MMB-MOCK Flashcards
Question 1
a. An essential feature of science is that it makes statements which are testable.
t/f
TRUE
Question 1b
b. A Likert scale produces a variable on a ratio scale.
FALSE
Question 1c
c. An “operational definition” of a variable or construct consists of specifying the set of activities required to measure that variable or construct.
TRUE
Question 1d
d. The gold standard for providing evidence of causality is the doubleblind, randomised controlled trial.
TRUE
Q 2a
a. The Type I error rate is always equal to the significance value (alpha) adopted for the test.
TRUE
Q 2b
b. A common null hypothesis when comparing a dependent variable between two groups is that the mean of the population of scores from which the first group was drawn is equal to the mean of the population of scores from which the second group was drawn.
TRUE
Q 2c
c. The p value yielded by a statistical test in SPSS is the probability of getting a result at least as extreme as that observed, if the null hypothesis is false.
FALSE
null needs to be true not false
Q 2d
d. For a test with a symmetric distribution and for a given set of data, you can find the pvalue for a one tailed test of these data by halving the pvalue for the corresponding two tailed test.
TRUE
Q 3a
a. An effect size is another measure of statistical significance; it can be defined only for a specific set of sample data, never for a population.
FALSE
An effect size can be calculated based on the population.
Q 3b
b. With a significance (alpha) level of 5%, the power will be 95%.
FALSE
Power is not right it is not linked to type 1 error rate
Q 3c
c. When designing an experiment, if it is required to calculate power, it is not normally necessary to make some prior estimate of effect size.
FALSE
Q 3d
d. If the treatment and control means for some DV in a population are 40 units and 30 units, and the standard deviation for the DV is 20 units, then Cohen’s “d” is calculated to be 0.5.
TRUE
Cohen’s “d” = difference between means divided by SD
= M1-M2/SD
Hence “d” = 40-30/20 = 0.5
Q 4a
a. Multiple regression requires a parametric DV and parametric and/or dichotomous (two valued) IVs (categorical IVs with more than two levels must be dummy coded).
TRUE
You can use parametric for variables.
A parametric variable is the same as a continuous variable
Q 4b
b. The null hypothesis when testing a model in multiple regression is that in the population, the DV correlates with some linear function of the IVs.
FALSE
The null hypothesis is that the DV has no relation to the IVs at all.
Q 4c
c. The value of the unstandardised coefficient for a given IV in multiple regression is the amount by which the DV is predicted to change when that IV is increased by 1, the other IVs being held constant.
TRUE
Remember the definition of regression coefficients.
Q 4d
d. “Adjusted Rsquared”in multiple regression is a measure of the amount of variance in the DV accounted for by the IVs collectively.
TRUE
“Adjusted Rsquared” is a kind of effect size. The output will tell us how good the model is at predicting the DV.
Q 5a
a. Possible alternatives to Fisher’s F test that are often used are a priori contrasts, and post hoc comparison of means.
TRUE
Q 5b
b. Fisher’s F test looks at the ratio between the measures of variability between, and within groups, and declares a significant result if this ratio is small enough.
FALSE
ratio is large enough.
Q 5c
c. If the null hypothesis is true, the group means for the data from a sample will all be exactly equal.
FALSE
There will be noise - it will likely never be exactly equal..
Q 5d
d. If more than one a priori contrast is performed, the significance level (alpha) that is used must be multiplied by the number of comparisons, to prevent inflation of type I error rates.
FALSE
must be divided
Q 6a
a. A basic assumption in repeated measures ANOVA is sphericity.
TRUE
Q 6b
b. The presence of an interaction between two factors means that the effect of one factor on the DV varies, as the level of the other factor alters.
TRUE
Q 6c
c. When using multifactorial ANOVA, you should never combine repeated measures and independent groups IVs in the same analysis.
FALSE
You can combine them
Q 6d
d. In a line plot of two IVs, an interaction will show itself as a lack of parallelism between the lines.
TRUE
Q 7a
a. The z value of a data point is its distance from the mean, measured in units of the standard deviation.
TRUE
Q 7b
b. A z value of 1 corresponds to the 50% percentile point in a normal distribution.
