Okay. I made that change. The MIANALYZE now produces output for 4 (gender,length,regions,status) of 8 of my predictors - in other words, no output for "ethno", "sab", "reasons", or "d8lgbtcom". These are all of my dichotomous variables, so I wonder if it's an issue with the coefficients, I selected. I changed the code from param=ref to param=glm as per your instructions. I'm not sure of the implications of this. Based on your explanation of coefficients above, does this mean that a variable with multiple levels will need multiple estimates lines? For example, the b5gp variable has 3 levels: Estimate 'gender' b5gp 1 -1/exp;* Estimate 'gender' b5gp 1 /exp;* Additionally, the mianalyze output provides one single-row LBetaEstimate Variance table and one single-row LBetaEstimate Parameter Estimates table). I'm not sure what this tells me that the original mianalyze output wasn't telling me before. Thank you! here is the log for mianlayze. NOTE: The data set WORK.EST_DS has 80 observations and 12 variables. NOTE: The data set WORK.REGPARMS has 740 observations and 9 variables. NOTE: PROCEDURE GENMOD used (Total process time): real time 44.16 seconds cpu time 27.37 seconds 21008 proc sort data=est_ds; 21009 by label _imputation_; 21010 run; NOTE: There were 80 observations read from the data set WORK.EST_DS. NOTE: The data set WORK.EST_DS has 80 observations and 12 variables. NOTE: PROCEDURE SORT used (Total process time): real time 0.01 seconds cpu time 0.01 seconds 21011 proc mianalyze data=est_ds; 21012 by label; 21013 modeleffects LBetaEstimate; 21014 stderr stderr; 21015 run; NOTE: PROCEDURE MIANALYZE used (Total process time): real time 0.07 seconds cpu time 0.07 seconds ... View more

Thanks, Rob. This actually brings up another one of my questions. I'm unclear on the meaning of these coefficients in the estimates statements. I'm not sure why there is sometimes "1", or "1 -1", or "1 0". I merely guessed these numbers based on examples I found online. But I'm unable to find any text that explains them. Could you explain that to me as well? Log below. Thank you!! 20597 Proc GenMod data=irnfcs ; 20598 title3 'MI. Mod Pois Regress. Healthcare provider w covs w/o moderators'; 20599 Class id ethnorac (ref='0') b5gp (ref='1') b2 (ref='1') provreg (ref='1') a13status (ref='0') 20599! d3_reasons (ref='0') 20600 a8_7cat (ref='2') e1_3cat (ref='1') d8lgbtcom (ref='0') poverty_2cat (ref='0') a14_5cat 20600! (ref='1') 20601 /param=glm ref=first; 20602 Model f1_2cat = ethnorac b5gp b2 provreg a13status d3_reasons a8_7cat d1_length d8lgbtcom a1 20602! e1_3cat poverty_2cat 20603 a14_5cat / Dist=poisson Link=log; 20604 lsmeans ethnorac b5gp b2 provreg a13status d3_reasons a8_7cat d8lgbtcom /ilink cl; 20605 weight tpcweights; 20606 by _imputation_ ; 20607 Repeated subject=id /printmle type=Ind; 20608 ods output GEEEmpPest= regparms; 20609 Estimate 'ethno' ethnorac 1 /exp; 20610 Estimate 'gender' b5gp 1 -1/exp; 20611 Estimate 'sab' b2 1 /exp; 20612 Estimate 'status' a13status 1 -1/exp; 20613 Estimate 'reasons' d3_reasons 1 /exp; 20614 Estimate 'regions of origin' a8_7cat 1 -1/exp; 20615 Estimate 'length' d1_length 1 /exp; 20616 Estimate 'd8lgbtcom' d8lgbtcom 1 /exp; 20617 ods output estimates=est_ds(where=(index(label,'exp')=1)); *keeps the EXP values and their SE; 20618 run; NOTE: Class levels for some variables were not printed due to excessive size. NOTE: Algorithm converged. NOTE: The scale parameter was held fixed. NOTE: Algorithm converged. NOTE: The empirical covariance matrix estimate is used in the LSMEANS statement. NOTE: The empirical covariance matrix estimate is used in the ESTIMATE statement. NOTE: The structure of the LSMeans table has changed from an earlier release of SAS. NOTE: The above message was for the following BY group: Imputation Number=1 NOTE: Class levels for some variables were not printed due to excessive size. NOTE: Algorithm converged. NOTE: The scale parameter was held fixed. NOTE: Algorithm converged. NOTE: The empirical covariance matrix estimate is used in the LSMEANS statement. NOTE: The empirical covariance matrix estimate is used in the ESTIMATE statement. NOTE: The structure of the LSMeans table has changed from an earlier release of SAS. NOTE: The above message was for the following BY group: Imputation Number=2 NOTE: Class levels for some variables were not printed due to excessive size. NOTE: Algorithm converged. NOTE: The scale parameter was held fixed. NOTE: Algorithm converged. NOTE: The empirical covariance matrix estimate is used in the LSMEANS statement. NOTE: The empirical covariance matrix estimate is used in the ESTIMATE statement. NOTE: The structure of the LSMeans table has changed from an earlier release of SAS. NOTE: The above message was for the following BY group: Imputation Number=3 /*...etc. for all 20 imputations*/ NOTE: The data set WORK.EST_DS has 0 observations and 12 variables. NOTE: The data set WORK.REGPARMS has 740 observations and 9 variables. NOTE: PROCEDURE GENMOD used (Total process time): real time 47.20 seconds cpu time 27.35 seconds 20619 proc sort data=est_ds; 20620 by label _imputation_; 20621 run; NOTE: Input data set is empty. NOTE: The data set WORK.EST_DS has 0 observations and 12 variables. NOTE: PROCEDURE SORT used (Total process time): real time 0.01 seconds cpu time 0.01 seconds 20622 proc mianalyze data=est_ds; 20623 by label; 20624 modeleffects LBetaEstimate; 20625 stderr stderr; 20626 run; NOTE: No observations in data set WORK.EST_DS. NOTE: PROCEDURE MIANALYZE used (Total process time): real time 0.00 seconds cpu time 0.00 seconds ... View more

