Research methods Flashcards
1
Q
How observational research is refined through behavioural categories
A
- Allows a target behav to be broken up into components that are observable and measurable
- Give eg of BC
- Using BC provides clear focus for the researcher
- Categorisation enables proposal of a testable hypothesis
- Categories allows for more objective data recording
- Categories should result in greater reliability
- Categories provide data that is easier to analyse
2
Q
Overt observation
A
Where observer is clearly visible and the ppl being observed know that they’re being observed
3
Q
Event sampling
A
- Observers decide on a specific event related to the investigation
- Relevant event recorded every time it occurs
4
Q
Benefits of studying same sample overtime
A
- Eliminates individual differences so it can be assumed that changes in development are due to changes in the environment
- Enables Rs to study patterns of development over time
- Allows for insight/in-depth analysis of indiv cases
- Allows for establishment of rapport, so that more detailed info about early experiences can be forthcoming
- Allows study of long term effects of early experiences
5
Q
Explain why it is sometimes necessary to deceive participants in social influence research. (Total 2 marks)
A
- Deception is necessary because if participants knew the aim, they might change their behaviour
- This might affect validity.
6
Q
Dealing w/ deception
A
Deception could be dealt with by debriefing the participant. It would have to be explained why it was necessary to deceive them and answer any questions that they might have wanted to ask, as well as reassuring them.
7
Q
A psychologist decided to interview both Zina and Amanda five months later to see if they could still remember the same level of detail about the incident.
Explain one ethical issue the psychologist must consider before interviewing Zina and Amanda
A
- Treating people with respect such as assuring their confidentiality, giving them the right to withdraw, etc.
- Protection from harm – Zina and Amanda could experience psychological harm from having to recall the details of the incident again so they could be offered counselling
- Informed consent – the psychologist must gain informed consent, so Zina and Amanda are aware that they will be interviewed about the incident.
8
Q
Describe two differences between these qualitative and quantitative data
A
- Quantitative data involves numbers (number of boys and girls), whereas qualitative data involves words, e.g. quotes from the interview
- Quantitative data can be measured objectively, whereas qualitative data is based on the subjective interpretation of language
- Quantitative data is immediately quantifiable, whereas qualitative data has to be transformed and is only quantifiable if the data is put into categories and the frequency is counted
- easier to identify trends/patterns
9
Q
The experiment used an independent groups design.
Explain how this study could have been modified by using a matched pairs design.
A
- the researcher needs to ensure that the two groups are matched for key variables
- example of at least one key variable – any that might reasonably be expected to affect memory in this situation, eg eyesight, age, intelligence
- all participants should be pre-tested/assessed for the key variable/variables
- for each person in one condition, the researcher should assign a ‘matched’ person in the other condition.
10
Q
Explain how such observational research might be refined through the use of behavioural categories.
A
- behavioural categories allow observers to tally observations into pre-arranged groupings
- examples of behavioural categories appropriate in this situation might be ……
- using categories provides clear focus for the researcher
- categorisation enables proposal of a testable hypothesis
- categories allow for more objective/scientific data recording
- use of categories should result in greater reliability
- categories provide data that is easier to quantify/analyse
- contrast with method described in the stem (own interpretation is too subjective/opinion based).
11
Q
picture 1 in pictures folder
A
- The total observation time for each parent was 10 minutes.
- The psychologist made 20 observations for each parent.
- To generate 20 observations for each parent she must therefore have recorded her observation every ½ minute or every 30 seconds.
12
Q
Explain what is meant by ‘overt observation’.
A
- overt observation is where the observer is clearly visible (not hidden from view)
- people being observed know that they are being observed
13
Q
Should the hypothesis for this study be directional? Explain your answer
A
‘it should not be directional,’ (1)
as there is no reference to evidence that allows the psychologist to predict the direction of the results (1).
14
Q
Explain why using stratified sampling might improve this study
A
- stratified sampling increases representation/generalisation by sampling many subsets of students
- stratified sampling reduces research bias as the subsets of students are selected randomly.
15
Q
Explain what is meant by ‘primary data’.
A
- primary data is original data/first hand response of the participants/source in the research.
- collected specifically for the research being carried out.
