Programming the statistical procedures from SAS

Re: GLM not using the correct error term

Reply
SAS Super FREQ
Posts: 3,547

Re: GLM not using the correct error term

Perhaps an administrator such as @LainieH could move this question to the SAS Statistical Procedures community where there is a better chance for a response.

N/A
Posts: 1

GLM not using the correct error term

Hi,

I am running GLM on my data with subsamples. I'm using the following code.

proc GLM data=DO_data order=data;

    class block distance core;

    model do = block distance core(block*distance);

    output out=check p=pred r=resi;

    test h=distance e=core(block*distance);

Because I am including subsamples, my F value for distance is supposed to be MST/MSE which is MS(distance)/MS(core(block*distance)). I've specified that in the code however my results are still showing F value that uses MSSE which is error from the subsamples. I could not find any mistake with the code unless someone could point out where I went wrong.

Thanks in advance.

Cheers

Community Manager
Posts: 291

Re: GLM not using the correct error term

[ Edited ]

Thank you, Rick!

 

@MAuluck, I moved this post to the SAS Statistical Procedures community for better visibility.

 

I accidentally moved Rick's reply first (first time moving a post in the new system).

 

Hope you can find an answer here.

 

Lainie

Respected Advisor
Posts: 3,780

Re: GLM not using the correct error term

You will see thet TEST statement output in a different section of the output below the default ANOVA table.  

 

I think PROC MIXED can do all this for you "automatically" given you specify the correct random and possibly repeated statement options.

Respected Advisor
Posts: 2,655

Re: GLM not using the correct error term

I have to agree with @data_null__ here.  This design looks like a repeated measures design (split-plot most likely), and PROC GLM does not correctly calculate tests or standard errors for those.

 

If you could present more about the design and the subsampling, I think a PROC MIXED approach could easily be applied.

 

Steve Denham

Ask a Question
Discussion stats
  • 4 replies
  • 308 views
  • 1 like
  • 5 in conversation