BookmarkSubscribeRSS Feed
bobyloe
Calcite | Level 5

Hi there,

 

I was wondering if there is way to run marginal quantile regression models in SAS?

My outcome is antibody levels following a vaccine dose, and I have multiple covariates, including time of visit, relative to vaccination.

I would like to model the change of median antibody levels over time (i.e., three study visits, timepoint 1, 2, 3 which are about a median of 20 days, 120 days, and 180 days after vaccination).

As this is a longitudinal analysis, GEE is a good option but to my understanding, marginal models model the mean, not median, changes with proc genemod.

And to my knowledge, proc quantreg models the quantile (median for my case) response at one specific timepoint.

To summarize, is there a code for longitudinal quantile regression in SAS?

 

Thanks, Bobby

2 REPLIES 2
sbxkoenk
SAS Super FREQ

Hello,

 

Quantile regression for longitudinal data with SAS --> There are several hits on internet.

 

You have only 3 time points. That's maybe a bit low to fit a spline.

If fitting a spline is an option to you, then see here:

Topic: Quantreg with Longitudinal Data?
Posted 04-02-2014 12:01 PM
https://communities.sas.com/t5/Statistical-Procedures/Quantreg-with-Longitudinal-Data/td-p/164865

 

Kind regards,

Koen

SAS Innovate 2025: Call for Content

Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!

Submit your idea!

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
  • 575 views
  • 4 likes
  • 3 in conversation