Programming the statistical procedures from SAS

PROC GENMOD: I get non-estimable least squares means, but an estimable difference in least squares means.

Reply
Occasional Contributor
Posts: 14

PROC GENMOD: I get non-estimable least squares means, but an estimable difference in least squares means.

I ran a PROC GENMOD code (see below).  The output shows that the least squares means for a binary variable, "Q", are non-estimable, but there is an estimated difference in least squares means between "Q = 1" and "Q = 0".

How is this possible?  I thought that the difference in least squares means is calculated by subtracting the 2 least squares means.  If my least squares means are non-estimable, then shouldn't my difference in least squares means be non-estimable, too?

Thanks for your thoughts.

proc genmod

  data = mydata;

  class Q (ref = '0')

  X (ref = '1')

  W (ref = '1')

  R;

  model successes/trials

  =

  Q

  X

  W

  X * W

  Q * X

  Q * W

  / dist = bin

  link = logit;

  repeated

  subject = R;

  lsmeans Q / exp diff cl e;

  lsmeans X / exp diff cl e;

  lsmeans W / exp diff cl e;

  lsmeans X * W / exp diff cl e;

  lsmeans Q * X / exp diff cl e;

  lsmeans Q * W / exp diff cl e;

run;

SAS Super FREQ
Posts: 3,547

Re: PROC GENMOD: I get non-estimable least squares means, but an estimable difference in least squares means.

Normally I don't try to answer these kinds of questions, but it is Saturday morning and I don't know if the experts will see this question until Monday.  I am not an expert in this area, but I'll give it a shot.

In theory, it possible to estimate the difference of means without being able to estimate the means. Suppose I collect data for two variables, X and Y. I don't give you the original data, but instead decide to subtract off some reference value from both variables nd then give you the adjusted values. I might subtract 7 or 13 or 321...you don't know.  As a consequence of my manipulation, there is no way that you can estimate the means of the variables. Howeer, you can easily estimate the mean of the difference X-Y, since my subtraction cancels out.

In your case, you have a binary variable Q. The level Q=0 is not estimable because it is getting lumped in with the intercept term. (I assume the level Q=1 has an estimate, right?)  However, you can estimate the incremental effect of Q=1 as compared to Q=0, which means that you can estimate the difference.

Valued Guide
Valued Guide
Posts: 684

Re: PROC GENMOD: I get non-estimable least squares means, but an estimable difference in least squares means.

This can easily happen with fixed-effect models.

Occasional Contributor
Posts: 14

Re: PROC GENMOD: I get non-estimable least squares means, but an estimable difference in least squares means.

Thanks for your reply on a Saturday morning, Rick!

No, actually - I do not get an estimate for Q = 1 in the least squares mean output.  Both Q = 1 and Q = 0 are non-estimable in the least squares mean table.

As I understand, the difference in least squares means is calculated by subtracting the 2 least squares means - which makes my result very strange.  If both the least squares means are non-estimable, then how can the difference in least squares means be estimable?

Ask a Question
Discussion stats
  • 3 replies
  • 352 views
  • 0 likes
  • 3 in conversation