Posted by Luah on Thursday, July 11, 2013 at 1:02am.
Usually you use z-tests when sample sizes are large (n is greater than
or equal to 30) whether or not you know the population standard deviation.
If you do not know the population standard deviation and have a small
sample (n < 30), then you can use t-tests.
T-tests for independent samples uses two different sets of research subjects. T-tests for dependent samples uses the same research subjects in two different conditions (like a "before" condition and an "after" condition) or when there are two samples that have been matched or "paired" in some way.
You can find examples of these types of tests online or in any statistics textbook.
Are my answers here correct ?
Research questions for z test, t test for independent samples and t test for dependent samples :
z test: "An investigator is interested in finding out whether the particular sample of college students is similar to or different from college students in general.
t test for independent samples: "Do 11th graders have significantly more unexcused absences than 10th graders in junior highs?
t test for dependent samples: " Do people drop weight after attending a weight loss boot camp for 2 months?
Suggest one psychological research question that could be answered by each of the following types of statistical tests:
z test
t test for independent samples, and
t test for dependent samples