FALSE
It coresponds to 0
Q 7c
c. An IQ of 70 corresponds to a z value of 2, if the mean is 100 and the s.d. is 15.
TRUE
Q 7d
d. Approximately 95% of the points for a normally distributed population lie between z = –2 and z = +2.
TRUE
Q 8a
a. The Bonferroni correction for multiple testing is applied by using a stricter alpha value, found by dividing some conventional value (such as .05) by the number of comparisons.
TRUE
Q 8b
b. Tukey’s “honestly significant difference” is an a priori test and it automatically corrects for inflation of type I error rate.
FALSE
Q 8c
c. When comparing means, it is essential to do an omnibus F test first, and only if that is significant can you legitimately use either an a priori or a post hoc test.
FALSE
Q 8d
d. The definition of a “contrast”, is that it is a formula involving group means in which all the coefficients add up to one.
FALSE
the coefficients add up to zero.
Q 9a
A fibre is found at the scene of a crime. The chief suspect owns a coat which, police suspect, he was wearing when committing the crime. The fibres on this coat have a thickness averaging 1.0 mm, with a standard deviation of 0.1 mm, and the thickness appears to have a normal (Gaussian) distribution. A fibre was found at the crime scene which appears very similar in colour and type of material to the suspect’s coat. The diameter of the fibre at the crime scene is 0.7 mm, i.e. 0.3 mm less than the mean for the coat. Which one of the following statements is true?
Select one:
a. The appropriate statistical test to apply is the t test, and the statistic to be tested is t = 0.3/0.1. If the test is significant, the coat was probably not the source of the fibre at the crime scene.
b. The appropriate statistical test to apply is the Wilcoxon Signed Rank test, and if the test is significant, the coat was 95% certain to have been the source of the fibre at the crime scene.
c. The appropriate statistical test to apply is the z test, with z = 0.3/0.1, and if the test is significant, the coat was probably not the source of the fibre at the crime scene.
d. Since there was only one fibre recovered, no estimation of the standard deviation of fibres from the perpetrator’s coat can be made, and therefore no conclusions can be drawn as to the guilt of the suspect.
c. The appropriate statistical test to apply is the z test, with z = 0.3/0.1, and if the test is significant, the coat was probably not the source of the fibre at the crime scene.
Only a single hair.. SD.
Q 10a
a. Cohen’s “d” is defined as the population standard deviation divided by the difference between the group means.
FALSE
difference between the group means / SD
Q 10b
b. The outcome of a significance test will tell you whether an effect is present but not, directly, how much of an effect is present.
TRUE
Q 10c
c. Values of “d” of 0.2, 0.5 and 0.8 are described as “small”, “medium” and “large” effect sizes.
TRUE
Q 10d
d. It is necessary to make some estimate of likely effect size in advance, when doing the power calculation for a planned experiment.
TRUE
Q 11a
You have conducted five separate ttests, and have read off the following pvalues from an SPSS output, which provides no protection against inflation of type I error: .045, .04, .02, .005, .001. You are using a basic 2tailed alpha criterion of .05. How many of these results should you declare as significant, having applied a
Bonferroni correction?
a. 1
b. 2
c. 3
d. 5
b. 2
.05/5 = .01
Q 12a
a. The usual null hypothesis with correlations is that the population correlation ρ is nonzero.
FALSE
Q 12b
b. If r is nonzero, the null hypothesis is rejected.
FALSE
If r is [significantly] nonzero
Q 12c
c. A correlation of - 1 means that the variables are independent.
FALSE
-1 means the variables are correlated.
Q 12d
d. Testing the null hypothesis with correlations involves determining if the observed sample correlation r is significantly different from zero.
TRUE
Q 13a
Refer to the scatterplot: Which one of the following alternative problems does this scatterplot appear to suggest?
a. Nonlinearity.
b. Heteroscedasticity (violation of the assumption that standard deviations of errors are equal for all predicted DV scores).
c. Presence of outliers in the solution.
d. Multicollinearity.
b. Heteroscedasticity (violation of the assumption that standard deviations of errors are equal for all predicted DV scores).
Q 14a
- Refer to the line plot - It represents the results of a two way ANOVA designed to measure the effects of gender and leglength on some aspect of musicality.
