BookmarkSubscribeRSS Feed
swapnilsoni
Fluorite | Level 6

how coefficients are estimated in VAR model in sas? why proc varmax output and proc reg outputs are same?

 

Please check the following programs:

 

/*Program-1: VARMAX PROCEDURE*/

/*Estimate VAR(1) model with all 3 variables (Trivariate)*/

proc varmax data=sashelp.class ;

model Age Weight Height/p=1 ;

run;

 

/*PROGRAM2: REG PROCEDURE*/

/*Let's replicate this using PROC REG with newly created dataset with manual lags*/

/*New dataset*/

data lag_data;

set sashelp.class;

Age_l=lag(Age);

Weight_l=lag(Weight);

Height_l=lag(Height);

run;

/*Use PROC REG: gives same result as above*/

proc reg data=lag_data;

model Age=Age_l Weight_l Height_l;

run;

 

Concern: Both are giving same output. This should not happen since VAR uses multivariate OLS not conventional OLS used in Regression. If not so the what is use of VAR?

1 REPLY 1
gergely_batho
SAS Employee
Parameter estimates should be the same, standard errors and p-values should be different.
Please someone correct me if I’m wrong.

hackathon24-white-horiz.png

The 2025 SAS Hackathon has begun!

It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.

Latest Updates

What is Bayesian Analysis?

Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.

Find more tutorials on the SAS Users YouTube channel.

SAS Training: Just a Click Away

 Ready to level-up your skills? Choose your own adventure.

Browse our catalog!

Discussion stats
  • 1 reply
  • 1139 views
  • 0 likes
  • 2 in conversation