Thanks, Rob. I used your code, but it does not run to completion. First, I still receive the log warning: "The model does not have a GLM parameterization. This parameterization is required for the TEST, LSMEANS, LSESTIMATE, and SLICE statement. These statements are ignored." The 20 imputations run through, but the data set work.est_ds has 0 observations and 12 variables so the proc sort command does not work (explanation: data set is empty). And mianalyze does not run because work.est_ds has no observations. ... View more

A note on my post: My understanding is that, through proc genmod, I can obtain relative risk measures from the Contrast Estimates Results tables (the Mean Estimate column). The issue is that I can not seem to obtain overall relative risk estimates, for example, through the amalgamating proc mianalyze stage. Which data from the mianalyze output will give me overall relative risk or incidence rate ratio estimates? Thank you!   ... View more

Hi. thanks for your response. I don't understand what you mean by this line: "I just check the result . It is ODDS not RELRISK ." I tried the code and link that you provided above. But adding an lsmeans line gives me the error: "The model does not have a GLM parameterization. This parameterization is required for the TEST, LSMEANS, LSMESTIMATE, and SLICE statement. These statements are ignored." Here is my code: Proc GenMod data=irnfcs ; title3 'MI. Mod Pois Regress. Healthcare provider w covs w/o moderators'; Class id ethnorac (ref='0') b5gp (ref='1') b2 (ref='1') provreg (ref='1') a13status (ref='0') d3_reasons (ref='0') a8_7cat (ref='2') e1_3cat (ref='1') d8lgbtcom (ref='0') poverty_2cat (ref='0') a14_5cat (ref='1') /param=ref ref=first; Model f1_2cat = ethnorac b5gp b2 provreg a13status d3_reasons a8_7cat d1_length d8lgbtcom a1 e1_3cat poverty_2cat a14_5cat / Dist=poisson Link=log; lsmeans ethnorac b5gp b2 provreg a13status d3_reasons a8_7cat d8lgbtcom /ilink cl; weight tpcweights; by _imputation_ ; Repeated subject=id /printmle type=Ind; ods output GEEEmpPest= regparms; Estimate 'ethno' ethnorac 1 /exp; Estimate 'gender' b5gp 1 -1/exp; Estimate 'sab' b2 1 /exp; Estimate 'status' a13status 1 -1/exp; Estimate 'reasons' d3_reasons 1 /exp; Estimate 'regions of origin' a8_7cat 1 -1/exp; Estimate 'length' d1_length 1 /exp; Estimate 'd8lgbtcom' d8lgbtcom 1 /exp; run; ... View more

Hi Koen, I discovered that the error was happening because some code was lost in the copy and paste process. All is resolved now, thanks to the code solutions provided here. Thank you! ... View more

The code successfully runs until it begins proc mianalyze. At this point, it freezes - so there is no information about the issue in the log and there is no error notice. My program has never frozen before and whatever is now happening at proc mianalyze has caused the program to freeze multiple times, so I'm not sure what the issue could be. ... View more

Thanks, Rob. I copied and pasted your solution and it's causing my program to crash each time I run it (before completing the mianalyze stage). Do you know why that might be? ... View more

Thanks, Koen! I tried to follow this manual yesterday, but continued to get errors. it's possible I don't understand the instructions. For example, adding "classvar=classval)" led to an error that the variable classval does not exist. The modeleffects list with "c3(c2 c1)" also confused me, as I wasn't sure how (or why) to apply this structure to my own code. I've tried to update my code again to follow these steps (abbreviated version posted below), but still receive a warning that the item covb could not be created. Any help you can provide would be appreciated! Proc GenMod data=irnfcs ; title3 'MI. Mod Pois Regress. Healthcare provider w/o moderators'; Class id f1_2cat (ref='0') ethnorac (ref='0') b5gp (ref='1') b2 (ref='1') provreg (ref='1') a13status (ref='0') d3_reasons (ref='0') a8_7cat (ref='2') d8lgbtcom (ref='1') poverty_2cat (ref='0') e1_3cat (ref='1') /param=ref ref=first; Model f1_2cat = a1 ethnorac e1_3cat b5gp b2 provreg d1_length a13status d3_reasons a8_7cat d1_length d8lgbtcom poverty_2cat / Dist=poisson Link=log; weight tpcweights; by _imputation_ ; Repeated subject=id /printmle type=Ind; ods output parameterestimates = regparms ParmInfo = irnparminfo CovB = irncovb; run; ods select all; proc print data=regparms; run; proc sort data=regparms; by _imputation_; run; data regparms2; set regparms; parameter=compress(parameter); proc print data=regparms2; by _imputation_; run; proc mianalyze parms=regparms2 covb=irncovb parminfo=irnparminfo; modeleffects intercept a1 ethnorac1 e1_3cat2 e1_3cat3 b5gp2 b5gp3 b22 provreg2 provreg3 provreg4 d1_length a13status1 a13status2 d3_reasons1 poverty_2cat1 a8_7cat3 a8_7cat4 a8_7cat5 a8_7cat6 a8_7cat7 d8lgbtcom2; run; ... View more