.

Question 3

Observational research

Answer 3

1. When a researcher watches people or animals and systematically records what they are doing.
2. Many believe observing behavior is better than self-reports (people cannot always state the reason for their behavior or report on past events accurately).

Question 4

Observer bias

Answer 4

1. A threat to construct validity, in which observers record what they want to see or expect to see, rather than what is really happening.
2. We have biases because of the schemas we have.
3. Biases can actually change the behavior of those they are observing (unintentional cues)

Question 5

Observer effect (reactivity)(how to prevent it)

Answer 5

1. Occurs when people change their behavior, or react when they know another person is watching.
2. Best behavior/ worst behavior, rather than typical behavior.
3. Occurs in humans and animals
4. Solutions: unobtrusive observation (hide, one way mirrors), wait it out (let those you are observing ‘get used to your presence’), measure behaviors results (measure traces of behavior, bottles left behind, footprints).

Question 6

Fence sitting

Answer 6

1. When asking controversial questions, responders play it safe by answering all questions in the middle of the scale (also when question is confusing or unclear).
2. Threatens construct validity by suggesting that respondents do not have an opinion when they actually do.

Question 7

Socially desirable responding (faking good)(how to avoid it)

Answer 7

1. When survey respondents give answers that make them look better than they really are.
2. To avoid this, ask for anonymous responses, or online surveys (respondents may be too shy, embarrassed, or worried about giving their real opinion).
3. To avoid, ask filler questions. Include several unrelated questions.

Question 8

Psychological reactivity

Answer 8

Aka observer effects (when people change their behavior when they know another person is watching or being observed) (EX. best behavior, worst behavior).

Question 9

Demand characteristics

Answer 9

1. When an experiment contains cues that lead participants to guess its hypothesis.
2. If demand characteristics are high, alternative explanations may be created.

Question 10

Semantic differential format

Answer 10

1. Respondents are asked to rate a target object using a numeric scale that is anchored with adjectives.
2. Ex. Rate my professor: Easy 1 2 3 4 5 Hard.
3. Ex. Five star rating format: one star=poor, five stars=outstanding.

Question 11

Likert scale

Answer 11

1. Respondents are presented with a statement and asked to use a rating scale to indicate their degree of agreement.
2. Strongly agree, agree, neutral, disagree, strongly disagree.
3. Ex. Rosenberg self-esteem inventory.

Question 12

Forced-choice format

Answer 12

1. People give their opinion by picking the best of two or more options.
2. Political polls
3. Narcissistic personality inventory

Question 13

Double-barreled questions

Answer 13

1. A question that asks two questions in one.
2. Ex. I look for main ideas as I read, and I formulate answers to questions I have as I read an assignment.
3. Has poor construct validity, are they responding to the first half of the question, the second half, or both.

Question 14

Double negatives

Answer 14

1. Make wording of survey questions unnecessarily complicated and cognitively confusing.
2. Ex. Does it seem possible or impossible to you that the Nazi extermination of the Jews never happened?
3. Reduces construct validity.

Question 15

Leading questions

Answer 15

1. Wording questions in a way that affects the outcome of the survey responses.
2. Ex. Do you think that relations between blacks and whites
   1. Will always be a problem? 2. Or a solution that will eventually
   be worked out?
3. This question is negatively priming this issue as a “problem”

Question 16

Question Order (how to deal with them)

Answer 16

1. The order in which questions are asked can affect the response to a survey. The earlier questions can change the way respondents understand and answer the later questions.
2. Prepare different versions of the survey, with the questions in different orders. Then look for order effects.

Question 17

Reverse worded items

Answer 17

1. Helps distinguish yea-sayers from true believers.

2. Helps a measure with construct validity.

Question 18

Masked study design

Answer 18

1. Observers in observational studies, are unaware of (or blind to) the conditions to which participants have been assigned, and sometimes are even unaware of what the study is about.

Question 19

Census

Answer 19

A sample of the whole population in a test or poll.

Question 20

Purposive sampling

Answer 20

When researchers want to study only certain kinds of people, so they seek out certain kinds of people. Ex. Studies on smokers, only have smokers in study).

Question 21

Convenience sampling

Answer 21

Samples are chosen merely on the basis of who is easy to access. (Most common method in behavioral research).

Question 22

Random sampling

Answer 22

1. When you draw a sample using some random method (drawing names from a hat, random digit phone dialer) so that each member of the population has an equal chance of being in the sample.
2. Enhances external validity

Question 23

Snowball sampling

Answer 23

A variation on purposive sampling that can help researchers find rare individuals. When samples are hard to obtain, researchers may ask participants to recommend acquaintances for the study. (Recruitment method).