16
Q
Explain one reason why the mean would be the most appropriate measure of central tendency to summarise the data
A
- the mean can be said to be representative of all the data collected as it is calculated using all the individual values.
- the mean is the most sensitive measure of central tendency as it uses all the values in set of data.
17
Q
Discuss the purpose of counterbalancing.
A
- it controls the impact of order effects (practice, fatigue or boredom).
- allows order effects to be distributed evenly across both conditions.
- making each condition of the IV occur as the first task and the second task equally.
- counterbalancing does not eliminate order effects which will be present because there are two separate tasks to be completed by each person.
18
Q
Explain how the follow-up study (RM study, timed, 2 conditions) could be said to be an improvement on the original study (questionnaire)
A
- the second study is more objective. In the first study participants self-reported what they believed to be the case and this is refuted by the follow-up study
- the measurement of time allows for more detailed analysis of data.
- use of experimental method involves manipulation of IV, establishing cause and effect in follow-up study which is not a feature of the self-report method used in the first study
- possibility of socially desirable answers as a feature of first study which might be unreliable and this is not present in follow-up study where measurements are more direct.
19
Q
Advantage of IGD
A
• same task/materials can be used in both conditions as participants are always naïve to the task.
20
Q
How to use standardisation used to overcome effects of EV
A
- testing all participants in the same room
- making sure that all participants hear the same instructions
- ensuring that all participants are tested by the same researcher.
21
Q
Explain how the psychologist could have used random allocation to assign the 15 participants in Condition B into the 5 group
A
- all the participants allocated a number from 1 to 15.
- the 15 numbers are put in a hat.
- assign first three numbers drawn to a group and repeat process for other 4 groups
22
Q
Using the information given in Table 2, explain how the psychologist could further analyse the data using percentages.
A
- for each condition, the overall number of ideas generated should be divided by the overall total of 185.
- the result for each condition should then be multiplied by 100 to give the percentage.
23
Q
Write a debriefing that the psychologist could read out to the participants
A
- explanation of the aim: to see if creativity is affected by the presence or absence of others
- information about the other condition – in an independent design people need to know about the condition in which they did not take part.
- specific ethical issues, eg right to withdraw data/be informed of results/check of welfare
- general ethical considerations, eg respect for participants.
24
Q
Explain 2 functions of the endocrine system.
A
- To secrete the hormones which are required to regulate many bodily functions
- To provide a chemical system of communication via the blood stream
25
Why are the standard deviation values found in the study above (states the SD for 2 conditions) useful descriptive statistics for the cognitive psychologist?
* useful to inform about the spread of scores
* indicates participant variables – as a group the people in Condition 1 are quite different/are more variable than those in Condition 2.
26
Outline problems of studying internal mental processes like memory ability by conducting typical experiments where memorise a list of words
* Direct observation of memory is not possible and must be inferred from the results/behaviour of the participants – this inference could be mistaken.
* The task given is rarely how normal memory functioning occurs because it is specifically designed to make measurement possible – the researcher therefore collects data that is only related to memory processing under experimental conditions.
27
Identical twins, different personalities
Use your knowledge of genotype and phenotype to explain this difference in their personalities.
* Holly and Rita have identical genotype as they are MZ twins.
* They have the predisposition to develop the same personalities as each other unless another factor(s) intervenes.
* For them to have developed different personalities over time, this must have been influenced by being in different environments.
* Their phenotypes – personalities achieved – are different, presumably because Rita was encouraged to be sociable and lively and Holly was not.
28
What does the scatter-gram suggest about the relationship between age and attitude to social care issues?
- there is a positive relationship between age and interest in social care issues/as people get older their interest in social care increases (1)
- this is because as the values on one co-variable increase, so do the values on the other co-variable (1)
- OR as age increases so does attitude to social care rating/score.
29
The researchers rated the active engagement of the participants in the discussion on social care. They used this rating as a measure of each participant’s attitude to social care issues.
Briefly explain how investigator effects might have occurred in this study.
If the researchers believed that older people would be more interested in social care they could have just given scores based on the age of the person.
30
Outline how the researchers could have avoided investigator effects having an impact on the study.
