Quiz
Psychological Research Methods Exam practice
Questions in this quiz (47)
1The WAIS intelligence quotient (IQ) is normally distributed with a mean of 100 and a standard deviation of 15. I fan IQ between 85 & 115 is deemed normal, what percentage of the the general population would be considered normal?
- A30%
- B50%
- C70%
- D90%
2In the four bivariate relationships given below, in terms of person-product moment correlations (r), the strongest relationship is one for which r is:
- A.69
- B-.70
- C-.10
- D.01
3In correlational analysis, skewed variables are transformed to be normally distributed because:
- Athis increases the relationship between variables
- Bthis decreases the relationships between variables
- Cthe removes the effect of influential points
- Dthis might invalidate the test
4Which on of the following does not increase the power of a test of r between X & Y?
- AStandardising the scores of X & Y (Llinear transformation)
- BAdopting a larger Type 1 error rate
- CConducting a one tailed test instead of two tailed
- DIncreasing the magnitude of r
5In clinical trials, it is ethnically responsible to use a sample size that is sufficient enough to detect an effect but not too large as to inconvenience the patient any longer than necessary. Which sample size should the research use to ensure that she has sufficient power?
- AN = 15 (power of .70)
- BN = 22 (power of .80)
- CN = 30 (power = .90)
- DN = 37 (power of .95)
6In clinical trials, it is ethnically responsible to use a sample size that is sufficient enough to detect an effect but not too large as to inconvenience the patient any longer than necessary. Which sample size should the research use to ensure that she has sufficient power?
- AN = 15 (power of .70)
- BN = 22 (power of .80)
- CN = 30 (power = .90)
- DN = 37 (power of .95)
7What is a type 1 error?
- AAccepting the null hypothesis when it is false
- BRejecting the null hypothesis when it is true
- CAccepting the null hypothesis when it is true
- DRejecting the null hypothesis when it is false
8A scatterplot of the residuals is NOT used to check for:
- Anormality of distribution of errors
- Bthe relationship between variables
- Ca non-random distribution of the residuals
- Dhomogeneity of variance of errors
9Which case will not be considered an influential in a regression of Y on X?
- AA case with a mean of X and a large Y
- BA case with a small X and a mean of Y
- CA case with a large X and a small Y
- DA case with a mean of X and a mean of Y
10When a regression line is fitted to the data, the lack of fit is best described by:
- AA negative correlation coefficient
- BA random distribution of the residuals
- CA non-random distribution of the residuals
- DA small unstandardised regression coefficient
11If the assumption of heteroscedasticity has been violated, the residual while display...?
- AA random distribution of the residuals
- BA curvilinear distribution of the residuals
- CA denser portion of residuals above the line
- DA fanning out of residuals to one side
12In multiple regression, the effect size of the prediction is given by the:
- Amultiple correlation coefficient
- Bsquared multiple correlation coefficient
- Csum of the squared beta coefficients
- Dsum of the individual squared correlations between the independent variable and the dependent variable
13In standard multiple regression where X1 & X2 are used to predict Y, the square of the multiple correlation (R2) is:
- Athe sum of the correlations between Y and X1 and between Y and X2
- Bthe sum of the squared correlations between Y and X1 and between Y and X2
- Cthe proportion of variance in Y uniquely & jointly predicted by X1 & X2
- Dthe proportion of variance in Y uniquely & jointly predicted by X1 plus the proportion of variance in Y uniquely predicted by X2
14In a standard multiple regression, X1, X2 & X3 were used to predict Y. The obtained F statistic had a probability of .001. The unstandarised equation of predicted Y was .8X1 + .4X2 + .3X3 + .5. The semi-partial correlations of X1, X2 & X3 were .15, .25 & .05 respectively. We can conclude that....
- AThe set of predictors did not significantly predict Y
- BX1 is a stronger predictor of Y than X2 or X3
- CX3 alone would not significantly predict Y
- DX2 makes the best unique contribution to the prediction of Y
15In a standard multiple regression of X1, X2 & X3 predicting Y, the tolerance value of X1 is the proportion of variance in X1 that is...
- Ashared with X2 & X3 but not with Y
- Bshared with Y but not with X2 & X3
- Cnot shared with X2 & X3
- Dshared with X2 & X3
16In a table of intercorrelations, predictor X1 had the highest, and statistically significant, correlation with Y (the dependent variable). Which one of the following statement is FALSE?