Question 24

Probability sampling

Answer 24

1. Drawing a sample at random from a representative population (every member of the pop. has an equal chance of being in the sample)(good external validity).
2. Crucial for determining external validity in frequency claims.

Question 25

Simple random sample

Answer 25

everyone in a pop. has a ticket and all tickets are put into a hat for a random selection (usually done by computer programs).

Question 26

Cluster sample

Answer 26

study college students in Cali. Get a list of all colleges in Cali (clusters), randomly select 5 colleges in that sample (clusters), then include every student from the 5 colleges

Question 27

Multistage sample

Answer 27

study college students in Cali. Get a list of all colleges in Cali (clusters), randomly select 5 colleges in that sample (clusters), then take a random sample of students from within the 5 colleges.

Question 28

Random Assignment

Answer 28

The use of a random method (e.g., flipping a coin) to assign participants into different experimental groups ( control group, experimental group, experimental group 2, etc.).

Question 29

Within-Subjects Designs

what they are, advantages and disadvantages

Answer 29

1. In a Within-subjects design there is only one group of participants and they are presented with all levels of the independent variable (exposed to both experimental and control).
2. Advantages: participants will be equivalent because they are exposed to all treatment groups. Gives researchers more power to notice differences between conditions. Require fewer participants, more efficient.
3. Disadvantages: participants can see all levels of the independent variable and then change the way they would normally act.

Question 30

Concurrent Measures Design

Answer 30

An experiment using a within-groups design in which participants are exposed to all the levels of an independent variable at roughly the same time, and a single attitudinal or behavioral preference is the dependent variable (indicated only once).
EX. Taste test between Pepsi and Coke, indicate the preferred choice.

Question 31

Between-subjects designs (aka independent-groups design) (advantages and disadvantages)

Answer 31

1. An experimental design in which different groups of participants are exposed to different levels of the independent variable such that each participant experiences only one level of the independent variable.
2. Participants do not participate in both experimental and control groups, they only get exposed to 1.

Question 32

Posttest-only Design

Answer 32

An experiment with a between-groups design in which participants are tested on the dependent variable only once. 
EX. Like our class experiment.

Question 33

​Repeated-measures Design

Answer 33

An experiment with a within-groups design in which participants respond to a dependent variable more that once, after exposure to each level of the independent variable.
EX. Interact with own child then measure oxytocin, interact with new child measure oxytocin.

Question 34

Mixed designs

Answer 34

.

Question 35

Design Confound (what are they, what effect do they have?, how to avoid/deal with them)

Answer 35

1. A second variable that happens to vary systematically along with the independent variable and therefore is an alternative explanation for the results.
2. EX. If researchers gave the red ink group harder anagrams to solve than the green or black ink conditions. If the researcher treated the red ink group differently than the other groups.
3. Alternative explanations in the way your procedures were carried out.
4. Design confounds threaten internal validity wand cannot support a casual claim.

Question 36

Selection Effect (what are they, how they arise, how to deal with them)

Answer 36

1. A threat (confound) to internal validity that occurs when the kinds of participants at one level of independent variable are systematically different from those at the other level of the independent variable.
2. EX. When you allow participants to choose which level of the independent variable they want to be in. Assigning all women or all men.
3. To avoid: use random assignment (rolling a die, flipping a coin, using a random number generator). Use a matched-groups design (sample of 30 participants in ink color study might pose a confound if there are 10 exceptionally intelligent people in one of the groups together. To avoid, give an IQ test before you then randomly assign them into groups).

Question 37

Order Effect or Carry over effects

Answer 37

1. A threat (confound) to internal validity that occurs when being exposed to one condition changes how people react to a later condition.
2. A within- groups design problem
3. Fatigue, practice, boredom

Question 38

Counterbalancing

Answer 38

1. To help within-groups design eliminate carryover effects, we can present the levels of the independent variable to participants in different orders to control for order effects.

Question 39

Testing threats

Answer 39

Scores on a measure have changed over time because participants have taken the test more than once.

Question 40

Maturation

Answer 40

A threat to internal validity that occurs when an observed change in an experimental group could have emerged more or less spontaneously over time. (People’s behavior can adapt and change and it may have nothing to do with the manipulation or independent variable).

