BookmarkSubscribeRSS Feed

Procedures like PROC GLIMMIX have a DDFM=method option on the MODEL statement to:

 

"specify the method for computing the denominator degrees of freedom for the tests of fixed effects that result from the MODEL, CONTRAST, ESTIMATE, LSMEANS and LSMESTIMATE statements."   

 

Specifics on these methods can be found in the Details => Degrees of Freedom Methods - - http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_glimmix_deta... of the GLIMMIX procedure documentation.

 

 

PHREG does not have this feature and, indeed, does not handle a multi-level clustered situation beyond two levels, e.g. - county nested in state. 

 

A received request is paraphrased as follows "I am doing some tests for fixed effects of level 2 (cluster level) using data of two levels with varying sample size in different clusters.   If you look for a reference and see how other software has done, refer to STATA 14 and the  MESTREG command - https://www.timberlake.co.uk/software/stata-new-multilevel-and-small-sample "

 

 

2 Comments
GZ
Fluorite | Level 6
Fluorite | Level 6
I really hope the DDFM method can be added to PHREG in next release. Very frequently we make inference about the fixed effects at multi-levels using survival data which are of small sample size or unbalanced among clusters. Without appropriate adjustment for the denominator degrees of freedom, the results (i.e. the default p values) can just be invalid. STATA 14 has done this with its MESTREG command. SAS may implement an addition of the feature directly? I look forward to seeing and using the new function in survival analysis.
GZ
Fluorite | Level 6
Fluorite | Level 6

STATA 14 MESTREG command may actually have no such functionality yet.   STATA web site (and Timberlake site) had a page titled “Multilevel survival models and Small-sample inference”, which could easily get readers confused. Nevertheless, SAS Institute is able and may well be the first to add this very useful feature to its product.