Chapter 17
SSr is __ in a repeated-measures ANOVA than in an independent design: a. smaller b. larger c. equal (but calculated differently) d. the same (give or take some measurement error)
a
The impact that one factor has on the outcome measure across all levels of the other factor is called: a. a main effect b. an interaction effect c. a simple effect d. none of the above
a
in a factorial analysis of variance, the degrees of freedom for the interaction effect is found by taking a. the model degrees of freedom, minus the degrees of freedom for each main effect b. the number of scores minus the degrees of freedom for the both main effects, minus 1 c. the number of cells minus the number of variables d. the number of scores minus the number of cells
a
in a factorial design, the interaction term a. is part of the linear model and behaves like any other predictor b. is added to the linear model but is not part of the linear model c. is part of the linear model but does not behave like other predictors d. is not explicitly represented in the linear model, but emerges from the main factors
a
in a two-way analysis of variance, what do you use as the population variance estimate for the denominator of the F ratios for the main and interaction effects? a. MSr b. Each is tested using a variance estimate based on the variation within the appropriate groupings (for example, the row effect is tested using an estimate based on averaging variance estimates of scores within each row) c. each tested using a variance estimate based on the variation among the appropriate marginal (or diagonal) means (for example, the row effect is tested using as the denominator an estimate based on the variance among the marginal row means.) d. the row and column effects are tested using an estimate based on the variation within the appropriate groupings (for example, the row effect is tested using an estimate based on averaging variance estimates of scores within each row), bus the interaction effect is tested based on averaging the estimates based on variance of scores within each cell
a
in a two-way factorial design, b1 a. is the difference between the two levels of Factor 1 when Factor 2 is at its base levels b. is the difference between the two levels of Factor 2 when Factor 1 is at its base level c. is equal to the group mean of the category for which all predictor variables have been dummy coded 1 d. none of the above
a
the impact that one factor has on the outcome measure within including all levels of the other factor is called: a. a main effect b. an interaction effect c. a simple effect d. none of the above
a
what type of ANOVA is used when there are two levels, and with different participants taking part in each condition? a. factorial b. one-way independent c. mixed d. one-way between subjects
a
In a factorial design, b1 equals a. the grand mean b. the difference between the mean of the baseline level of the factor 1 and the group at the experimental level of factor 1 c. the mean of the control group for factor 2 d. the difference between the mean of the group at the baseline level of the factor 2 and the group at the experimental level of Factor 2
b
The degrees of freedom for the total sum of squares is a. N-p b. N-1 c. The square root of N-1 d. k-1
b
if you find evidence of moderation, this means that a. the effect is smaller than you predicted b. the impact of one variable upon the outcome changes across levels of the other variable c. a third, unmeasured variable, is impacting the results of your experiment d. the effect is neither small nor large: it is moderate
b
in a factorial design, b0 equals a. the mean of the control group for Factor 2 b. the mean of the group for which all predictor variables are coded as 0 c. the mean of the control group for Factor 1 d. the grand mean
b
in a factorial design, b1 equals: a. the effect of factor 2 when factor 1 is at its baseline level b. the effect of factor 1 when factor 2 is at its baseline level c. the mean the group when factor 1 is at its experimental level d. the mean the group when factor 1 is at its experimental level
b
in a two-way factorial design, b2 a. is the difference between the two levels of Factor 1 when Factor 2 is at its base level b. is the difference between the two levels of Factor 2 when Factor 1 is at its base level c. is equal to the group mean of the category for which all predictor variables have been dummy coded as 1 d. none of the above
b
when scientists conduct experiments, they sometimes manipulate more than one independent variable this is called a "factorial design" because: a. another term for an interaction is a factor b. another term for an independent variable is a factor c. another term for a dependent variable is a factor d. none of the above
b
Can you express the effect size of an F-ratio using r? a. Always b. only for a repeated-measures ANOVA c. only if the F-ratio has only 1 df d. never
