topic Re: Paired t-test vs proc anova in Statistical Procedures

Paired t-test vs proc anova

Errant — Sat, 09 Jun 2018 18:43:19 GMT

I have a data set that looks like this:

It's originally divided by strata, treatment vs. placebo, and how individuals perform across visits. Individuals do not change statuses or classifications at anytime. I am trying to compare the means for the treatment vs placebo group for the first strata, after the second visit. I've already create a table, that is filtered solely for the first strata and for observations after the second visit. I'm trying to figure out, given the structure of the data, if it would be better to do a proc anova or a paired t test. The paired t test seems appropriate for the task, but I don't know if it's appropriate for my data.

Thank you!

Re: Paired t-test vs proc anova

pau13rown — Sat, 09 Jun 2018 20:38:49 GMT

you could but repeated measures would be more thorough because you have two post-baseline values

edit: maybe this is helpful https://statistics.laerd.com/statistical-guides/repeated-measures-anova-statistical-guide.php

Re: Paired t-test vs proc anova

PaigeMiller — Sat, 09 Jun 2018 20:58:36 GMT

PROC GLM with the REPEATED statement, not PROC ANOVA