Deck 12: Statistical Analysis

Question 1

In a t-test, the degrees of freedom are a function of the

A)variance.
B)difference between the means.
C)sample size.
D)alpha-level.

Answer 1

C

Question 2

Why do researchers not conduct several t-tests to analyze experiments that have more than two conditions?

A)The means will be invalid.
B)The sample size is too small.
C)Type I error is inflated.
D)The power of the analysis is low.

Answer 2

C

Question 3

If the calculated value of t exceeds the critical value of t, the researcher

A)fails to reject the null hypothesis.
B)commits a Type I error.
C)has made a calculation error.
D)rejects the null hypothesis.

Answer 3

D

Question 4

The paired t-test

A)requires that two t-tests be conducted.
B)is less powerful than the randomized t-test.
C)is used to analyze within-subjects designs.
D)tests differences between pairs of participants.

Question 5

The calculated value of F is based on the ratio of between-groups variance to ________ variance.

A)error
B)systematic
C)total
D)reliable

Question 6

If the calculated value of F is 5.76 and the critical value of F is 2.37, the researcher will

A)make a Type I error.
B)reject the null hypothesis.
C)conclude that the group means do not differ.
D)perform a t-test.

Question 7

What statistic would you use to test whether the means of a two-group experiment were significantly different?

A)ANOVA
B)T-test
C)F-test
D)Regression analysis

Question 8

The effect of the independent variable is reflected in the

A)sum of squares between-groups.
B)mean square within-groups.
C)degrees of freedom.
D)grand mean.

Question 9

If the independent variable in an experiment had absolutely no effect on participants' responses, all of the variance in the data is _______ variance.

A)reliable
B)between-groups
C)error
D)confounded

Question 10

A directional hypothesis

A)is tested with a paired t-test.
B)stipulates whether alpha or beta is more important.
C)requires more participants than a nondirectional hypothesis.
D)predicts which of two means will be larger.

Question 11

If the calculated value of F is .89 and the critical value of F is 4.36, what is likelihood that the researcher will make a Type I error?

A))00
B))05
C))89
D)1)00

Question 12

If we calculate the sum of squares separately for each experimental condition, then sum them, we get the

A)total sum of squares.
B)mean square within-groups.
C)means square between-groups.
D)sum of squares within-groups.

Question 13

To calculate a value for t, you divide the

A)error variance by the sample size.
B)sample variance by the population variance.
C)degrees of freedom by the variance.
D)difference between the means by the error variance.

Question 14

F = MS_bg / ________

A)SS_bg
B)MS_total
C)df_bg
D)MS_wg

Question 15

The Bonferroni adjustment is used to

A)increase power.
B)reduce the likelihood of a Type I error.
C)test interactions between variables.
D)lower error variance.

Question 16

The analysis of a factorial design with two independent variables will test

A)one main effect and an interaction.
B)two main effects and an interaction.
C)two main effects and two interactions.
D)None of these answers are correct.

Question 17

One-tailed is to two-tailed as

A)alpha is to beta.
B)directional is to nondirectional.
C)posttest only is to pretest-posttest.
D)Type II is to Type I.

Question 18

In principle, if no interaction is present in a two-way factorial design, SS_total =

A)SS_A + SS_B.
B)SS_A + SS_B + SS_wg.
C)SS_wg - (SS_A + SS_B).
D)SS_A×B.

Question 19

The numerator of the formula for the t-test contains

A)the condition means.
B)an estimate of the error variance.
C)the sample size.
D)the pooled standard deviation.

Question 20

What statistical analysis is used to analyze data from experimental designs that involve more than two conditions?

A)T-test
B)Regression
C)Chi-square test
D)Analysis of variance

Question 21

Distinguish between a one-tailed and a two-tailed statistical test.

Question 22

When do researchers use multivariate analysis of variance (MANOVA)?

Question 23

What are simple main effects, and when do researchers test them?

Question 24

When ANOVA is used to analyze data from experiments with two independent variables, the total sum of squares is composed of four parts. What are they?

Question 25

When are t-tests, ANOVA, and MANOVA used?

A)To analyze data from experiments only
B)To analyze data from correlational designs only
C)To analyze data from both experimental and nonexperimental designs
D)None of these answers are correct.

Question 26

When would you use a multivariate analysis of variance?

A)To analyze data from designs with several independent variables
B)To conduct a within-subjects analysis
C)To protect against Type II error
D)To analyze a set of dependent variables

Question 27

If a significant main effect involves an independent variable with two conditions, the main effect is interpreted by

A)testing the simple main effects.
B)inspecting the means.
C)testing the interaction.
D)doing follow-up or post hoc tests.

Question 28

The first step in interpreting a significant interaction is to

A)test the simple main effects.
B)inspect the means for the main effects.
C)conduct an ANOVA.
D)do follow-up or post hoc tests.

Question 29

When ANOVA is used to analyze data from experiments with one independent variable, the total sum of squares is composed of two parts. What are they?

Question 30

Explain the rationale behind the t-test.

Question 31

The effect of one independent variable at a particular level of another independent variable is a(n)

A)F-ratio.
B)post hoc effect.
C)simple main effect.
D)between-groups effect.

Question 32

When the calculated value of F is less than the critical value of F, what decision does the researcher make regarding the null hypothesis?

Question 33

What is an interaction?

Question 34

MANOVA analyzes a composite variable that is the sum of the weighted dependent variables. This composite variable is the

A)discriminant function.
B)canonical correlation.
C)factor loading.
D)canonical variable.

Question 35

When would you use a paired t-test?

Question 36

What do you do to interpret a significant main effect the involves an independent variable that has more than two conditions?

A)Test the simple main effects.
B)Simply visually inspect the means.
C)Test the interaction.
D)Conduct post hoc tests.

Question 37

Why do researchers not use t-tests to analyze the data from experimental designs that have more than two conditions?

Question 38

In two sentences or less, describe the rationale behind the F-test.

Question 39

What happens to the overall likelihood of making a Type I error as the number of dependent variables increases?

A)Type I error increases
B)Type I error decreases
C)Type I error exceeds Type II error
D)Type II error exceeds Type I error