* Discussion of separate observation by the two researchers and comparison – inter-rater reliability
* Having ‘blind’ rating of the discussion by someone who is unaware of the aim or research hypothesis
* Filming the discussions so there is a permanent record that can be checked by peer review of the data to confirm the scores/ratings
31
Benefits for the researcher of using both closed and open questions
* Closed questions would present participants with options for their response so the researchers would be able to collate and display the information collected easily.
* Closed questions make it easy to compare specific response to questions the researchers wanted answered – they can be sure there will be certain information because they have restricted the options to include that information.
* Open questions allow respondents to interpret the question as they wish to and develop their response with detail or depth – so there is lots of information received.
* Open questions allow the researchers to pursue a line of enquiry that they may not have predicted but which comes to light because of a response by an interviewee
32
Explain how the researchers should have addressed two ethical issues in the investigation.
Consent – to be part of what is in essence two studies. Participants should be forewarned – a briefing.
Protection from harm – at the end of participation all will have to be fully aware that they were rated for their social care interest and a low score might indicate they are ‘uncaring’. They may wish to withdraw their data.
Right to withdraw – being made aware that they can at any time stop participating and at the end of their participation they can withdraw detail of their behaviour in the research.
33
Explain one way in which the researchers may have checked whether their categories were reliable
- IOR
- The consistency between the recordings of two researchers would be assessed by asking each researcher to categorise the essays independently for ‘references to love’.
- The data would then be compared and if similar then the analysis is reliable
34
Explain how the data collected from the interview might have improved upon the data collected from the content analysis.
* The interviewer could have asked follow-up questions to gain greater insight into some of the points raised in the essay
* The interview would produce more detail/depth of information than the participant would have been able to reveal within the essay • Interview data would have provided a further measure of reliability/validity of the original essay content
* The interviewer may have gained rapport with the participant so they have felt comfortable revealing more personal/sensitive information face-to-face
35
Explain two factors that the researcher had to take into account when deciding to use the sign test
- Nominal data as patients are assigned to one of three categories – ‘improved’, ‘deteriorated’ or ‘neither’
- Testing for difference in the number of absences in the year following and prior to treatment
- Repeated measures as the same patients` work records are compared before and after treatment
36
Calculate the sign test value of s for the data in Table 1 on the previous page. Explain how you reached your answer
- The most commonly occurring sign is + (12) and the least frequently occurring sign is – (5).
- The 0s are disregarded. The total for the least frequently occurring sign is the value of s = 5
37
In what ways would the use of primary data have improved this investigation?
* Primary data are obtained ‘first-hand’ from the participants’ themselves so are likely to lead to greater insight: eg into the patients` experience of treatment, whether they found it beneficial, negative, etc.
* Secondary data, such as time off work, may not be a valid measure of improvement in symptoms of depression. Primary data are more authentic and provide more than a surface understanding: eg participants may have taken time off work for reasons not related to their depression.
* The content of the data is more likely to match the researcher’s needs and objectives because questions, assessment tools, etc. can be specifically tailored: eg an interview may produce more valid data than a list of absences
38
If identifying whether data is quantitative or not
•Mention what they're measuring that makes the data quantitative in the justification
Eg, the number of participants who completed the questionnaire in each condition
39
Why data is primary
* the data is collected first hand (directly) from the participants.
* data is collected for the purpose of the investigation.
40
For this study, the researchers had to use different participants in each condition and this could have affected the results.
Outline one way in which the researchers could have addressed this issue.
RANDOM ALLOCATION
• each participant is assigned a number or identified by name
• the numbers/names are placed into a random number generator/hat/lottery method
• the first participant drawn is assigned to condition 1, the second to condition 2, etc. OR the first 15 participants are assigned to condition 1 and the next 15 are assigned to condition 2.
MATCHED PAIRS
• participants should be matched on a variable that is relevant to the experiment
• this could be ascertained through the use of a pre-test e.g. completing a confidence questionnaire
• participants from each matched pair are allocated to different conditions.
41
What is the most appropriate measure of central tendency for calculating the average of the scores, from Table 1,
MEAN
- the mean is the most sensitive method as it takes all the scores in each data set into account
- OR there are no anomalous results/outliers/freak scores in either set of scores, so the mean will not be distorted
42
Explain what is meant by ‘event sampling’
* observers/researchers decide on a specific event relevant to the investigation
* relevant event is recorded every time it happens
* in this investigation this may be every time a child in the playground is approached by/talks to/plays with another.
