I am running a model using proc genmod and have run a lsmeans statement. I would like to save only some of the columns of the lsmeans table using the ods output. General setup: proc genmod data = data; class x; model y= x / dist = nb link = log offset = myoff; lsmeans x / pdiff; ods output 'x Diffs'=diffs(keep = x Estimate 'Standard Error'); run; This gives the error that 'Standard Error' is not valid. This is not surprising because it has a space in the variable name. I tried specifying as: ods output 'x Diffs'=diffs(keep = x Estimate 'Standard Error'n); which adds the 'n' as suggested here but that also does not work. There are many variable names in output tables which contain spaces, so understanding how to do this would be very helpful. Thank you ... View more

Hello,   I am looking to fit a GEE ZINB model using proc nlmixed. I have turned to proc nlmixed as neither proc genmod or proc GEE can handle zero-inflated distributions for GEE analysis.   Following SAS sources, such as note 2 here , I believe I can set up the nlmixed statement correctly as needed. However, I am not sure how to specify clustering. In general, my code looks like:   proc nlmixed data = data; /* linear predictor for zero inflation */ eta_zero = a0; prob_zero = 1/(1 + exp(-eta_zero)); /* linear predictor for negative binomial */; eta_mean = b0 + b1*dTLN + b2*dNLLN + b3*dT; mean = exp(eta_mean + myoff); IF y= 0 THEN lglk = LOG(prob_zero + (1-prob_zero)*(1+(phi*mean))**(1/phi)); ELSE lglk = LOG(1-prob_zero) + y*LOG(phi*mean) - (y+(1/phi))*LOG(1+(phi*mean)) + lgamma(y+(1/phi)) - lgamma(1/phi) - lgamma(y+1); model y ~ general(lglk); random ??? ; run; I understand proc nlmixed can utilize a 'random' statement which can include a subject identifier, but I do not want to include any random effects (I am trying to avoid a linear mixed effects model). I would just like to account for clustering/correlation as a subject can provide more than one response. Note, the data is not a longitudinal study setup.   Is there a way to manipulate the random statement to allow for some correlation structure but not to estimate any random effects, setting up for interpretation as a GEE? Or is there another statement/line in nlmixed I can do this?   Thanks! ... View more

I am using SAS proc genmod to fit models. For example, proc genmod data=long_respir descending; class ID Treatment visit (ref="0"); model y = Treatment visit Treatment*Visit / dist=binomial link=logit type3 wald covb; repeated subject=ID / withinsubject=visit logor=fullclust; run; Where in the model statement specifying 'type3' requests SAS to output Type III tests for each of the predictor variables in the model. My question is: How can I view the contrast statements and 'L' matrix SAS uses to produce its Type III tests? To elaborate, if I write my own contrast statement, I can include the '/ e;' at the end to view the 'L' matrix implied by my contrast. I would like to see the 'L' matrix implied by the contrasts SAS uses to produce the Type III tests. I cannot find how I can get SAS to give me that.   I have read the SAS proc genmod documentation for both the model statement and contrast statement and I do not see an option to get what I desire. So, either there is not an option to get this or I am overlooking something. ... View more