BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
bdm0909
Calcite | Level 5

I am estimating a nonlinear regression using proc model and would like to output the log likelihood. Can this be ouputted?

1 ACCEPTED SOLUTION

Accepted Solutions
kessler
SAS Employee

PROC MODEL supports a variety of estimation methods which can be specified using options on the FIT statement.  Most of the estimation methods do not use a log likelihood function in their formulation.  However, for the FIML method, a log likelhood function is evaluated and is reported in the Estimation Summary Statistics table. You can read more about the FIML method used in PROC MODEL here:

http://documentation.sas.com/?docsetId=etsug&docsetVersion=14.2&docsetTarget=etsug_model_sect070.htm...

 

A log likelihood value is also used and reported when you specify your own likelihood using an 'errormodel ~ general' statement, or when you estimate a model using the t distribution.

View solution in original post

1 REPLY 1
kessler
SAS Employee

PROC MODEL supports a variety of estimation methods which can be specified using options on the FIT statement.  Most of the estimation methods do not use a log likelihood function in their formulation.  However, for the FIML method, a log likelhood function is evaluated and is reported in the Estimation Summary Statistics table. You can read more about the FIML method used in PROC MODEL here:

http://documentation.sas.com/?docsetId=etsug&docsetVersion=14.2&docsetTarget=etsug_model_sect070.htm...

 

A log likelihood value is also used and reported when you specify your own likelihood using an 'errormodel ~ general' statement, or when you estimate a model using the t distribution.

sas-innovate-2026-white.png



April 27 – 30 | Gaylord Texan | Grapevine, Texas

Registration is open

Walk in ready to learn. Walk out ready to deliver. This is the data and AI conference you can't afford to miss.
Register now and lock in 2025 pricing—just $495!

Register now

Discussion stats
  • 1 reply
  • 1475 views
  • 2 likes
  • 2 in conversation