1) Use analysis of variance rather than a t test whenever the null hypothesis makes a claim about:

a. more than one population mean

b. more than two population means

c. the population variance

d. the population shape

e. a t-test can be used in all of these cases

2) A treatment effect probably exists if:

a. total variability exceeds the sum of the variability between groups and the variability within groups

b. variability between groups and variability within groups are approximately equivalent

c. variability within groups clearly exceeds variability between groups

d. variability between groups clearly exceeds variability within groups

3) Any sum of squares term always equals the:

a. sum of the deviations of squared scores about their mean

b. sum of the squared deviations of all scores about their mean

c. square of the sum of all scores

d. deviations of all scores about their squared mean

4) Given an ANOVA with 4 and 50 degrees of freedom for between and within, respectively, how many subjects were there altogether?

a. 50

b. 51

c. 54

d. 55

e. 56

5) Rejection of the overall null hypothesis in an ANOVA always indicates that:

a. at least one population mean differs from all others

b. two or more population means differ from all the others

c. all populations means are different from each other

d. all of the above

6) When all possible differences between pairs of population means are evaluated not with an F test, but with a series of regular t tests, the probability of at least one:

a. type II error is larger than the specified level of significance.

b. type I error is larger than the specified level of significance.

c. type I error is smaller than the specified level of significance.

d. type II error is smaller than the specified level of significance.

7) Which of the following is NOT true in ANOVA?

1. the combined degrees of freedom for between and within variability add up to equal the total degrees of freedom

2. the combined sum of squares (SS) for between and within variability add up to equal the total sum of squares

3. the combined degrees of freedom for between and within variability add up to equal the total number of subjects

4. all of these are true

8) If the null hypothesis is true in a chi-square test, discrepancies between observed and expected frequencies will tend to be:

a. small enough to qualify as a rare outcome

b. large enough to qualify as a rare outcome

c. small enough to qualify as a common outcome

d. large enough to qualify as a common outcome

9) In the one-variable chi-square test, degrees of freedom equal:

a. the total number of observations

b. one less than the total number of observations

c. the total number of categories

d. one less than the total number of categories

e. none of these

10) In an observed sample of 200 people, 100 males and 100 females, 30 males are conservative (70 are liberal), and 20 females are conservative (80 are liberal). What is the expected frequency of liberal males?

a. 50

b. 70

c. 75

d. 100

e. none of these

11) To use chi-square properly, all of the following must be true EXCEPT:

a. the total number of subjects equals the total number of observed frequencies

b. none of these needs to be true

c. every observed frequency is five or more

d. all of these must be true

e. every expected frequency is five or more