If the homogeneity of variance assumption is violated in an independent groups t test, this means _________.
a. the populations from which the samples were drawn have different standard deviations
b. you should use the sign test
c. the sample sizes should be equal and N greater than 30 to use the t test
d. the populations from which the samples were drawn have different standard deviations and the sample sizes should be equal and N greater than 30 to use the t test
e. all of these
Assuming large between subject variability, which of the following tests is usually the most sensitive (N held constant)?
a. t test for correlated groups c. t test for independent groups
b. sign test d. they are all equal in sensitivity
A correlated groups design is more sensitive than an independent groups design if _________.
a. there are large inter-subject differences
b. there are small inter-subject differences
c. the experimental treatment effect is strong
d. there is a high correlation between paired scores
If the homogeneity of variance assumption is violated in an experiment using the t test for independent groups, this means _________.
a. the populations from which the samples were drawn have different variances
b. the power of the t test will be reduced
c. t the test can still be used, if the violation is a moderate one
d. the t test should not be used
e. the populations from which the samples were drawn have different variances and t the test can still be used, if the violation is a moderate one
In an experiment using the independent groups design, there are 10 subjects in one group and 12 subjects in the other group. The sampling distribution of t that is appropriate for that experiment is identical to the t distribution that is appropriate for a single sample design with _________ subjects.
a. 22 c. 20
b. 21 d. 11
The power of the t test increases with _________.
a. increases in N
b. increases in the effect of the independent variable
c. decreases in the sample variance(s)
d. all of these
For which of these tests do you need to know the sampling distribution of the relevant statistic in order to use the statistic for hypothesis testing?
a. z test c. sign test
b. t test d. all of these
Changing sample size has no effect on power when using the t test.
Indicate whether the statement is true or false
If we conclude that there is a significant correlation in the population we may be making a Type I error.
Indicate whether the statement is true or false
The 99 confidence limit is always wider than the 95 confidence interval.
Indicate whether the statement is true or false
Quick Reply