43
Briefly discuss how observational research might be improved by conducting observations in a controlled environment.
* controlled environment affords the opportunity for control of extraneous variables
* examples of extraneous variables that might be controlled and how/why they could affect the outcome of a study if not controlled
* exclusion of extraneous variables allows for greater inference about cause and effect
* exclusion of extraneous variables means researcher can replicate the observation to check for reliability of the effect.
44
Explain how this study could be modified by checking the sleep questionnaire for test-retest ability. (testing for correlation)
* the same participants would complete the sleep questionnaire on more than one occasion
* each participants’ scores from the first occasion should be correlated with his/her results from the later occasion to be shown on a scattergraph to describe the correlation, with scores from the first test plotted on one axis and the scores from the second test plotted on the other axis
* the strength of the correlation should then be assessed using either a Spearman’s rho test (or a Pearson’s r test)
* the degree of reliability is then determined by comparing the correlation with the statistical table to determine the extent of correlation – there should be a (strong) positive correlation between the two sets of scores.
45
Write the full reference for this book as it should appear in the reference section of the researcher’s report.
Bem, S.L (1993) The lenses of gender: transforming the debate on sexual inequality. New Haven. Yale University Press.
Selman R.L (1980) The growth of interpersonal understanding: developmental and clinical analyses. New york. Academic Press.
Surname, initials (year of publishing) title. Place published. publisher.
46
explain the difference between primary and secondary data.
* primary data is gathered directly/first-hand from the participants, and is specific to the aim of the study whereas secondary data has previously been collected by a third party (another researcher or an official body), not specifically for the aim of the study, and then used by the researcher
* in this study, the interview recordings are primary data –gathered specifically for the purpose of investigating causes of aggressive behaviour whereas the school records are secondary data – pre-existing and not gathered for the purpose of investigating causes of aggressive behaviour.
47
Explain how the psychologist could continue her investigation by carrying out thematic analysis of the interview recordings
* use the recordings to make a transcription of the interview
* use coding to initially analyse the transcripts
* review the transcriptions/codes looking for emergent themes/ideas that might be linked to later aggressive behaviour, eg family violence, parental argument, alcohol misuse.
No credit for answers referring to pre-determined categories, codes, themes and/or counting frequencies
48
Concordance rate for mathematical reasoning ability for MZ twins (58%) higher than DZ twins (14%)
Outline how these researchers could have used a statistical test to establish concurrent validity of the mathematical reasoning ability test.
* concurrent validity would involve correlating the results on the maths test with results for the same group of people on an established maths reasoning test
* A Spearman’s rho or Pearson’s r test should be used for the two sets of test results
* if the mathematical ability test is valid then there should be a significant positive correlation between the two sets of test scores at the 0.05 level.
49
Explain one limitation of the level of measurement of nominal data
– categorical data is crude/unsophisticated/does not enable very sensitive analysis
– because it does not yield a numerical result for each participant
50
A researcher studied the effect of light intensity on visual memory. He carried out a controlled experiment. Participants in Group 1 viewed a drawing in extra bright light for 60 seconds then had to recall the details. Participants in Group 2 viewed the same drawing in normal light for 60 seconds then had to recall the details. The researcher recorded the number of details correctly recalled in the two conditions.
Referring to the item above, explain what is meant by the scientific emphasis on causal explanations. [
* All variables are controlled except for light conditions (the IV)
* Any change in the number of details correctly recalled (the DV) must therefore be due to/caused by the manipulation of light intensity (the IV)
* Use of control enables the researcher to infer causality/cause and effect
51
Explain why the data in Table 2 is primary data and not secondary data
– because it is collected from participants directly/first-hand
– rather than gathered from reports of previous research
52
Explain one strength of primary data.
* Data gathered is more likely to be focused on the purpose of the research
* Less peripheral/redundant information
* Control issues – first-hand data can be controlled whereas secondary data may have been gathered under differing conditions
53
advantage of using a repeated measures design
Control for individual differences so that the researcher can be more certain that the effect is not due to characteristics such as gender, personality etc.
54
What is the calculated value of the sign test statistic ‘S’? Explain your answer.
