Examination for BSc Psychology (PRACTICE PAPER A)

4PAHPRM2 RESEARCH METHODS 2 PRACTICAL EXAMINATION

Section A

The questions in Section A are about the article by Shalvi et al. (2012).

You are provided with a replication of Experiment 1 from this article in an SPSS data file named: Shalvi et al Replication Expt 1.sav

Use the data in this file to answer the questions that follow.

Question A1 [11 marks available]

Shalvi et al. (2012) report this analysis on page 1266 of their article:

Time. As we expected, participants in the high-time-pressure condition took less time to report the outcome of the die role (M = 10.8 s, SD = 4.4 s) than those in the low-time-pressure condition (M = 23.2 s, SD = 11.2 s), t(70) = −6.01, p < .001, which indicates that the time-pressure manipulation was successful.

Repeat this analysis for the data that you have been given, and report it.

(a) Table A1. Time taken in seconds to report the outcome of the die role (report values to one decimal place)

(b) Report the test statistic (to two decimal places): t = __________

(c) Report the degrees of freedom df =  __________

(d) Report the exact p-value (to three decimal places): p ____________

(e) Is the result statistically significant? (Select one answer): Yes  /  No

(f) The outcome of this test has important implications for how other analyses in this experiment are interpreted. In this regard, briefly explain what the main implication of a non-significant outcome to this test would be.

[A1: 11 marks available]

Question A2 [11 marks available]

Shalvi et al. (2012) report this analysis of the low-time-pressure condition on page 1266 of their article:

The distribution of reported outcomes differed from the uniform. distribution expected from a fair die roll in [both] the low-time-pressure condition, χ²(5, N = 38) = 13.47, p = .02, …

Repeat this analysis for the data that you have been given, and report it.

HINT: You should use a filter or split the file to examine ONLY the data for the low-time-pressure condition.

(a) Table A2. Expected frequencies if the data follow a uniform. distribution, and observed frequencies for the number reported as showing on the die.

(b) Report the test statistic (to two decimal places): = __________

(c) Report the degrees of freedom df =  __________

(c) Report the sample size for this analysis N = __________

(d) Report the exact p-value (to three decimal places): p ____________

(e) Is the result statistically significant? (Select one answer): Yes  /  No

(f) Which kind of chi-square test did you use? (Select one answer):

Chi-square goodness-of-fit test / Chi-square test for contingency tables

(g) What do you conclude from this test? (One sentence is sufficient)

[A2: 11 marks available]

HINT: If you have used a filter or split the file on this question, REMOVE THE FILTER/SPLIT BEFORE MOVING ON TO THE NEXT QUESTION.

Question A3 [11 marks available]

Shalvi et al. (2012) report this analysis that includes a Mann-Whitney U test on page 1266 of their article:

Supporting our hypothesis, participants in aggregate lied significantly more, by reporting higher die-roll outcomes, in the high-time-pressure condition (M = 4.56, SD = 1.48) than in the low-time-pressure condition (M = 3.87, SD = 1.61), Mann-Whitney Z = 2.03, p < .05.

Repeat this analysis for the data that you have been given, reporting the descriptive statistics in Table A3, and the outcome of the Mann-Whitney U test below.

(a) Table A3. Outcome of die-role reported by participants

(report values to two decimal places)

(b) Report the test statistic for this Mann-Whitney U test

(to two decimal places):

_________  = __________

(c) Report the sample size for this analysis N = __________

(d) Report the exact p-value (to three decimal places): p ____________

(e) Is the result statistically significant? (Circle one answer): Yes  /  No

(f) Is the conclusion from this test the same as, or different to, the conclusion that Shalvi et al (2012) reported for the equivalent analysis (see extract above)? (Select one answer):

(g) Give one reason that might explain why the researchers used a (non-parametric) Mann-Whitney U test to analyse this difference between the two conditions, in preference to using a t-test (as would be more usual when examining a mean difference).

