A couple of comments: PROC RELIABILITY doesn't have a data step, so you need to clarify whether your question is about the DATA step to construct the data for PROC RELIABILITY or the procedure itself. I don't think that increasing the length of the variables in the DATA step is the answer. SAS stores the data in floating point, so whether you are using length 4 or 8, the same size number can be stored. The difference is in the precision and therefore the size of the maximum integer it can store precisely. The maximum storage length for a real number is 8 bytes. SAS does all of the internal computation in its procedures using double precision arithmetic. This sort of thing can happen when you have both extremely large numbers and extremely small ones in the same model (similar to a divide by 0 problem). You may need to rescale some of your variables. ... View more

not that I've seen. You can pretty much guess the predominant procedure by looking at the task title, but it's not guaranteed (The "describe" tasks can involve multiple procedures). You can always open an EGuide task, then preview the code to see the procedures used. ... View more

The INFILE statement is used for text files (and similar). The IMPORT procedure is used for a number of other data structures that SAS cannot read directly through one of its library engines. To see which applies to which, read the documentation for the INFILE statement, the IMPORT procedure, and LIBNAME engine. ... View more

You might get Jack Shostak's book "SAS Programming in the Pharmaceutical Industry'. ... View more

Welcome to the forum. "Procedures" may be a better place, but this is fine. Unfortunately, the SAS procedures that do automated selection don't recognize the higher order terms. You end up having to do the model selection manually (say with GLM rather than REG). I would generally take a backward elimination approach. If there are several higher order terms, then I'd do a 'chunk test' to look at a bunch of them at once (e.g. If I have 5 squares, I'd do one model with them in and one model with them out and build the f-test with 5 d.f. from the two models.) to reduce my multiple comparisons risks. Ditto the interaction terms. If someone else has reported that a particular higher order term is important, I might test that one individually to see if it holds in my data. Doc Muhlbaier Duke ... View more

Yup. Most of the time data are unbalanced for human studies analysis (we don't have nearly the control of our research subjects as in Ag!). Just like in GLM vs Latin Squares ANOVA, you lose some power by the lack of balance, but you gain in flexibility. ... View more

There is a bootstrap tool on the SAS support web site that works well. Check out this knowledgebase article: http://support.sas.com/kb/22/220.html ... View more

I prefer "data set" if for no other reason than it is the way I learned it. http://en.wikipedia.org/wiki/Data_set The two word approach is also used in the Federal Register, so I need to use it that way to quote things. ... View more

You need to call tech support on this one. ... View more

One way; not elegant, but effective. DATA new; a=3; * your constant, for example; DO i=1 to 10; *10 is max of index. y=a*RANNOR() + RANNOR(); OUTPUT; END; DROP i a; RUN; will generate a data set with one value of y for each value of the index. If you want to keep x_i and b_i, you need to do the assignment outside of the assignment statement for y. Note that the two executions of RANNOR generate different sequences of normal deviates. See documentation for details. Doc Muhlbaier Duke ... View more

If you rename the task in EGuide and then run it, the RTF takes the name "RTF - " in the output. At least that's what I get in 4.1 with multiple files in one e-mail task. Renaming the e-mail task also makes the zip file have the e-mail task name, which also helps with filing an interpretation. ... View more

The intercept can be viewed as the baseline risk if all the other effects are set to their 0 value (reference cell coding for class variables). Whether it is meaningful or not depends on the sorts of independent variables and the domain of study. (It is usually not meaningful if there are any continuous predictors.) I rarely even look at it. Doc Muhlbaier Duke ... View more

One approach to getting the output into a dataset or export is to use ODS. You can create/output/manipulate pretty much anything you can print from a procedure. You'll need to read a good bit of documentation or BBUs to become proficient, but the results can be quite useful. ... View more

Use PROC FREQ and output the table to a dataset, then split the dataset (or run FREQ twice, once for men and once for women; men shown below): PROC FREQ DATA=mydata(WHERE=(sex='M')); TABLES to*from*age/out=males; RUN; ... View more