c
In a two-way factorial analysis, MSaxb = a. SSaxb/df axb b. SS axb c. all of the above
c
In a two-way factorial design, the SSm will be a. not partitioned further b. partitioned into two parts:variance explained by factor 1 and variance explained by factor 2 c. partitioned into three parts including the interaction d. partitioned into two parts: SSa and SSb
c
Subsequent to obtaining a significant result from an exploratory one-way independent ANOVA, a researcher decided to conduct three t-tests to investigate where the differences between groups lie. Which of the following statements is correct? a. the researcher should accept as statistically significant tests with a probability value of less than 0.016 to avoid making a type 1 error b. this is the correct method to use. the researcher did not make any predictions about which groups will differ before running the experiment, therefore contrasts and post hoc tests cannot be used c. the researcher should have conducted orthogonal contrasts instead of t-tests to avoid making a type 1 error d. none of these options are correct
c
how many F ratios do you figure in a two-by two analysis of variance? a. 1 b. 2 c. 3 d. 4
c
In a two-way factorial design, SSaxb is... a. All of SSm that is left after you've figured out how much the two factors explain b. SSm-SSa-SSb c. easy to calculate (once you've figured SSa and SSb) d. all of the above
d
In a two-way factorial design, how many means are used to figure the SSm? a. 1 b. 2 c. 3 d. 4
d
In a two-way factorial design, the degrees of freedom for the interaction is a. df axb = dfm - dfa - dfb b. df axb = dfa x dfb c. 1 d. all of the above
d
In a two-way factorial design, the easiest way to calculate the sum of squares for the interaction is a. calculate the group mean for the second level of each factor, subtract each score from this mean, square and sum b. calculate the sum of squares for both factors c. SSa x SSb d. SS axb = SSm - SSa - SSb
d
In a two-way factorial design, the model sum of squares can be described as a. SSt b. SSm + SSr c. SSr d. SSa + SSb + SS axb
d
When reporting the results of a factorial ANOVA, you should report: a. the effect of each factor (even if not significant) b. the interaction effect (even if not significant) c. dfm and dfr d. all of the above
d
in a factorial design, b2 equals: a. the mean the group when factor 1 is at its experimental level b. the grand mean c. the effect of factor 1 when factor 2 is at its baseline level d. the effect of factor 2 when factor 1 is at its baseline level
d
in a factorial seeding, b3 equals: a. the difference between the effect of factor 2 when factor 1 is at its baseline level and the effect of factor 2 is at its experimental level the b. the difference between the effect of factor 1 when factor 2 is at its baseline level and the effect of factor 1 when factor 2 is at its experimental level c. the interaction d. all of the above
d
in a two-way factorial design, you can calculate the main effect of the first factor by: a. acting as if it was the only factor and calculate the mean for each level of that factor b. calculating the sum of squares for that factor by subtracting the each group mean from the grand mean, squaring and summing c. and use k-1, where k is the number of group means, as the degrees of freedom d. all of the above
d
in order to test the interaction between two predictors, assign the dummy code 1 to: a. cases that are not in the control condition for factor 1 cases that are not in the control condition b. for factor 2 c. cases that are in experimental condition for factor 1 or are in the experimental condition for factor 2 d. cases that are in the experimental condition for factor 1 and for factor 2
d
the F-ratio is a. a measure of the ratio of systematic variation to unsystematic variation b. the signal to noise ratio for a particular variable (or interaction) c. calculated like this: first convert the sum of squared error into a mean squared error by dividing each sum of squares by its degrees of freedom to get the mean squares for each factor, then divide that by the mean squares of the residual d. all of the above
d
the model sum of squares is calculated by these steps, in this order a. calculate the grand mean. calculate the group means. calculate the difference between each group mean and the grand mean. sum across all groups. square the sum b. calculate the group means. calculate the difference between each score and the grand mean. sum across all cases. square the sum c. calculate the grand mean. calculate the difference between each score and the grand mean. sum across all cases d. calculate the grand mean. calculate the group means. calculate the difference between each group mean and the grand mean. square those differences. sum across all groups
d