- AIn a forward regression, X1 was not included in the final equation because its contribution was redundant to other predictors that entered the equation
- BIn a backward regression, X1 was not included in the final equation because its contribution was redundant to other predictors that entered the equation
- CIn a stepwise regression, X1 was not included in the final equation because its contribution was redundant to other predictors that entered the equation
- DIn a hierarchical regression, X1 was not relevant to the hypothesis being tested
17In a study that had collected initial weight, weight loss after training, motivation to lose weight, duration of training period, and amount of exercise, what is likely to be the dependent variable?
- AWeight loss after training
- BMotivation to loose weight
- CDuration of training period
- DAmount of excercise
18In the study described in (2), which of the following regression methods would allow the most sophisticated test of a theory on weight loss?
- AMultiple regression
- BHierarchical regression
- CStepwise regression
- DBackward regression
19In the study described in (2), if you were select a predictor to enter in the first step, which would you select?
- AInitial weight
- BMotivation to lose weight
- CDuration of training period
- DAmount of exercise
20In a hierarchical regression predicting Y, predictors X1 and X2 as Subset A were first entered by the researcher, followed by predictors X3 and X4 as Subset B. Which one of the following statements is definitely true?
- APredictors in subset A are not correlated with predictors in subset B
- BPredictors in subset A account for more variance in Y than predictors in subset B
- CTotal R2 is the sum of the changes in R2 due to the entry of Subset A and Sunset B
- DTotal R2 is the sum of the squared correlations between Y and each predictor
21Which one of the following is most likely a polytomous variable>
- AGender
- BAge
- CMarital status
- DIncome
22A researcher collected data on religious affiliation and involvement in gambling. Religious affiliation was a polytomous variable with four categories; namely, Christian, Buddhist, Muslim, and “No religion”. Three dummy variables (0,1), called Christian, Buddhist, and Muslim, were created to represent Christian, Buddhist, and Muslim affiliations, respectively. In a stepwise multiple regression to predict gambling, Christian and Buddhist were the two predictors selected. In interpreting the effect of Christian in this regression, which one of the following statements is definitely true?
- A C tests the effect of Christian versus Buddhist on gambling
- B C tests the effect of Christian versus Buddhist and Muslim on gambling
- C C tests the effect of Christian versus Muslim and “No religion” on gambling
- D C tests the effect of Christian versus “No Religion” on gambling
23In a large sample (N = 500), removing a poor fitting case with a large standardized residual (i.e., ZRE_1) is likely to
- ADecrease R2 a little
- BDecrease R2 a lot
- CIncrease R2 a little
- DIncrease R2 a lot
24The magnitude of the pearson product-moment correlation (r) between X & Y is not biased by:
- Asize of the sample
- Bnon-normality in X
- Cnon-normality in Y
- Dnon-linearity of the relationship
25The external validity of an experiment can by improved by:
- Ausing a representative sample of the population
- Bholding constant the effect of nuisance variables
- Cbalancing the effect of nuisance variables
- Drandom assignment of participants to treatment groups
26The external validity of an experiment can by improved by:
- Ausing a representative sample of the population
- Bholding constant the effect of nuisance variables
- Cbalancing the effect of nuisance variables
- Drandom assignment of participants to treatment groups
27Balancing nuisance factors (e.g., sex, age) neutralizes their potential effects on the internal validity of an experiment, but nuisance factors can still
- Adecrease sensitivity and increase external validity
- Bdecrease both sensitivity & external validity
- Cincrease sensitivity & decrease external validity
- Dincrease both sensitivity & external validity
28The defining characteristic of a true experiment is:
- Athe high degree pf control in testing
- Bthe random assignment of subjects to experimental & control conditions
- Cthe operationalisation of dependent variables
- Dthe systematic manipulation of independent variables
29A sample of 100 participants were randomly allocated into two equal-sized weight loss programmes - one that focussed on dieting and the other that focussed on exercise. At the end of 20 weeks of training, 32 participants remained – 20 in the dieting group and 12 in the exercise group. Results show that the weight lost by the dieting group was significantly less than that of the exercise group. A criticism of this experiment is that the findings may be biased by the effect of:
- Ahistory
- Bselection bias
- Cattrition
- Dregression to the mean
30Use of control group, plus random assignment of participants to treatment, would allow us to avoid:
- Aselection bias
- Battrition
- Cexperimenter bias
- Deffects from testing
31The ANOVA tests for differences between
- Avariances of the groups
- Bstandard deviations of the groups
- Cmeans of the groups
- Dindividuals of the groups
32A statistically significant result means that the obtained probability (p) of the test statistic is
- Aless than .05
- Bequal to .05
- Cgreater than .05
- Dgreater than 1
33If assumptions of the ANOVA are violated, the actual Type 1 error rate will...