Question 41

Instrumentation

Answer 41

1. A threat to internal validity that occurs when a measuring instrument changes over time from having been used before.
2. EX. Observers judgements become more or less strict over a period of watching many people. Using a alternative surveys in one experiment.

Question 42

Regression Threat

Answer 42

A threat to internal validity related to regression toward the mean, by which any extreme finding is likely to be closer to its own typical, or mean, level the next time it is measured (with or without the experimental treatment or intervention).

Question 43

Placebo effects

Answer 43

1. When participants who receive a treatment improve because they believe they are receiving an effective treatment, even when it is a placebo.

Question 44

Spontaneous remission

Answer 44

1. Symptoms of disorders can improve on their own, with no known cause, it just happens with time.

Question 45

History threats

Answer 45

Something specific that happens, a historical, external, environmental event, that occurs to everyone in a group or experiment. Ex. Collecting data then events of 9/11 happen and alter and change everything.

Question 46

Attrition Threat (what it is, why it is a problem)

Answer 46

1. In a repeated-measures experiment or quasi-experiment, a threat to internal validity that occurs when a systematic type of participant drops out of a study before it ends.
2. Attrition is a problem if those participants who dropped out were those with extreme or high or low scores. Dropping their scores will dramatically change the “average” end results.

Question 47

Comparison groups (what are they, why are they used?)

Answer 47

1. A group in an experiment whose levels on the independent variable differ from those of the treatment group in some intended and meaningful way.
2. Without comparison groups, you can not support a casual claim. You must be able to compare, “the red pen made me anxious compared to the green pen.”

Question 48

Effect size

Answer 48

1. The magnitude of a relationship between two or more variables (the strength of the correlation, r is closer to 1= more strength).
2. 0.10 weak, .30 moderate, .50 strong
3. More accurate predictions with stronger effects
4. More important results have stronger effects (although some seemingly small effect sizes may yield life saying results, ie. medicinal amounts).

Question 49

Statistical significance (and what it depends on: effect size, sample size, etc.)

Answer 49

1. A conclusion that a result is extreme enough that it is unlikely to have happened by chance if the null hypothesis is true.
2. Strong correlations, r closer to 1, more likely to be significant.
3. Large sample size and small correlations, r not close to 1, will be significant. Small sample size and small correlations will not be significant,

Question 50

The relationship between effect size and statistical significance (how are they different, how does one influence the other?)

Answer 50

1. Strong correlations, r closer to 1, more likely to be significant.
2. Can not tell from just effect size, you need to interpret p values associated with it.

Question 51

Cohen’s rule of thumb (regarding the strength of a correlation)

Answer 51

A measure of effect size that tells how far apart two group means are, in standard deviation units.

1. 0.10 small or weak
2. 0.30 medium or moderate
3. 0.50 large or strong

Question 52

Association Claim (what are they, how are they made, how are they interrogated?)

Answer 52

1. A claim about two variables, in which the level of one variable is said to vary systematically with the level of another variable, such that when one variable changes, the other variable tends to change too.
2. Also called bivariate associations: describes a relationship between two measured variables (not manipulated).
3. Interrogated by construct validity (how well was each variable measured? What were the researchers operationalizations?) statistical validity (effect size, stat. significance, outliers, zero correlation actually representing curvilinear), and external validity.
4. Type: positive, negative, zero, curvilinear.

Question 53

Outlier (what they are, how they affect the correlation between two variables)

Answer 53

1. An extreme score, one or a few cases that stand out as either much higher or much lower than most of the other scores in a sample.
2. Single outliers can have strong effects on correlation coefficients, r. Can change r=0.26 to r=0.37.
3. Especially problematic when an outlier has extreme scores on both of the variables.
4. Matter most when sample is small.

Question 54

Scatterplot (what are they, why we look at them)

Answer 54

1. A graphical representation of an association, in which each dot represents one participant in the study measured on two variables. 2. We look at them to see if a correlation can be made (positive, negative, zero, curvilinear).
2. correlational coefficient r of -.33 = negative correlation (1 variable up, 1 variable down = -) and moderate strength (how close to 1 is .33).

Question 55

The 3 rules of causality

Answer 55

1. Covariance: a correlation or association between the cause and effect.
2. Temporal precedence: the causal variable has to come first in time, before the effect variable.
3. Internal validity: there must be no plausible alternative explanations for the relationship.
4. One variable is manipulated and one variable is measured.

Question 56

The concept of pattern and parsimony in correlational research (association claims)

Answer 56

The degree to which a theory provides the simplest explanation of some phenomenon.