Which one of the following statements does this plot appear to illustrate?
a. There is a main effect of gender, no main effect of leglength, and an interaction.
b. There is a main effect of leglength, no main effect of gender, and no interaction.
c. There is a main effect of both gender and leglength, but no interaction.
d. There is a main effect of leglength, no main effect of gender, and an interaction.
d. There is a main effect of leglength, no main effect of gender, and an interaction.
A qualatative interaction as there is a cross.
Q 15a
a. It is an assumption of most parametric tests involving separate groups that the distributions of the DV within the groups do not depart too far from normality.
TRUE
separate groups (cells may be a better answer)
Q 15b
b. Multivariate outliers can be detected in a distribution by looking at histograms of each individual variable.
FALSE
Q 15c
c. Correlation calculations are not sensitive to the presence of outliers.
FALSE
Q 15d
d. Multicollinearity in a set of continuous independent variables can be detected by a significance test on the size of the Mahalanobis distance.
FALSE
Q 16a
a. It is not possible to enter a categorical (noninterval) variable with fewer than three levels as an IV into a multiple regression unless it is first coded into a number of dichotomous variables.
FALSE
Q 16b
b. The dummy coding of a categorical variable with 4 levels requires the substitution of two dichotomous variables for the original single categorical variable.
FALSE
n - 1 = number to be dummy coded.
Q 16c
c. Dummy coding of a categorical IV of N levels involves the choice of particular level of the categorical variable, with which the other N – 1 levels are compared, using N + 1 dummy variables.
FALSE
N - 1
Q 16d
d. Suppose a multiple regression includes just one IV, which is a multilevel categorical IV. Then the results of the significance tests carried out in SPSS on the regression coefficients of the dummy variables are equivalent to a set of t tests in univariate ANOVA. These t tests compare the levels of the DV for one fixed level of the categorical variable, and those of all the other levels of the variable.
TRUE
This is correct - to remind us that when looking at regression coefficients we are actually doing a one sample t test. Testing whether the regression coefficient is far enough from zero to be significant.
A zero regression coefficient has no predictor on the DV.
Q 17a
a. The basic idea of ANCOVA is one of “signal reduction”: it is used to improve the power of an ordinary ANOVA by using a covariate to reduce the effect size associated with the ANOVA.
FALSE
ANCOVA is noise reduction - to improve the signal to noise ratio.
Q 17b
b. In order to be of value in an ANCOVA, the covariate should have no significant correlation with the DV.
FALSE
the covariate should correlate with the DV.
Q 17c
c. One requirement for the validity of ANCOVA is homogeneity of regression, i.e. if regression lines are plotted separately for each group for the DV on the CV, the slopes of these lines do not significantly differ from one another.
TRUE
Q 17d
d. ANCOVA can give misleading or uninterpretable results if the various groups in the ANOVA are randomly allocated, and if they fail to differ significantly in their mean values of the covariate.
FALSE
opposite of truth - ANCOVA is good if you have randomly alocated groups
Q 18a
a. The type I error rate is equal to the alpha significance level, and the type II error rate (in percent) plus the power (in percent) equals 100%.
TRUE
Q 18b
b. The type I error rate is equal to alpha, and the type II error rate equals the power.
FALSE
Q 18c
c. The type I error rate plus the type II error rate equals 100%.
FALSE
Q 18d
d. The power plus the type I error rate equals 100%.
FALSE
Q 19a
In writing an academic paper describing experimental results for publication, which one of the following is generally not recommended?
a. Including separate subheadings for Design, Participants, Apparatus and Procedure in the Methods section.
b. Giving a detailed summary of previously published work in similar areas in the Introduction section.
c. Including an indepth discussion of the interpretation of the experimental findings in the Results section.
d. Mentioning and evaluating any limitations of the study in the Discussion section.
c. Including an indepth discussion of the interpretation of the experimental findings in the Results section.
