BookmarkSubscribeRSS Feed
jjdubs
Calcite | Level 5

I have an ordinal categorical variable (group 1, 2, 3, 4) at two time points. I want to evaluate the change in groups from time 1 to time 2. However, I don't want to just compare the marginal frequencies at each time point. I want to know whether change from group 1 to group 2 is the same as change from group 2 to group 3 is the same as change from group 3 to group 4? A stuart maxwell test only tells me difference in marginal frequencies and wilcoxon signed rank only tells me if there is a difference in the ranks between time 1 and time 2. Anyone with advise on how to seek my answer? Thanks!

2 REPLIES 2
jjdubs
Calcite | Level 5

I have an ordinal categorical variable (group 1, 2, 3, 4) at two time points. I want to evaluate the change in groups from time 1 to time 2. However, I don't want to just compare the marginal frequencies at each time point. I want to know whether change from group 1 to group 2 is the same as change from group 2 to group 3 is the same as change from group 3 to group 4? A stuart maxwell test only tells me difference in marginal frequencies and wilcoxon signed rank only tells me if there is a difference in the ranks between time 1 and time 2. Anyone with advise on how to seek my answer? Thanks!

ballardw
Super User

Providing some example data never hurts, it may only need to be 10 rows or so, enough to discuss results from. It may help to provide some information about how many records you have.

You should provide some examples using that example data on what you mean by change from group 1 to group 2.

 

Then describe or provide an example of how you will actually use the value(s) you are asking for in a sentence or two in a report.

sas-innovate-2026-white.png



April 27 – 30 | Gaylord Texan | Grapevine, Texas

Registration is open

Walk in ready to learn. Walk out ready to deliver. This is the data and AI conference you can't afford to miss.
Register now and save with the early bird rate—just $795!

Register now

What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 2 replies
  • 2202 views
  • 2 likes
  • 2 in conversation