@Demographer wrote: 1-Sorry I'm not sure what do you mean exactly by "You can set the parameter estimates of the LOGISTIC procedure as the starting values of the GLIMMIX procedure." Do you mean that if the intercepts of the model without covariate are for 0.5 0.2 0.3, I should use parms (0.5) (0.2) (0.3)? Yes, that is what I mean. You can also additionally set the starting values of other parameters (e.g., regression coefficients of the variables in the model other than the intercept) as the estimates obtained from the previous LOGISTIC procedure call. @Demographer wrote: 2-4 categories occ_reduced Frequency Percent Cumulative Frequency Cumulative Percent HIGH 467666 36.55 467666 36.55 LOW 107108 8.37 574774 44.92 MED 601957 47.05 1176731 91.97 UNEM 102782 8.03 1279513 100.00     In fixed effects logistic regression models, when one category of a categorical indepenent variable has too few observations or even zero observation, complete or quasi-complete separation can result, which means that the maximum likelihood estimator does not exist. When running SAS programs, this may be exemplified by failure of convergence. I could not remember if the same applies to the dependent variable as well and am also not that sure if such phenomena can be directly carried over to mixed effects model. But I saw that the second and fourth category of the dependent variable in your model both contain less than 10% of the entire observations in the dataset. Given that your log mentioned plenty of amount of removal of observations in model building process, it might be the case that too few observations whose dependent variable fall into the second and fourth category are eventually utilized. You can verify my conjecture on your own. So, if probable, you may try to combine the second and fourth category and build the model again. If that still does not work or combining categories is not permitted, look through the independent variables to see if variables with categories having little or zero data points exist. If that still does not work, look through the independent variables to see if any continuous ones exist. If so, you might try categorizing them (e.g., transform the continuous variable of age into elderly vs. not elderly). If that still does not work... then I am sorry that I have no idea how to tackle this problem in this case. ... View more

Two issues: (1) I saw a PROC LOGISTIC code preceding the PROC GLIMMIX code. So your analytic process falls into the scenario I mentioned days ago. You can set the parameter estimates of the LOGISTIC procedure as the starting values of the GLIMMIX procedure. You do not necessarily need to follow the exact code of @jiltao, as that was used as an example. In addition, the four numbers in parentheses are flanked by "*/" or "/*", which essentially nullify them by setting them as appendices. Refer to SAS Help to see the exact method of  specifying starting values. (2) How many categories are there in your dependent variable? How many observations fall into each category? You can show this in a one-way table easily get by PROC FREQ. ... View more

As @jiltao has mentioned, it (or maybe them) is (are) provided with trial and error. I comprehend it as providing it (them) arbitrarily. If the current step of providing starting values is among one of the many steps in your entire analytic process and that the starting values to be provided can be estimated from the preceding step, then you can set values of the estimated parameter obtained in the preceding step as the starting values of the current step. This is a practice adopted in Amazon.com: SAS for Mixed Models, Second Edition: 9781590475003: Littell Ph.D., Ramon C., Milliken Ph.D., George A., Stroup Ph.D., Walter W., Wolfinger Ph.D., Russell D., Schabenberger Ph.D., Oliver: Books. ... View more

The PARMS statement is used for providing starting values of parameters for iterations that estimate the parameters (e.g., regression coefficients). With no starting values provided, the simple inclusion of "PARMS;" in the code does not help. ... View more

I am also curious on two issues of provision of starting values by the user. (1) I remember that maximum likelihood is the method used here. Theoretically, if identifiability holds, then the maximum likelihood estimator should be unique. So is it useful to try different starting values? (2) I had personally tried providing starting values in the NLMIXED procedure and had noted the effect of the provision of starting values. This could have a bearing on the ultimate parameter estimates (contradicting the theoretical result I stated in the last paragraph, which is also something about which I am puzzled). So would not it be subjective if we arbitrarily provide starting values?  ... View more

What is the sample size of your entire data? I saw plenty of observations excluded from analysis due to zero, negative or missing weights. You could alternatively provide the size of the sample eventually used by the GLIMMIX procedure. ... View more

Another paper (Calculating power in analysis of variance. (apa.org)) found on the book Statistical Power Analysis for the Behavioral Sciences | Jacob Cohen | (taylorfrancis.com) also discusses the topic of power calculation in mixed effect models. Of closer revelance to your question is another paper cited in this book: Optimum Sample Size and Number of Levels in a One-Way Random-Effects Analysis of Variance: The Journal of Experimental Education: Vol 41, No 4 (tandfonline.com). A table of optimum sample size or number of levels for the random effects model is included in the latter paper. I hope these information helps. ... View more

Thank you for your reply and explanation! ... View more

Thank you for your reply! In the past few hours, I searched for information regarding the MEMSIZE option on the web and found a convenient way to change the memory available for a SAS session into 1TB while launching a new SAS session on my computer that is using Windows 10. Step 1: open a folder (any folder will do); Step 2: Paste the following code in the address bar:   C:\Program Files\SASHome\SASFoundation\9.4\sas.exe -memsize 1T For readers not familiar with the meaning of this code, it should be noted that the path is where my SAS is installed. Readers using my code should change that path to the where SAS is installed in their computer accordingly.   Step 3: Press the "Enter" button on the keyboard. And everything is done. A SAS session is launched automatically after you press the "Enter" buttion. But it should be noted that the alteration done in this manner is only valid in this very session. In other words, if you end this session by closing SAS window and launch yet another one with another method (like clicking the SAS shortcut in the Start Menu), then the largest amount of memory SAS can use resumes to the default value, which is usually 2GB. ... View more

What is the correct code to change the memory then? I tried the following code and the log reported an error: -memsize 1T; ... View more

Thank you! ... View more

You can search on the web for papers on this field like Estimating power in (generalized) linear mixed models: An open introduction and tutorial in R | Behavior Research Methods (springer.com). R code is provided in the paper. ... View more

The getoption function seems a useful function. Could you please provide examples on how to use them to check the memory available? I checked SAS Help and found it seems not available as a statement that acts independently like "ODS GRAPHICS ON;". It seems that it must be embedded in an argument like  if getoption('yearcutoff') = '1926' then do; So if I am just launching a new SAS session and want to check out how much memory do I have, how should I use the getoption function to do this? ... View more

All right. I have got it. Thank you for your patient reply! ... View more

Thank you! I took a second look at your reply and have now understood why it was there. ... View more