Problem Set 6--WORKSHEET

Description

Chapter 12

The problem sets are designed to provide you with opportunities to practice and master the respective statistical procedures in the assigned chapters. You can use the Salkind book (or even another stats book you feel more comfortable with) to help you work through the problems. If needed, use a calculator (or if you are really up to it, use some statistical software but this is NOT needed to solve any of the problems).

Instructions

Read each question carefully. Select the correct answer. You have 3 days to complete this problem set.

Total Questions

10

Total Points

100

Question

What would be the most appropriate statistical test for a research project examining whether recidivism scores from 20 juveniles changed after participating in a cognitive-behavior program, in comparison to their scores prior to participating in the program?

Answer

t-test for the correlation coefficient

t-test for dependent means

t-test for independent samples

t-test for related populations

Question

For a t-test for dependent means, how do you calculate the degrees of freedom?

Answer

n -1, where n is the number of pairs of observations

n₁ - 1 + n₂- 1

n₁ - 2

n₁ + n₂

Question

When do you use table B2?

Answer

At the beginning of the t-test

to set the level of risk

to determine the critical t-test value

to determine the obtained t-test value

Question

Calculate the degrees of freedom. DF=

The hypothetical data are from students who participated in Respect Your Classmate education program. The pretest and posttest measures are the number of times a student was respectful to classmates during the last week before (pretest) they participated in the program. The posttest is the number of times they were respectful to a classmate the week after completing the program. You are interested in if the program was successful, that is, are the posttest scores significantly different from the pretest scores (Hint: assume a one-tailed test).

Answer

-9

10

20

9

Question

Calculate the t value. t =

The hypothetical data are from students who participated in Respect Your Classmate education program. The pretest and posttest measures are the number of times a student was respectful to classmates during the last week before (pretest) they participated in the program. The posttest is the number of times they were respectful to a classmate the week after completing the program. You are interested in if the program was successful, that is, are the posttest scores significantly different from the pretest scores (Hint: assume a one-tailed test).

Answer

7.80

77.80

-9.89

-5.90

Question

Interpret your results at p < .05.

The hypothetical data are from students who participated in Respect Your Classmate education program. The pretest and posttest measures are the number of times a student was respectful to classmates during the last week before (pretest) they participated in the program. The posttest is the number of times they were respectful to a classmate the week after completing the program. You are interested in if the program was successful, that is, are the posttest scores significantly different from the pretest scores (Hint: assume a one-tailed test).

Answer

The null hypothesis must not be rejected. It can be concluded that there is no significant difference between the two sets of scores and the program was a failure.

The null hypothesis must be rejected. It can be concluded that there is a significant difference between the two sets of scores and the program was successful.

No interpretation of the results are possible because the obtained value is equal to .05.

Question

How many subjects were there in the study?

Answer

can not be determined

59

50

56

Question

The obtained t statistic was _______ and it was ________.

Answer

1.13, not significant

1.13, significant

55, not significant

.05, significant

Question

In a two-tailed test, you would reject the null hypothesis

Answer

whenever there is a difference between the obtained t value and the critical value

only if the difference between the obtained t value and the critical value is a negative number

whenever the obtained t value is larger than the critical value

whenever the critical value is 0

Question

What is the difference between a t-test for independent samples and a t-test for dependent samples?

Answer

A t-test for independent samples compares two unrelated groups, while a t-test for dependent samples is used to compare scores from the same subjects under two different conditions.

A t-test for independent samples compares two related groups, while a t-test for dependent samples is used to compare scores from the same subjects under the same conditions.

There is no difference between the two.

p < .05 in an independent sample and p > .05 in a dependent sample.