STATS FINAL

For an experiment comparing more than two treatment conditions you should use analysis of variance rather than separate t tests because:
A. a test based on variances is more sensitive than a test based on means.
B. There is no difference between the two tests, you can use either one.
C. conducting several t tests would inflate the risk of a Type I error.
D. separate t tests would require substantially more computations.

2.If the null hypothesis is true and there is no treatment effect, what value is expected on average for the F-ratio?
A. k - 1
B. N - k
C. 1.00
D. 0

3.An analysis of variance produces SStotal = 40 and SSwithin = 10. For this analysis, what is SSbetween?
A. Cannot be determined without additional information.
B. 400
C. 30
D. 50

4.In general the distribution of F-ratios is:
A. positively skewed with all values greater than or equal to zero.
B. negatively skewed with all values greater than or equal to zero.
C. symmetrical with a mean of zero.
D. symmetrical with a mean equal to dfbetween.

5.In analysis of variance, the F-ratio is a ratio of:

A. sample means.
B. two variances.
C. sample variances divided by sample means.
D. sample means divided by variances.

6.For an independent-measures experiment comparing two treatment conditions with a sample of n = 10 in each treatment, the F-ratio would have df equal to ________.

A. 19
B. 1, 19
C. 1, 18
D. 18

7. A researcher reports an F-ratio with df = 2, 36 for an independent-measures experiment. How many treatment conditions were compared in this experiment?

A. 3
B. 2
C. 38
D. 36

8.A researcher reports an F-ratio with df = 1, 24 for an independent-measures experiment. How many individual subjects participated in the experiment?

A. 27
B. 24
C. 25
D. 26

9.Which combination of factors is most likely to produce a large value for the F-ratio?

A. large mean differences and small sample variances
B. small mean differences and small sample variances
C. large mean differences and large sample variances
D. small mean differences and large sample variances

10.Under what circumstances are post tests necessary?

A. When you reject the null hypothesis with exactly 2 treatment conditions.
B. When you reject the null hypothesis with more than 2 treatment conditions.
C. When you fail to reject the null hypothesis with more than 2 treatment conditions.
D. When you fail to reject the null hypothesis with exactly 2 treatment conditions.

In the F-ratio for a repeated-measures ANOVA, what happens to variability caused by individual differences?

A. Must be computed and subtracted out of the numerator and the denominator.
B. Is automatically eliminated from the numerator but must be computed and subtracted out of the denominator.
C. Is automatically eliminated from the denominator but must be computed and subtracted out of the numerator.
D. Is automatically eliminated from both the numerator and the denominator.

In a repeated-measures ANOVA, a P value corresponds to:

A. the product obtained by multiplying all the scores for each individual person.
B. each individual score in the research study.
C. the total of all the scores for an individual treatment.
D. the total of all the scores for an individual person.

A repeated-measures analysis of variance produces SSwithin treatments = 24 and SSbetween treatments = 40. For this analysis, what is the value of SSerror?

A. 64
B. Cannot be determined from the information provided.
C. 16
D. 24

A researcher obtains an F-ratio with df = 2, 12 from an ANOVA for a repeated-measures research study. How many subjects participated in the research study?

A. 14
B. 7
C. 15
D. 13

Which of the following are sources of variability that contribute to SSbetween treatments in a repeated ANOVA?

A. treatment effect, individual differences, and random unsystematic differences
B. treatment effect and individual differences
C. individual differences and random unsystematic differences
D. treatment effect and random unsystematic differences

In a repeated-measures ANOVA, a P value is obtained by:

A. finding the sum of the scores for a treatment.
B. summing the T values of all treatments.
C. N-k.
D. finding the sum of the scores for a participant in the study.

In a repeated-measures ANOVA the SSwithin treatments is divided into two components. What are they?

A. total variability and error
B. between subjects and error
C. between subjects and between treatments
D. between treatments and error

The results of a repeated-measures ANOVA are reported as follows, F(3, 27) = 1.12, p > .05. How many subjects participated in the study?

A. 40
B. 9
C. 10
D. 36

For a repeated-measures ANOVA, which of the following is computed differently, compared to an independent-measures ANOVA?

A. the denominator of the F ratio
B. between treatment SS
C. within treatment SS
D. total SS

The appropriate denominator for the F-ratio for a repeated-measures ANOVA is:

A. variance between subjects.
B. remaining variance when the variance within treatments is subtracted from the variance between subjects.
C. remaining variance when the variance between subjects is subtracted from the variance within treatments.
D. variance within treatments.