‘S’ is the frequency of the least common difference. There are 8 positive differences, 2 negative differences and 2 ties.
55
Using the table of critical values of ‘S’ above, state whether the findings of the study are significant at p < 0.05. Explain your answer.
- identifying the correct value of N (N = 10, total number of differences)
- Compare crit and calculated value
- stating that for an N of 10, a value of ‘S’ = 2 is not significant at the p≤ .05 level
56
Explain what is meant by operationalisation
operationalisation involves clearly specifying/defining observable behaviours that represent the more general construct under investigation/to enable the behaviour under investigation to be measured
57
The students thought that having a dog on a lead was a useful measure of considerate behaviour because it had face validity. Explain what is meant by face validity in this context
- face validity – where a behaviour appears at first sight (on the face of it) to represent what is being measured
- Application: Having a dog on a lead appears at first glance to be measuring considerate behaviour because if a dog is on a lead it is less able/likely to upset other people by coming close, frightening, chasing, biting, growling etc
58
Explain how inter-observer reliability could be ensured by working as a pair
- The student pair should discuss and agree beforehand their interpretation of the behavioural categories
- Each student should then observe the same people/space/target at the same time but record/tally independently
- Their respective recordings/tallies should be correlated using an appropriate statistical test ascertain the level of agreement
59
state whether or not the result of the Chi-square test is significant at the 0.05 level of significance.
Justify your answer.
* Yes, the result is significant
* Because the calculated value of Chi-square is more than the critical table value at 0.05, either 4.60 or 5.99, depending on whether student uses one or two-tailed values
* One-tailed is consistent with the hypothesis and Q13, but there is an argument that the Chi-square test should always be two-tailed so either can be credited
* Where df equals 2
60
In the discussion section of their report of the investigation the students wanted to further discuss their results in relation to levels of significance.
Write a short paragraph the students could use to do this
- Explanation of levels of significance as an indication of the measure of the influence/effect of chance/random factors on the findings.
- With the present results there is a 95% confidence in accepting the research hypothesis/confidence that any difference/effect is due to the variables under investigation, in this case the location of the public spaces.
- There is a 5% possibility that the same frequencies would occur if there was no real difference between the two towns.
- The calculated value in this case well exceeds the critical value at 0.05 but does not meet the more stringent level of significance of 0.01.
- Possibility of type one error.
61
Explain how the students could develop their interview findings by carrying out a content analysis and why content analysis would be appropriate in this case.
- content analysis is suitable because the students are analysing recordings which are a form of media.
- Students could identify specific ideas/concepts that occur in the recordings
- They could then set up a system of categories and tally the ideas/concepts
62
Design an experiment to investigate the effect of indoor plants on mood in office workers. For your measure of mood you should devise a measure that would give data suitable for testing at the ordinal level of measurement.
In your answer you should provide details of:
- Design – include reference to the experimental design, variables and controls
- Materials/Apparatus – describe any special materials required
- Data analysis that could be used – include reference to descriptive and inferential analysis
Justify your choices.
DESIGN
• The experimental design to be used (repeated/independent/matched).
• IV and DV – note the DV must be suitable for ordinal level analysis
• Any relevant aspect of control eg duration of study, control of relevant environmental variables eg office heating, noise pollution
MATERIALS/APPARATUS
• The self-devised instrument for measuring mood should be one that yields ordinal level data
• A rating scale is the most suitable measure eg ratings from 1 – 10 where 1 = very unhappy and 10 = very happy. Statement(s) from the rating scale should be outlined
• Alternatively students could describe a questionnaire and give examples of suitable items
DATA ANALYSIS
• Descriptive statistics should include a measure of central tendency and dispersion (given the requirement for an ordinal level measure the most appropriate here would be the median and range but can award some credit for other measure of central tendency and dispersion)
• Suitable inferential analysis would be a test for differences between two conditions suitable for data at the ordinal level (Mann Whitney or Wilcoxon). Whichever test is chosen it should be consistent with the proposed experimental design. (
63
Explain why a histogram would not be an appropriate way of displaying the means shown ( mean time taken to run 400m w/ and w/o music)
- you need to have continuous data
| - categorical/nominal used
64
What do the mean and standard deviation values in Table 1 suggest about the participants’ performances with and without music? Justify your answer
- mean times suggest about the effect of music on the participants’ 400m performance - participants run faster with music (take less time to run 400 metres) or participants run more slowly without music (take more time to run 400 metres).
