Imagine that a researcher conducts an experiment using a within-groups design. S
ID: 3339171 • Letter: I
Question
Imagine that a researcher conducts an experiment using a within-groups design. Specifically, the same participants provide related scores on a dependent variable at two different levels of an independent variable. (Please assume that a relevant population standard deviation is not known). Which of the following analyses would be appropriate for comparing means for both levels of the independent variable?
1) A z test
2) A one-sample t test (using raw means for the two levels of the independent variable)
3) A paired-samples t test
4) An independent-samples t test
Explanation / Answer
Answer:
3) A paired-samples t test
Explanation: We are given that the same participants provide the related scores on a dependent variable at two different levels of independent variables. This means observations are paired or data is paired data. For comparing the means of paired data, we always use a paired samples t test.