In a two-factor analysis of variance a main effect is defined as:

A. the mean differences among the levels of one factor.
B. the mean difference between the two factors.
C. the difference between the largest treatment mean and the smallest treatment mean.
D. the mean differences among all treatment conditions.

The results from a two-factor analysis of variance show a significant main effect for factor A and a significant main effect for factor B. Based on this information, you can conclude that:

A. the interaction cannot be significant.
B. there probably is a significant interaction
C. you cannot make any conclusion about the significance of the interaction.
D. there must by a significant interaction.

A two-factor experimental study means that the study has:

A. two dependent variables.
B. an interaction between two variables.
C. two independent variables
D. exactly two groups of participants.

For an experiment involving 2 levels of factor A and 3 levels of factor B, with a sample of n = 10 in each treatment condition, what are the df values for the F-ratio for the AxB interaction?

A. 2, 54
B. 3, 54
C. 5, 54
D. 1, 54

The results of a two-factor analysis of variance produce df = 1, 30 for the F-ratio for factor A and df = 2, 30 for the F-ratio for factor B. What are the df values for the AxB interaction?

A. 3, 30
B. 1, 30
C. 2, 30
D. 2, 60

A two-factor, independent-measures research study is evaluated using an analysis of variance. The F-ratio for factor A has df = 2, 36 and the F-ratio for factor B has df = 3, 36. Based on this information, what are the df values for the AxB interaction?

A. df = 5, 72
B. df = 6, 72
C. df = 6, 36
D. df = 5, 36

The analysis of variance for a two-factor experiment produces:

A. three separate F-ratios.
B. two separate F-ratios.
C. four separate F-ratios.
D. one overall F-ratio followed by a series of required post hoc tests.

In a two-factor analysis of variance, the F-ratios for factor A, factor B, and the AxB interaction:

A. may have different df values and may have different denominators.
B. may have different df values but they all have the same denominator.
C. all have the same df values and they all have the same denominator.
D. all have the same df values but they may have different denominators.

If the results of a two-factor experiment are presented in a line graph, then an interaction can be seen whenever:

A. the lines are parallel.
B. the lines in the graph are not straight (bent).
C. there is a space separating the lines.
D. the lines move toward each other or cross.

A two factor analysis of variance produces SSA = 20, SSB = 40 and SSAxB = 90. For this analysis, what is the value for SSbetween treatments ?

A. 60
B. 30
C. 150
D. Cannot be determined without additional information.

A negative value for a correlation indicates:

A. a much stronger relationship than if the correlation were positive.
B. increases in X tend to be accompanied by decreases in Y.
C. a much weaker relationship than if the correlation were positive.
D. increases in X tend to be accompanied by increases in Y.

A Pearson correlation of r = +0.85 indicates that a graph of the data would show:

A. points widely scattered around a line that slopes up to the right.
B. points clustered close to a line that slopes up to the right.
C. points clustered close to a line that slopes down to the right.
D. points widely scattered around a line that slopes down to the right.

Which of the following pairs of variables should produce a negative relationship?

A. Driving distance from college and weekly cost of gas for a group of commuting college students.
B. Number of hours studying and number of errors on a math exam.
C. IQ and weight for a group of third-grade students.
D. Model year (2003, 2004, etc.) and price for a used Honda.

What is the value of SP for the following set of data?



a. -15

b. -11

c. -14

d. 14

Suppose the correlation between height and weight for adults is +0.80. What proportion (or percent) of the variability in weight can be explained by the relationship with height?

A. 80%
B. 64%
C. 40%
D. 100 - 80 = 20%

For a hypothesis test for the Pearson correlation, the null hypothesis states that:

A. the population correlation is zero.
B. the sample correlation is zero.
C. there is a non-zero correlation for the sample.
D. there is a non-zero correlation for the general population.

The Pearson and the Spearman correlations are both computed for the same set of data. If the Pearson correlation is r = +1.00, then what can you conclude about the Spearman correlation?

A. It will be positive.
B. There is no predictable relationship between the Pearson and the Spearman correlations.
C. It will have a value of 1.00
D. It will be positive and have a value of 1.00

Under what circumstances should the Spearman correlation be used?

A. The researcher's primary interest is the linearity of the relationship.
B. The Pearson is too difficult to compute
C. All of the other options are appropriate circumstances for the Spearman correlation.
D. The original data are measured on an ordinal scale of measurement.

In what situations can the point-biserial correlation be used?

A. When an independent-measures t test would also be appropriate.
B. When both X and Y are ranks.
C. When both X and Y are dichotomous.
D. When a single-sample t test would also be appropriate.

Under what conditions is the phi-coefficient used?

