Suppose we are planning to studying a treatment for depression. We will obtain b
ID: 2957434 • Letter: S
Question
Suppose we are planning to studying a treatment for depression. We will obtain base- line depression scores Xi, i = 1,...,30 on a set of research subjects. Three months later, after the treatment is complete, we will obtain a new set of depression scores Yi, i = 1, . . . , 30 on the same subjects. We anticipate that the treatment will reduce average depression scores by 1.6 raw units. For power analysis, we assume that the pre-treatment measures will have a standard deviation of 3 units, the post-treatment measures will have a standard deviation of 2 units, and the pre-treatment and post- treatment measures will be correlated 0.4 with each other.(i) What is the power for detecting the anticipated effect of 1.6 units when using a paired t-test;
(ii) What would the power be if we used an unpaired t-test?
Explanation / Answer
We anticipate that the treatment will reduce average depression scores by 1.6 raw units. For power analysis, we assume that the pre-treatment measures will have a standard deviation of 3 units, the post-treatment measures will have a standard deviation of 2 units, and the pre-treatment and post- treatment measures will be correlated 0.4 with each other. (i) What is the power for detecting the anticipated effect of 1.6 units when using a paired t-test; Question : is it when there is non-random sampling? so, if there is a direct relationship between data points u use paired. Am i right or wrong, and is there anything else of importance? Answer : Use a paired samples t-test when you're testing the same people twice, such as when you give the same person a pre-test (Time 1), then a post-test (Time 2), and you compare his/her scores at two different times (to see if there's a significant difference between the scores at Time 1 vs. the scores at Time 2). Use an independent samples t-test when you're testing different people's scores (such as men vs. women) to see if there's a significant difference between their scores. It doesn't have to do with whether the sampling is random. I hope that helps!