Programming the statistical procedures from SAS

Fixed effects in Proc Probit

Reply
N/A
Posts: 1

Fixed effects in Proc Probit

How can I run a fixed effect model in Probit?

My model is: y=f(V1, V2, V3).

y is a 0/1 binomial variable.
V1, V2, V3 are continuous variables.

The observations are taken over a period of 30 years. A portion of the total number of observations come from each of the thirty years.

Since the V1,V2 and V3 vary over the thrity years, I want to add a year fixed effect.

I am using SAS 9.2. I have looked in the SAS Documentation but am unable to locate the command/options, etc.

Can anybody help?

Thanks.
Valued Guide
Valued Guide
Posts: 684

Re: Fixed effects in Proc Probit

Based on your question, I think you simply want:

proc probit;
class y;
model y = v1 v2 v3 year;
run;

This assume that y is strictly 0 or 1. There is an alternate syntax when you have a count of y out of n for each observation.
SAS Employee
Posts: 245

Re: Fixed effects in Proc Probit

A fixed effects model can be fit in PROC LOGISTIC using the STRATA statement. For example:

proc logistic;
strata year;
model y=v1 v2 v3;
run;

This fits the conditional logistic model that avoids estimating parameters for the years. However, a probit model cannot be fit when the STRATA statement is used and there is no STRATA statement in PROC PROBIT.
Contributor
Posts: 58

Re: Fixed effects in Proc Probit

Hello dear ? 

Can i get Pseudo R squre or R squre using this regression in SAS?
any help will he highly appreciable. 
THnaks

Contributor
Posts: 58

Re: Fixed effects in Proc Probit

Hello dear
Can I get Pseudo R squre using Proc logistic?
Thanks for help
Ask a Question
Discussion stats
  • 4 replies
  • 1667 views
  • 0 likes
  • 4 in conversation