BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
SBS
Obsidian | Level 7 SBS
Obsidian | Level 7

I am new to SAS and don' t quite understand if GENMOD, GLIMMIX. or NLMIXED is the right for below hypothesis testing - 

 

I want to isolate gender differences in preferences for a particular attribute of a product based on data available about their product purchases. I understand that I have to use a mixed Poisson or Negative binomial (in case of over dispersion) regression model as in my data - (1) I have same person buying multiple products (also, a given product might be bought by several people); and (2) the product attribute I am interested is a count variable.

 

In essence, I want to test the hypothesis: Women prefer products that are high onproductAttribute1 more than do men, even after controlling for price of the products".

 

I am currently running the following procedure in SAS:

 

proc genmod data=myData;
class GenderCosumer consumer_id;
model productAttribute1 =GenderCosumer + price  / type3 dist=negbin;
Repeated subject=consumer_id/sorted type=exch;

 

Is this right?

1 ACCEPTED SOLUTION

Accepted Solutions
StatDave
SAS Super FREQ

You could use either GENMOD, GEE, GLIMMIX, or NLMIXED to fit a model to a count response with repeated measurements on subjects. The choice largely depends on what type of model you want to fit for what intended purpose. GENMOD and the newer GEE fit a Generalized Estimating Equations model that is a population averaged model for population level inferences. GLIMMIX and NLMIXED can fit random effects models that are considered subject-specific models for inferences more at the subject level.

View solution in original post

2 REPLIES 2
StatDave
SAS Super FREQ

You could use either GENMOD, GEE, GLIMMIX, or NLMIXED to fit a model to a count response with repeated measurements on subjects. The choice largely depends on what type of model you want to fit for what intended purpose. GENMOD and the newer GEE fit a Generalized Estimating Equations model that is a population averaged model for population level inferences. GLIMMIX and NLMIXED can fit random effects models that are considered subject-specific models for inferences more at the subject level.

SBS
Obsidian | Level 7 SBS
Obsidian | Level 7
Thanks a lot for clarification StatDave! Could you share the link to the newer GEE procedure? Is this available on University Editions as well?

sas-innovate-2024.png

Available on demand!

Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.

 

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
  • 815 views
  • 1 like
  • 2 in conversation