- Abe greater than a
- Bequal to a
- Cbe smaller than a
- Dbe smaller of greater than a
34A Brain Training software company claims that its 20-week training programme can increase a person’s IQ by five points. Given that the normative mean of IQ is 100, with a standard deviation of 15, the magnitude of the claimed effect is
- Anegligible
- Bsmall
- Cmedium
- Dlarge
35A Brain Training software company claims that its 20-week training programme can increase a person’s IQ by five points. Given that the normative mean of IQ is 100, with a standard deviation of 15, the magnitude of the claimed effect is
- Anegligible
- Bsmall
- Cmedium
- Dlarge
36Upon obtaining a significant F test result in an ANOVA comparing mean weekly gambling frequency of Catholics, Protestants and Non-Christians, what test(s) would you use to compare the group means?
- Athe student t-test
- Bthe student newman keuls test
- Cthe tukey HSD test
- Dthe tukey kramer test
37In between subjects ANOVA, the error term is the unexplained variance of the dependent variable. A second facotr when included in a one-way ANOVA, making it a two-way ANOVA, has the effect of:
- Acontrolling another source of variance, and increasing the error term
- Bcontrolling another source of variance, and decreasing the error term
- Cadding another source of variance, and increasing the error term
- Dadding another source of variance, and decreasing the error term
38In a two-way ANOVA, the number of possible F ratios is
- A4
- B3
- C2
- D1
39When a significant F ratio is found for interaction in ANOVA of two factors (A & B) the next steps is to test:
- Amain effect of factor A
- Bmain effect of factor B
- Csimple main effect of A & B
- Dassociation of A & B
40A researcher performed a two-way between-subjects ANOVA - the p value obtained for the first factor (AGE) was .020, the p value obtained for the second factor (GENDER) was .060 and the p value for the interaction (AGE x GENDER) was .040. The most appropriate conclusion to make at this point, without further testing, is:
- Aage is statistically significant and gender is not statistically significant
- Bage is statistically significant under some level of gender
- Cgender is statistically significant under some level of age
- Db or c, or both
41Planned orthogonal contrast should be used:
- Afor setwise comparison means
- Bfor pairwise comparison means
- Cfollowing a significant F in the oneway ANOVA
- Din place of the overall F test in ANOVA
42The most conservative pairwise comparison between a set of four means is:
- Athe t test
- Bthe scheffe test
- Cthe student newman keuls test
- Dthe tukey test
43In a conventional experiment involving five planned comparisons, the bonferroni method would have a set error rate to:
- A<.01
- B.01
- C<.05
- D.05
44Which of the following statements about a set of orthogonal contrasts between five groups is FALSE?
- Athe coefficients of a linear contrast sum to 0
- Bthe cross products of coefficients of any pair of contrasts sum to 0
- Cthe can at most be five contrasts in the set of orthogonal contrasts
- Dthere are more than one set of orthogonal contrasts
45In an analysis of covariance (ANCOVA) on the final weight of participants in a group focussing on diet and those in a group focussing on exercise, it is important to partial out the effect of:
- Ainitial weight
- Bage
- Cgender
- Dgroup
46In an one-way analysis of covariance (ANCOVA), there is the dependent variable (DV), the independent variable (IV), and the covariate (CV). The purpose of ANCOVA is to test:
- Adifferences between the IV on the DV that is not explained by the CV
- Bdifferences between the IV on the CV that is not explained by the DV
- Cdifferences between the IV on the DV and the CV
- Ddifferences between the IV on the CV and the DV, after adjusting for each other
47In within-subjects ANOVA, the Greenhouse-Geisser epsilon-correction procedure is employed to handle an untenable assumption about the
- Ahomogeneity of variances
- Bhomogeneity of covariances
- Cindependence of observations
- Dnormality of distribution of observations.
Information
- Description
- Quiz on Psychological Research Methods Exam practice, created by Emma Cox on 24/06/2014.
- Author
- Emma Cox
- Language
- English
- Views
- 63
- Rating
- 5.0 out of 5 · 1 rating Rate this quiz