Q 20a
An experiment is intended to measure whether a person’s appearance affects perceptions of their ability to perform a job. Participants rated photographs of individuals as either smartly dressed or not smartly dressed, and were asked to rate their organizational and leadership skills, on a scale of 1 to 20. The gender of the participants was evident from the photographs. Which one of the following statements about this design is false?
a. This is a multifactorial design, with two IVs and a continuous DV. It would probably be analyzed using a 2x2 ANOVA.
b. Each IV has two levels, and one degree of freedom, and the interaction term also has one degree of freedom.
c. The analysis of the data produced by this study yields three separate tests of significance.
d. In this design, standard of dress is a twolevel, categorical IV. Gender is determined before the experiment begins and is not a variable, and therefore cannot be included in the analysis.
d is FALSE
d. In this design, standard of dress is a twolevel, categorical IV. Gender is determined before the experiment begins and is not a variable, and therefore cannot be included in the analysis.
Q 21a
a. A high value for Cronbach’s alpha for a set of test items always demonstrates a satisfactory outcome, and makes it unnecessary to check separately whether the instrument is truly unifactorial.
FALSE
Cronbach’s alpha is a test of internal consistancy -
eg. using a single factor for a questinnaire
Cronbach’s alpha tells us which questions are contributing positiviely to the factor.
Q 21b
b. At the rotation stage of an Exploratory Factor Analysis, it is a good idea to use an orthogonal rotation such as varimax in the first instance, unless you have good reason to suppose that factors are oblique.
FALSE
oblique rotation is best
Q 21c
c. Cronbach’s alpha is a measure of external validity amongst the items of some measuring instrument.
FALSE
internal validity
Q 21d
d. Kaiser’s criterion for determining the number of factors is not recommended in general.
TRUE
Kaiser’s criterion tends to be over inclusive.
Q 22
An exploratory factor analysis of 15 variables yields the following scree plot. How many factors would you advise extracting in the light of this?
Select one:
a. Two, because one should not include the “elbow” when estimating the number of factors.
b. Three, because Kaiser’s criterion dictates that all eigenvalues over one should give rise to a factor.
c. Three, because one should include all components down to and including the “elbow” in a scree plot.
d. Five, because there should be at most three times the number of variables as there are factors.
a. Two, because one should not include the “elbow” when estimating the number of factors.
Q 23
In an attempt to evaluate the effectiveness of different approaches to discouraging smoking, smokers were exposed to two different deterrents. One group of smokers were shown graphic pictures of patients with serious smokingrelated illnesses, and another group was asked to read an article on the economic disavantages of smoking. Subsequently, each participant was shown three smokingrelated products: a standard cigarette, a lowtar cigarette and nicotine lozenges. They were asked to evaluate the overall appeal of these products after exposure to the deterrents, and the scores were noted for each product. Which one of the following statements is true?
Select one:
a. This is a mixed, between subjects and within subjects design; the between subjects variable is the type of deterrent to which a participant is exposed, and the within subjects variable consists of the three smoking related products. It would be analyzed in SPSS using the repeated measures ANOVA program.
b. This is a mixed, between subjects and within subjects design; the between subjects variable is the type of smoking related product being evaluated, and the within subjects variable is the type of deterrent to which a participant is exposed.
c. A significant main effect of the repeated measures variable would suggest that the deterrents tested, overall, have more effect on altering the appeal of some smoking products than others.
d. A significant interaction between the betweensubjects variable and the within subjects variable would suggest that one of the deterrents has a greater impact than the other, overall, on the appeal of the tobacco products tested.
a is TRUE:
a. This is a mixed, between subjects and within subjects design; the between subjects variable is the type of deterrent to which a participant is exposed, and the within subjects variable consists of the three smoking related products. It would be analyzed in SPSS using the repeated measures ANOVA program.
Q 24a
a. Exploratory factor analysis basically involves identifying clusters of variables that are correlated with other variables within the cluster, but not strongly correlated with variables in other clusters.
TRUE
Q 24b
b. The first step in a factor analysis, following data cleaning, is to rotate the solution using an oblique or orthogonal method.
FALSE
It is finding how many factors using a scree
Q 24c
c. With an oblique rotation, you should examine the structure matrix rather than the pattern matrix for evidence of a simple factor structure.
FALSE
examine the pattern matrix not the structure matrix
Q 24d
d. Bartlett’s test of sphericity should be nonsignificant for any factors to exist.
FALSE
should be significant
