SAS Support Communities
Help
cancel
Turn on suggestions Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 
since ‎05-09-2020
‎07-16-2021
anguye11
Calcite | Level 5
There are no new messages in this topic

Re: Binomial clustered data-genmode

by Calcite | Level 5 in Statistical Procedures
‎07-16-2021 10:37 AM
‎07-16-2021 10:37 AM
Try -   proc genmod data= data; class hospital gender(ref="2") outcome(ref="1") ID; model outcome= gender /dist=binomial link=log; repeated subject=hospital / logor=nest1 subcluster=ID; estimate 'M v F' gender 1 -1 / exp; /*if male=0 and female=1 in your data*/ run; The repeated statement above fits an Alternative Logistic Regression model. The exp option in the estimate statement will transform the beta estimate to a RR ... View more
There are no new messages in this topic

How to specify order-restricted test for 3 groups with PROC PLM

Message contains a hyperlink
by Calcite | Level 5 in Statistical Procedures
‎07-16-2021 09:32 AM
‎07-16-2021 09:32 AM
Hi all,    I need to conduct a 3-group comparison where the alternative hypothesis is order-restricted: A > B > C. This test is unlike a traditional F-test where the alternative is A ≠ B ≠ C. I read from Vanbrabrant, 2014 (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4292225/),  order-restricted tests can be accomplished using PROC PLM but I could not find the right example in the PLM documentation. I believe I need to use the UPPERTAILED or LOWERTAILED option of LSESTIMATE but I'm not certain how to specify the contrasts -    proc plm restore=mymodel; lsestimate group 1 0 -1 / ftest uppertailed; I think the above is comparing A > C but not A > B > C ?   Thank you for your help, Anthony ... View more