- justification about the difference in the mean scores in each condition – mean time is greater in condition A than condition B (or mean time is lower in condition B than condition A).
- standard deviations suggest about the spread of scores in each condition – performance is more consistent in condition A than condition B (or performance is less consistent in condition B than condition A)
- justification about the difference between the standard deviations in each condition – standard deviation is smaller in condition A than in condition B (or standard deviation is greater in condition B than condition A).
65
Calculate the percentage decrease in the mean time it took participants to run 400 metres when listening to music. Show your workings.
123 – 117 = 6
6 ÷ 123 =0.048780
0.048780 x 100 = 4.878
Answer = 4.88
66
explain whether or not the results are significant.
* the result is not significant (at the 5% level)
* because the calculated value of t (1.4377) is less than the critical/table value of t, which is 1.833 (at 0.05, for a directional hypothesis where df is 9).
67
What is meant by a Type II error?
A Type II error would occur where a real difference in the data is overlooked as it is wrongly accepted as being not significant, accepting the null hypothesis in error (a false negative).
68
Explain why psychologists normally use the 5% level of significance in their research.
The 5% level is used as it strikes a balance between the risk of making the Type I and II errors (or similar).
69
Identify one extraneous variable that could have affected the results of this study. Suggest why it would have been important to control this extraneous variable and how it could have been controlled in this study.
- eg type/rhythm of music/equipment/environmental variables.
- participant variables only acceptable if feasibly could have changed in a week eg illness/hydration level/injury/etc.
- explanation of why it is important to control their chosen variable in the context of this study ie the impact on the DV.
- how the stated variable could be controlled.
70
Describe the process of peer review
* other psychologists check the research report before deciding whether it could be published
* independent scrutiny by other psychologists working in a similar field
* work is considered in terms of its validity, significance and originality
* assessment of the appropriateness of the methods and designs used
* reviewer can accept the manuscript as it is, accept with revisions, suggest the author makes revisions and re-submits or reject without the possibility of re-submission
* editor makes the final decision whether to accept or reject the research report based on the reviewers’ comments/recommendations
* research proposals are submitted to panel and assessed for merit.
71
Describe purpose of peer review
* to ensure quality and relevance of research, eg methodology, data analysis etc
* to ensure accuracy of findings
* to evaluate proposed designs (in terms of aims, quality and value of the research) for research funding.
72
Explain why it is more appropriate for the psychologist to use an observation than a questionnaire in this case (about if people actually work out or chat at gym)
An observation would be more appropriate because a self-report method like a questionnaire would lead to socially desirable answers/lying/self-delusion/misremembering,
so would not reflect what really happens at the gym, so the data would lack validity.
73
Design an observational study to investigate how people spend their time at the gym.
In your answer you will be awarded credit for providing appropriate details of:
• type of observation with justification
• operationalised behavioural categories
• use of time and/or event sampling with justification
• how reliability of data collection could be assessed.
• Type of observation with justification
– eg covert or overt, naturalistic, participant or nonparticipant and why
• Operationalised behavioural categories
– detail of at least two specific and observable behaviours to be recorded. This must go beyond the idea of global constructs such as exercising, socialising, use of other facilities
• Use of time and/or event sampling with justification
– recordings can take place at specified time intervals (time sampling) eg every minute or as the behaviour occurs (event sampling) eg number of times interaction occurs with another gym member. The type(s) of sampling must be appropriate for the behaviours chosen
• How reliability of the data collection could be assessed, -
inter-observer reliability eg using two observers/raters and comparing separate recordings; statistical comparison (correlation) of data from both observers/raters, intra-observer reliability eg checking video recordings.
74
A psychologist wanted to test the effects of biological rhythms on the ability to solve maths problems. She used random sampling to form two groups each of 20 students.
She tested one group on one set of maths problems at 3 am in the morning. The other group were tested on another set of maths problems at 3 pm in the afternoon. She found that performance of the group tested at 3 pm was significantly better than the group tested at 3 am.
