BookmarkSubscribeRSS Feed
Coming98
Calcite | Level 5

I'd really appreciate it if someone could offer some suggestions or point me to the correct SAS PROC.

 

I am trying to estimate a system of two probit models:

Y1 = Y2 + X1 + X3

Y2 = Y1 + X1 + X2 + X4

 

The bivariate probit model shows clearly that Y1 and Y2 are correlated. Could someone tell me which SAS PROC handles this type of estimation? Thanks a lot!

 

AL

2 REPLIES 2
StatDave
SAS Super FREQ

PROC QLIM in SAS/ETS® can fit a bivariate probit model.

Coming98
Calcite | Level 5

Thank you for your response!

 

I did use QLIM to run a bivariate probit model and I found Y1 and Y2 to be significantly correlated.

 

A theory suggests that Y1 might affect Y2 but not vice versa. In order to test that, I'd like to run two probit models simultaneously with Y2 included as Y1's explanatory variable and Y1 included as Y2's explanatory variable. Can QLIM do that as well?

 

Again, sorry for the basic question but I did not find that in the supporting doc. Thanks for your help.

 

AL 

sas-innovate-white.png

Missed SAS Innovate in Orlando?

Catch the best of SAS Innovate 2025 — anytime, anywhere. Stream powerful keynotes, real-world demos, and game-changing insights from the world’s leading data and AI minds.

 

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
  • 1532 views
  • 0 likes
  • 2 in conversation