[A3: 11 marks available]

Question A4 [12 marks available]

(a) Which of the following research terms accurately describe some aspect of the design or analysis of Experiment 1 of Shalvi et al. (2012):

Select ‘Yes’ or ‘No’ for each term.

(b) Justify the answers that you gave in part (a) above. (The equivalent of one or two well-written sentences per part (i to iv) will be sufficient for this question.)

[A4: 12 marks available]

Section B

The questions in Section B are about the Cognitive Styles Study

Use this data file for Section B: Cognitive Styles Specimen Data.sav

Question B1 [4 marks available]

(a) Obtain Cronbach’s alpha for the CFC scale, and write the value below.

Give the value of alpha to three decimal places

a =  ________________

(b) Which one of the ten questions/assumptions or study hypotheses does this value (a) provide information for? (Select one answer)

(c) With respect to this question/assumption or study hypothesis that Cronbach’s alpha can be used to examine, the value of a that you have recorded above would usually be regarded as (select one answer):

[B1: 4 marks available]

Question B2 [12 marks available]

This question is about study hypothesis H7a:

H7a There will be a positive linear relationship between NFC score and the number of years spent in post-compulsory full-time education.

You will examine this hypothesis using simple linear regression.

Undertake the appropriate analysis that will allow you to obtain the equation for the regression line that can be used to predict overall NFC score from the number of years spent in post-compulsory full-time education.

(a)(i) Write down the equation for the regression line for this analysis, using N for the overall NFC score and P for the number of years spent in post-compulsory full-time education.

Values in the equation should be given to three decimal places.

Equation: ______________________________________________

(ii) Use the equation for the regression line to calculate the expected overall NFC score for a participant who has spent five years in post-compulsory education. Show your working in the space provided.

Your final answer should be written correct to one decimal place

Answer (expected NFC score): _______________

(iii) Use your equation from part (a)(i) to answer the following question. Imagine that there are two people, and that one of these has spent one more year in post-compulsory full-time education than the other.

What is the expected difference in overall NFC score between these two people? This answer should be given to three decimal places

Expected difference in NFC score: _______________

Question B2 (continued)

(b) What is the percentage of variance in overall NFC score that is accounted for by the number of years spent in post-compulsory full-time education?

Give the percentage to one decimal place.

_____________ %

(c)(i) For the linear relationship examined by this regression analysis, write down the unstandardized regression coefficient (b), the standardized regression coefficient (b) and the exact p-value for the regression.

Give these values to three decimal places

b = ____________ b = ____________ p = ____________

(ii) Is the regression statistically significant? (Circle one answer)

Yes  /  No

(iii) One of these three values listed in part (c)(i) above is also the Pearson correlation (r) for the relationship between the overall NFC score and the number of years spent in post-compulsory education. Which one of the three is this? (Circle one answer)

[B2: 12 marks available]

Question B3 [23 marks available]

For this question, you need only consider the following two hypotheses that relate to the consideration of future consequences (CFC):

H6b People that invest in shares will have higher CFC scores than those that do not invest in shares.

H8 There will be a negative linear relationship between CFC score and the number of cigarettes smoked per week.

Use the data that you have been provided with to write a Results section that would be appropriate for a research report in psychology. Analyse and report only the information that is appropriate and relevant to the two hypotheses listed above. You should assume that the only variables of interest for your Results section are the ones needed to investigate these two hypotheses.

You may use tables and graphs where necessary or beneficial. Marks will be awarded for layout, clarity and correct interpretation of the statistical data, and appropriate description of how the data were treated. In order to save space and time, you may use the abbreviations H6b and H8 to refer to the hypotheses. Any other abbreviations that you use should be defined first. You may assume that parametric statistical tests can be used for analyses that involve measurement data (i.e., for analyses that involve at least one NON-categorical variable). Report a t-test if you are analyzing a mean difference.Write your Results section in the space provided below.

[B3: 23 marks available]