When submitted for peer review the paper was rejected because of serious design problems.
Explain one problem with the design of this study and suggest ways of dealing with this problem
Problem – random sampling; the 3 pm group might simply have been better at maths than the 3 am group. The solution would be a matched pairs (matched on maths ability) or repeated measures design.
Problem – use of different maths tests, with no evidence that they were matched for difficulty. The solution would be to use the same set of maths problems if a matched pairs design was used.
Individual differences due to independent groups design so use repeated measures but would need different but equivalent tests and counterbalancing.
Other issues, such as individual differences in biological rhythms (‘owls’ versus ‘larks’) confounding results.
75
Should the hypothesis be directional? Explain your answer.
- as there is no reference to evidence that allows the researchers to prediction the direction of the results
76
Write a suitable hypothesis for this investigation. (looking for a correlation)
‘There is a relationship between the map reading scores and the driving error ratings of motorists’.
77
Why a scattergraph is appropriate in displaying these data (looking for a relationship between 2 variable)
because it shows a relationship between two variables
78
comment on the relationship between the map reading scores and the driver rating scores of the participants.
General pattern - if a participant scored highly on the map reading task then they are also rated highly on the practical driving task, (or vice versa)
This suggests a person who has good map reading ability also has good driving skills so these spatial abilities are (positively) related/correlated
79
Briefly outline one problem of using a single trained observer to rate the participants’ driving skills in the practical task.
Briefly discuss how this data collection method could be modified to improve the reliability of the data collected. [
Possible problems:
Researcher bias – using one observer means objectivity/reliability/validity cannot be checked
Possible modifications:
-Increasing the number of observers of the driving task because then the data is less subject to individual bias. The observations could then be correlated
-Recording the driver performance so that the data is not lost but can be reviewed as often as required.
80
The researchers decided to analyse the data using a Spearman’s rho test.
Explain why this is a suitable choice of test for this investigation.
The test determines the strength of a relationship between two variables which is what the researchers
were looking for in their initial aim
The data are in related pairs
The variables under test are both ratings measured at the ordinal level.
81
(Using the table of crit values to see if significant or not)
what conclusion can the researchers draw about the relationship between the map reading and driving skills of the motorists?
Explain your answer.
The null hypothesis should be rejected and the alternative hypothesis accepted
There is a significant (positive) relationship between the map reading ability and the driving ability of the participants
Drivers who are skilled at map reading are also skilled at driving
82
Distinguish between a Type I error and a Type II error
A Type I error occurs when a researcher claims support for the research hypothesis with a significant result when the results were caused by random variables
A Type II error occurs when the effect the researcher was attempting to demonstrate does exist but the researcher claims there was no significance in the results/erroneously accepts the null hypothesis
The difference is that in a Type I error the null hypothesis is rejected when it is true and in a Type II error it is retained when it is false.
83
What do the mean and standard deviation values suggest about the male and female performances in the investigation?
Means: the mean score for males is almost 3 times larger than that of the females which suggests they are very much better at map reading than the females
Standard deviations: sds are quite similar to each other suggesting the spread of performances of the male participants and the female participants is similar within each group
84
Briefly explain one reason why it is important for research to be replicated.
The likelihood of the same differences occurring twice (or more), by chance alone are much smaller than when they occur the first time.
Effects that occur in a study are more likely to be reliable if they occur in a repeat of the study – replication therefore increases (external) reliability
85
Imagine you have been asked to design a study to investigate possible gender differences in card sorting behaviours. You decide you will ask participants to sort a shuffled pack of playing cards into their suits of hearts, clubs, diamonds and spades. You decide you will time the participants as they do this using a stop watch.
Discuss the following aspects of this investigation:
- with reference to the card sorting task, explain how you would ensure that this is made the same task for all participants
- one methodological issue you should take into account when obtaining suitable participants for this study and explain how you would deal with this issue -how you would ensure that the experience of your participants is ethical.
The task: the answer must show an appreciation of the fact that the usual way of merely sorting a shuffled pack of cards into suits will have to be modified in order to ensure that each participant has exactly the same task. [Initial shuffle, record the order, reinstate that order for each participant.]
Suitability of participants: the answer must include information about how familiarity with cards could become a confounding variable if not controlled and how this could be controlled practically.
