Lesson 11 : Bivariate Analysis I – Testing Relations

Each question has only one best answer. Circle clearly the letter of the best answer. If you make a mistake, cross out the circle, and write the letter in capitals next to the question. If a question has both a capital letter and is circled, the letter will be considered to be the answer.

1. What is the difference between a one-sample t–test and a two sample t-test?

a. A one-sample t-test evaluates a one-sample difference. A two-sample t-test evaluates a two-sample difference.

b. A one-sample t-test evaluates whether the sample mean reflects the population mean. A two-sample t-test evaluates whether two independent group means differ.

c. A two-sample t-test compares variances, while a one-sample t-test does not.

d. A one-sample t-test compares one mean with a population mean, while a two-sample test compares two means against the population mean.

e. The only difference between one-sample and two-sample t-test is the number of samples.

2. You are asked to calculate the t-statistic to determine whether the mean ages of two groups of respondents are significantly different. You are given the mean and standard deviation for each group. What other information do you need?

a. An estimate of the skewedness of each mean.

b. The standard deviation of the entire population.

c. The separate sample sizes of groups 1 and 2.

d. The total sample size of groups 1 and 2 summed together.

e. None, you have enough information to calculate t.

3. Sandra wants to examine the difference in computer usage between 25 males and 36 females. She knows she has to do a two-sample t-test. How many degrees of freedom does she have?

a. 25

b. 36

c. 59

d. 60

e. 61

4. Roberto wants to test for the possibility that the mean from Group A is significantly higher than the mean from Group B. He calculates t and finds that it is significant at the 0.6 level for a two-tailed test. What can he conclude about the mean from Group A being higher than the mean from Group B.

a. He can conclude that Group A is not significantly higher than Group B.

b. He can conclude that the man for Group B is significantly higher than that of Group A.

c. He can conclude that the one-tailed test is significant at the 1.2 level.

d. He can conclude that the one tailed test is significant at the 0.03 level.

e. He can’t conclude anything because he cannot do a one-tailed test.

5. Barbara collects data on network downtime. What kind of analysis does Barbara need to do to determine whether there are any significant differences between the amounts of downtime for three Intranets?

a. Chi-square.

b. t-test

c. ANOVA

d. MANOVA

e. gamma

6. What is the F ratio?

a. The mean between-group variance divided by the mean within-group variance.

b. The mean within-group variance divided by the mean between-group variance.

c. The mean between-group variance divided by the total variance.

d. The mean within-group variance divided by the total variance.

e. None of the above.

7. Joe wants to look at whether race and gender affect mean online purchases. What statistic should Joe use?

a. One-way ANOVA

b. MANOVA

c. ANCOVA

d. Factorial ANOVA

e. None of the above.

8. Isabelle observes that as user recommendations rise, so do number of online purchase for that product. Which statement(s) is(are) true?

a. The covariation is positive

b. The covariation is positive and linear

c. The covariation is positive and nonlinear

d. The covariation is undefined

e. a and b.

9. David is studying men’s and women’s knowledge of a website. To better understand the relationships between gender and knowing or not knowing the site, David builds a 2-by-2 table. He puts the independent variable (gender) in the columns and the dependent variable (knowledge) in the rows. He collects data from 20 men and 20 women. Ten men and 15 women report knowing about the web site. What are the row marginals?

a. 20 and 20

b. 5 and 15

c. 10 and 15

d. 15 and 25

e. 5 and 35

10. Stacey is interested in website “click-on”. She initially tests her hypothesis that information overload causes people to leave the site. During a preliminary analysis of her data, Stacey finds that education level is predictive of overload perceptions, which in turn predicts time at the site. What kind of variable is education?

a. A dependent variable

b. An antecedent variable

c. An intervening variable

d. An interval-level variable

e. None of the above.

11. A PRE measure of association:

a. Tells us how well we can guess the dependent variable given the independent variable.

b. Tells us how much error would be reduced if we had more accurately collected our data.

c. Tells us the probability of finding an association by chance.

d. Is illustrated by the chi-squared statistic

e. a and d

12. What statistic would you use to test the null hypothesis that differences in a 2-by-3 cross tabulation table exist solely by chance?

a. Odds ratio

b. Chi-square

c. Lambda

d. Fisher’s exact test

e. None of the above work.

13. John wants to see whether the relationships in a 2-by-2 crosstabs table exist solely by chance. Due to small sample size, John expects some of the cells to be less than 5. What statistic should John use?

a. Odds ratio

b. Chi-square

c. Lambda

d. Fisher’s exact test

e. None of the above

14. Which of the following is a measure of association between two ordinal variables?

a. Gamma

b. Chi-square

c. Odds ratio

d. t-test

e. a and b

15. The values of gamma range from what to what?

a. 0 to 1

b. 0 to ¥

c. ¥ to ¥

d. – 1 to +1

e. None of the above

16. What is the difference between gamma and Kendall’s tau-b?

a. Gamma ignores ties in rank-order data

b. Kendall’s tau-b ignores ties in rank-order data.

c. Gamma relies on nominal data: Kendall’s tau-b relies on ordinal data.

d. Kendall’s tau-b treats ordinal data as nominal-level data.

e. None of the above.

17. Joseph wants to look at the effects of age on computer use. He divides age into young (1) and old (2). He divides computer use into low(1) and high(2). How should joseph measure the association between these ordinal variables?

a. Chi-square

b. Gamma

c. Yule’s Q

d. Eta-squared

e. Pearson’s product-moment correlation

18. Josephine asked 30 men and 30 women to rank order the names of 25 browsers according to their support for user privacy. Now Josephine wants to compare the mean rank order of each browser for men with the mean rank order for women. What kind of correlation should she calculate?

a. Pearson’s product-moment correlation

b. Eta-squared

c. Gamma

d. r ²

e. Spearman’s r.