And the macro itself or, better yet, a link to where you found the macro. SAS 5 was from the 70's or early 80's, so I suspect (hope) that is a version number for the macro rather than SAS itself. ... View more

This warning "WARNING: The quoted string currently being processed has become more than 262 characters long.  You might have unbalanced quotation          marks." is a very red flag; it can generate all sorts of other errors and strange behaviors.  Somewhere you have unbalanced quotes.  I suspect the problem is in your autoexec.sas file and not in the code itself and that you are getting it in the second run because you have not closed SAS in between runs.  Bring both of them into an editor that color codes comments and it should pop out at you (The one in EG 6.1 does fine.  I think SAS Studio would show it too.) Doc Muhlbaier ... View more

Actually, the work directories are designed to go away when you end the SAS process.  You should not attempt to reuse them.  Our SAS Admin runs the cleanwork tool to delete any orphan work and utility directories that are left by uses who exit SAS abruptly. ... View more

slg, that's the problem:  If you take a mean of logged data (as Bailey did in the t-test) and exponentiate that mean, it is NOT an estimate of the mean of the non-logged data.You end up with the geometric mean, which is much more difficult to interpret. ... View more

stat@sas:  Although the log transform is used empirically on skewed data (the variance stabilization that PGStats mentioned), in some areas it is the standard approach to work with certain types of variables.  It may be that the data are known from other work to follow a lognormal distribution. Bailey:  If the data are indeed log scaled, stat@sas' comment on interpretation needs to be paid attention to.  The test statistics are valid and the means/S.D's are too (on the log scale).  Where you run into challenges is that the difference of the means may not be interpretable. ... View more

Likely something to call tech support about. ... View more

Try unchecking 'Show SAS output log'. In 6.1, that is located under tools --> options --> project views (process flow). ... View more

As Jaap points out there are lots of ways to attack the Data Governance issues.  We have found that it is partly technical and partly behavioral. Locking down data and code stored in the OS is pretty straightforward.  Locking down an entire EG project might be something you could do, but you could also cripple it beyond any value.  EG stores the SAS logs in the project.  Those are always generated, so there is always writing going on.  That means the (temporary) copy of the project that is being run must have write access.  You can lock down the copy on disk, but it won't keep users from messing with it while they are using it. ... View more

Bootstrap simulations would not typically run out of memory (unless you are using IML), but it could easily run out of disk space.  For instance, the old %bootsamp macro stores the intermediate data on disk and it can add up fast. Can you post your bootstrap code. Also, this thread may be helpful: ... View more

Restonian, Stacie, Cynthia, I, too, was disappointed with the University Edition.  For years I taught introductory statistics to physicians who wanted to do research.  Ninety percent had no interest in learning SAS syntax.  I found EGuide a great improvement over the other tools I've used over the years in the course.  SAS Studio is a step backwards for my needs. Even though the installation of full SAS is a pain in the a**, that hassle pales in comparison to the pain of the SAS data step learning curve. ... View more

What you are asking about is called 'last observation carried forward' (LOCF).  There is an entire literature about why this approach is not statistically sound for imputation (just Google it sometime), but it is still used a lot in the social sciences.  I don't intend that as a criticism (sometimes we are 'told' what to do), but wanted to point out that LOCF is not without its detractors. EGuide can't do LOCF with the point-and-click interface; you have to write a data step and use the LAG function (See SAS(R) 9.4 Functions and CALL Routines: Reference, Second Edition for examples.) If the first item is missing, then you can sort the results in descending order and do it again. ... View more

One additional thought.  Some DBAs disable 'trusted connections' for SQL/Server.  If you can't use it interactively, you can't use it with SAS. ... View more

The simplest way might be to write a batch file to do it.  It really depends on the tools you have available. ... View more