Ethical issues: specific or more general ethical considerations as applied to this study – protection of welfare, confidentiality, respect or integrity.
86
Identify one extraneous variable that the psychologist should have controlled in the study and explain why it should have been controlled. (3)
```
Identify EV (1)
Explain why should be controlled and how affect DV, eg, can confound results... (2)
```
87
Explain one advantage of using a stratified sample of participants in this study.
ensures that this sample is truly representative because different types of people (males/females) working in this company are represented in the sample in the correct proportions.
88
What conclusions might the psychologist draw from the data in Table 1? Refer to the means and the standard deviations in your answer
Means
• Conclusion: when people believe they are presenting to a large audience they are less fluent in their spoken communication than when they believe the audience is small (or vice versa).
• Justification/Application: this is supported by the difference in the mean fluency scores which show more verbal mistakes (on average 6 more mistakes) when the audience is believed to be large (or vice versa).
Standard deviations
• Conclusion: performances of participants in Condition A where audience is believed to be small are less varied/dispersed/spread out than in Condition B where audience is believed to be large (or vice versa).
• Justification/Application: lower SD in Condition A suggests that individual performances in Condition A were more similar to each other and/or all quite close to the mean of 11.1.
89
Explain how using the standard deviation rather than the range
- this would be an improvement because the SD is a measure of dispersion that was less easily distorted by a single extreme score.
- one that takes account of the distance of all the verbal error scores from the mean.
- not just the distance between the highest verbal error score and the lowest verbal error score.
90
Name an appropriate statistical test that could be used to analyse the number of verbal errors in Table 1. Explain why the test you have chosen would be a suitable test in this case. (mean verbal errors in each condition)
unrelated t-test.
: • can assume interval data because verbal errors can be assumed to be of equal size (ie one verbal error is equivalent to any other verbal error)
• the experimental design is independent groups
• the psychologist is looking for a difference between the two conditions.
Mann-Whitney test.
• data should be treated as ordinal. Cannot assume interval data because verbal errors cannot be assumed to be of equal size (ie one verbal error is not equivalent to any other verbal error)
• the experimental design is independent groups
• the psychologist is looking for a difference between the two conditions
• SDs are quite different.
91
The psychologist found the results were significant at p<0.05. What is meant by ‘the results were significant at p<0.05’
This means that there is a less than 5% likelihood that this difference would occur if there is no real difference between the conditions
OR the researchers would have a 95% confidence level.
92
Briefly explain one method the psychologist could use to check the validity of the data she collected in this study. [
* asking other people if verbal errors are a good measure of verbal fluency (face validity)
* giving participants an alternative/established verbal fluency test and checking to see that the two sets of data are positively correlated (concurrent validity).
93
Briefly explain one reason why it is important for research to undergo a peer review process
* prevents dissemination of irrelevant findings/unwarranted claims/unacceptable interpretations/personal views and deliberate fraud – improves quality of research
* ensures published research is taken seriously because it has been independently scrutinised
* increases probability of weaknesses/errors being identified – authors and researchers are less objective about their own work.
94
Design an observation study to investigate sex differences in non-verbal behaviour of males and females when they are giving a presentation to an audience.
In your answer you should provide details of:
* the task for the participants
* the behavioural categories to be used and how the data will be recorded
* how reliability of the data collection might be established
* ethical issues to be considered.
* The task for the participants – detail of what the men and women in the study will have to do. This must go beyond ‘give a presentation to an audience’.
* The behavioural categories to be used and how the data will be recorded – detail of specific and observable behaviours to be recorded. This must go beyond the idea of global constructs such as ‘body language’ or ‘gesture’. Also detail of recording method to be used, eg record sheet.
* How reliability of the data collection might be established, eg using two observers/raters and comparing separate recordings; statistical comparison of data from both observers/raters.
* Ethical issues to be considered, eg specific or more general ethical considerations as applied to this study – protection of welfare, confidentiality and deception, respect or integrity.
Examples of possible tasks:
• presentation of findings from a school project
• presentation on ‘My Hobby’
• presentation on ‘My Holiday’.
```
Examples of suitable non-verbal behaviours include:
• arm movements
• smiling
• speech hesitations
• pointing etc.
```