A. All of the other options are conditions for using phi.
B. When both X and Y are dichotomous variables.
C. When both X and Y consist of ranks.
D. When one of the two variables is dichotomous.

In the general linear equation, Y = bX + a, what is the value of b called?
A. slope
B. X intercept
C. Y intercept
D. correlation between X and Y

The regression equation is determined by minimizing:
A. the total error between the predicted Y values and the actual Y values.
B. the total squared error between the X and the Y values.
C. the total squared error between the predicted Y values and the actual Y values.
D. the total error between the X and Y values.

For the regression equation Y = 2X - 1, if the mean for X is MX = 8, what is the mean for Y?
A. Impossible to determine
B. 4.5
C. 15
.d.7

If the correlation between X and Y is r = 0.00, then SP = 0 and the regression equation is:
A. Y = X + 0
B. Y = 0 + MY
C. Y = 0 + MX
D. Y = X + MX

If there is a negative correlation between X and Y, then the regression equation Y = bX + a will have ________.
A. b > 0
B. a > 0
C. a < 0
D. b < 0

A set of n = 25 pairs of scores (X and Y values) has a Pearson correlation of r = 0.60. How much of the variance for the Y scores is predicted by the relationship with X?
A. 0.64 or 64%
B. 0.36 or 36%
C. 0.40 or 40%
D. 0.60 or 60%

A linear regression equation is computed for a sample of n = 18 pairs of X and Y scores. For the analysis of regression testing the significance of the equation what are the df values for the F-ratio?
A. df = 2, 16
B. df = 1, 16
C. df = 1, 17
D. df = 2, 15

A multiple regression equation with two predictor variables has R2 = 0.30 and SS = 100 for a sample of n = 15 participants. What is the standard error of estimate for this equation?
A. v30/12
B. v70/13
C. v70/12
D. v30/13

The Pearson correlation between X1 and Y is r = 0.40 and SSY = 100. When a second variable, X2, is added to the regression equation, we obtain R2 = 0.25. How much additional variance is predicted by adding the second variable compared to using X1 alone?
A. 9 points
B. 40 points
C. 15 points
D. 25 points

For either linear regression or multiple regression, the value of SSresidual can be computed directly by:
A. (Y - Y)2
B. (Y - MY)2
C. (Y - bX)2
D. (Y - MY)2

The term observed frequency refers to:
A. the frequencies found in the population being examined.
B. the frequencies that are hypothesized for the population being examined.
C. the frequencies computed from the null hypothesis.
D. the frequencies found in the sample data.

The expected frequencies:
A. can contain fractions and negative numbers.
B. can contain fractions or decimal values.
C. can contain both positive and negative values.
D. are always whole numbers.

The chi-square distribution is:
a.positively skewed with all values greater than or equal to zero
.b.symmetrical with a mean equal to n - 1.
c.negatively skewed with all values greater than or equal to zero.
d.symmetrical with a mean of zero.

The term expected frequencies refers to:
a.the frequencies that are hypothesized for the population being studied
.b.the frequencies computed from the null hypothesis.
c.the frequencies found in the sample data.
d.the frequencies that are found in the population being studied.

What does it mean to obtain a negative value for the chi-square statistic?
A. The expected frequencies tend to be larger than the observed frequencies.
B. There are large discrepancies between the observed and expected frequencies for most categories.
C. The observed frequencies tend to be larger than the expected frequencies.
D. The chi-square statistic can never be negative.

The chi-square test for goodness of fit evaluates:
a.the shape or proportions for a population distribution
.b.None of the other options are evaluated by the chi-square test
.c.the relationship between two variables.
d.the mean differences between two or more treatments.

The null hypothesis for the chi-square test for independence states that:
A. there is a relationship between the two variables.
B. both variables have the same frequency distribution.
C. there is no relationship between the two variables.
D. the two variables have different frequency distributions.

A chi-square test for independence has df = 2. What is the total number of categories (cells in the matrix) that were used to classify individuals in the sample?
A. 3
B. 2
C. 4
D. 6

A sample of 100 people is classified by gender (male/female) and by whether or not they are registered voters. The sample consists of 60 females, of whom 50 are registered voters, and 40 males, of whom 25 are registered voters. If these data were used for a chi-square test for independence, the expected frequency for registered males would be ________.
A. 15
B. 25
C. 45
D. 30

Under what conditions can the phi-coefficient be used to measure effect size for a chi-square test for independence?
A. When both variables consist of more than two categories.
B. When either of the two variables consists of exactly two categories.
C. When either of the two variables consists of more than two categories.
D. When both variables consist of exactly two categories.