Great, thanks! ... View more

Thank you for your answer. I forgot to include my standardization code here. Actually, the dataset currently used, named fish2, is the result after standardization. The standardization code: /*Standardize all variables in the dataset named fish1*/ proc stdize data=fish1 out=fish2; var Length1 Length2 Length3; run;   ... View more

One option might be to make use of the WEIGHT statement in Proc CAUSALMED to run with one of the replication methods.  The general approach would be to use one of the SURVEYXXX procedures to compute the replicate weights and then to run CAUSALMED with each set of replicate weights.  There is an example of doing something similar with Proc GENMOD.  You could likely adapt this example by substituting the CAUSALMED step for the GENMOD step.  You might need to do some research to see if this would be statistically valid, but I have seen others use a similar approach with BRR for mediation models. SAS/STAT Poisson Regressions for Complex Surveys ... View more

For your second question. p-value is highly depended on the size of sample. if your size of sample is large enough, you would always get <.0001 . It has nothing to do with CI of OR or estimated coefficient. And p-value is said for alpha=0.05, if you set alpha=0.0001, you would also get H0 is not significant conclusion. ... View more

Yes, it works. Thank you so much! ... View more

Part of the theoretical justification of the adjustment of confidence intervals in the presence of adjustment of estimated variances or standard errors in complex survey data analysis is the exceedingly low degrees of freedom used for building confidence intervals compared to the one used for construction of such interval under a simple random sampling setting. In fact, the degrees of freedom used for such interval estimation is usually a "rule of thumb degrees of freedom" and equals to the difference between the unique number of primary sampling units and the number of strata. In most sampling cases, this number is usually dramatically lower than the sample size minus one, which is the degrees of freedom used for building confidence intervals in a simple random sampling setting. Why do we employ such a small degrees of freedom for complex surveys? I think part of the reason lies in the shrunken effective sample size caused by the correlation among survey subjects. To understand the concept of effective sample size, I would like to modify an example provided in Amazon.com: Applied Survey Data Analysis (Chapman & Hall/CRC Statistics in the Social and Behavioral Sciences): 9780367736118: Heeringa, Steven G., West, Brady T., Berglund, Patricia A.: Books. Suppose you are a researcher interested in the distribution of age and sex of the English teachers of a school. You entire a classroom with 50 students and ask them questions on their teachers' age and sex. Given that the students actually share an English teacher and their results are correlated, you actually receive the same answer among them. Therefore, if you ask your question one by one, you do not have information on 50 teachers, you only have information on one. In other words, the effective sample size is 1 instead of 50. From a statistical perspective, the shrinkage in effective sample size is attributable to the correlation among the observations. In a simple random sampling setting, the assumption that subjects are independent of each other is tenable, so the information you get from one subject is completely different from that of the other subject. You really get something you new every time you obtain one sample subject. But once the observations are correlated, as in complex surveys, you actually receive less information from a new respondent than you do when they are independent of each other, an assumption you can safely make in a simple random sampling setting. ... View more

In general, the difference will be in the manner in which the variances are computed.  Complex survey data uses methodology that adjusts for the design (cluster and strata) effect.  Data that is merely weighted will use the usual formulations for weighted variances.   ... View more

It looks like  the order of record has changed between these two datasets. Here is an example.   data ds; call streaminit(123); do n=1 to 100; baseline=rand('normal'); month1=rand('normal'); month2=rand('normal'); if n in (10:20 90 98:100) then call missing(baseline); if n in (1:4 9 28:30) then call missing(month1); if n in (40:50 80:85) then call missing(month2); output; end; run; proc sort data=ds out=ds2; by descending n; run; proc mi data=ds seed=123 nimpute=100 out=out1; var baseline month1 month2; run; proc mi data=ds2 seed=123 nimpute=100 out=out2; var baseline month1 month2; run; proc sort data=out2 out=out22; by _Imputation_ n; run;         ... View more

Thank you very much for providing such a wonderful solution! ... View more

Actually, the STRATA statement in the SURVEY procedures are intended to house the strata used in the sampling design, not the croostabs. For your problem, it is appropriate to use syntax like gender*outcome or age group*gender*outcome like you might frequently do in the FREQ procedure. ... View more

The long format is not usually compatible with performing  multiple imputation, thus data restructuring from long to wide or the reverse is often needed for multiple imputation.  There is a good discussion in Raghunathan's Missing Data in Practice text (2016) pages 121-126 and in the 2018 paper linked below. Using SAS for Multiple Imputation and Analysis of Longitudinal Data ... View more

No, you are interpreting it correctly.  I was wrong about what was contained in that data set. In any regard, hypothesis testing in finite mixture models is not very well defined because it is difficult if not impossible to derive the asymptotic distribution for the mixture likelihood.  There is a paper that discusses the problem and makes a few suggestions related to goodness of fit tests that might work.  Anything that they propose would not be available in SAS, but you might be able to program it yourself. Hypothesis testing for finite mixture models - ScienceDirect   ... View more

Thank you. I now know how to set edf.  ... View more

Hi Rob,   Thank you for sharing! Would you be able to share an example of the dataset I need to create? I require the individual treatment means for each visit - would it be using the array terms? ... View more