Hi Sir, I want to print values of all numeric variables (40 variables), so I can use the code below. But I want to suppress one variable to be printed. How can I do that? proc print;   var _numeric_; run; Similarly, in another case, I want to output all numeric variables except one variable. How can I do that? Thanks for teaching. ... View more

Hi Sir, I finally finished the running for a linear regresion model using PROC GENMOD. But it took 25 hours. The dataset has 1 million cases and 40 categorical variables. What I don't quite understand is that: The estimated intercept is 1400, as the overall mean (all the predicators in the model are categorical and parameterized with effect coding). But the original observed mean for the dependent variable is only 250. I don't understand why there is such a big difference. Because of poor model fit? Thanks for your idea. ... View more

Hi Sir, I used PROC GENMOD to run a linear regression analysis. The reason that I want to use PROC GENMOD is that it provides the effect coding, while PROC GLM does not have this option. As the analysis is linear regrssion (DIST=normal), can I get the R-Squared value from PROC GENMOD? It seems that there is no option available for this request. Many thanks! ... View more

Hello sir, I have a question regarding the merge statement. As an example, I try to merge two files data01 and data02 into a single file data03, by variable a. But the values of data02 overwrite the values of data01. For missing values of data01, this is good. But it is bad that the missing values of data02 also overwrite the values of data01. My question is how to keep values of data01 from being overwritten if they are not missing? data work.data01;   input a b;   cards;   1 2   2 .   3 1; run; data work.data02;   input a b;   cards;   1 2   2 2   3 .   ; run; data work.data03;   merge work.data01 work.data02;   by a; run; /*Result: Obs  a    b   1     1    2   2     2    2   3     3    . ... View more