Date:         Thu, 28 Apr 2011 09:08:44 -0500
Reply-To:     Robin R High <rhigh@UNMC.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Robin R High <rhigh@UNMC.EDU>
Subject:      Re: Difference in parameter estimation LSMEANS and ESTIMATE
              statement with covariate adjustments
Comments: To: Ray Harvey <rharvey3015@GMAIL.COM>
Comments: cc: Ray Harvey <rharvey3015@GMAIL.COM>
In-Reply-To:  <201104281402.p3SAlcTe007679@wasabi.cc.uga.edu>
Content-Type: text/plain; charset="US-ASCII"

Ray,

You can add a value for the covariate (of greatest interest to you) on the
ESTIMATE statement to estimate adjusted means, e.g., it could be the mean,
but some round value that makes sense for your objectives is perhaps more
intuitive, e.g., if the covariate was "age", I'd rather enter the
adjustment at age 50 or age 55 than the mean of all subjects, (say if it
were 52.38 years).  Also, in GENMOD, with poisson you could add the exp
option.

in GENMOD can enter

 Estimate 'Control Stdy Yr1' intercept  1 grp 1 0 study_yr 1 0 0
grp*study_yr 1 0 0 0 0 0 randnum .5 / exp;
 Estimate 'Control Stdy Yr2' intercept  1 grp 1 0 study_yr 0 1 0
grp*study_yr 0 1 0 0 0 0 randnum .5 / exp;
 Estimate 'Control Stdy Yr3' intercept  1 grp 1 0 study_yr 0 0 1
grp*study_yr 0 0 1 0 0 0 randnum .5 / exp;

 Estimate 'Intervention Stdy Yr1' intercept  1 grp 0 1 study_yr 1 0 0
grp*study_yr 0 0 0 1 0 0 randnum .5;
 Estimate 'Intervention Stdy Yr2' intercept  1 grp 0 1 study_yr 0 1 0
grp*study_yr 0 0 0 0 1 0 randnum .5;
 Estimate 'Intervention Stdy Yr3' intercept  1 grp 0 1 study_yr 0 0 1
grp*study_yr 0 0 0 0 0 1 randnum .5;

Robin High
UNMC







From:
Ray Harvey <rharvey3015@GMAIL.COM>
To:
SAS-L@LISTSERV.UGA.EDU, Robin High <rhigh@UNMC.EDU>
Cc:
Ray Harvey <rharvey3015@GMAIL.COM>
Date:
04/28/2011 09:02 AM
Subject:
Re: Difference in parameter estimation LSMEANS and ESTIMATE statement with
covariate adjustments



Hi Robin,

Thank you for the reply.

So, when using the ESTIMATE statement I am testing only main unadjusted
effects, whereas when I use LSMEANS the parameter estimates are adjusted
for the other covariates in the model?

Is it possible to write an ESTIMATE statement to produce adjusted
parameter estimates in a multivariable model?

Thanks for your help,