Every thing that I have ever known or had to say on that topic is here.  https://support.sas.com/techsup/technote/mr2010c.pdf I'm pretty proud of this work. Parts are pretty technical, but it explains a lot.   The shortest answer I can give you is: No.   D-efficiency depends on so many things: how you coded, what mix of levels you have how many choice sets, how many alternatives, restrictions, and others. I like to show "toy" examples where all those things perfectly come together to make perfect designs. Even then, they are only perfect for the beta vector you specified, typically all zeros. Most of the time, we don't have toy examples and have no earthly idea how much D-efficiency can range for any particular problem.   Things to consider: Can you estimate every parameter of interest? If not, why not. With certain types of restrictions, you can never estimate everything that you can without them. How do your variances look? This is probably the key question. If they are wildly big, you might need more choice sets or a richer candidate set. I don't have time now to rerun your analysis, but I don't recall seeing any red flags when I did. If you post the variance results, I'll look at them later and comment.   Finally, let me say that you are asking a good question. I encourage you to look around in the article I mentioned for more help. ... View more

I assume you are looking for SAS the airline. This is SAS the software company. ... View more

I don't know, but has the length of variables in one of the data sets drastically increased, radically changing the size of the output data set? I would start by running PROC CONTENTS on both data sets and looking for something unexpected. ... View more

Reach out to SAS tech support. There at least used to be a visually impaired employee who would know everything there is to know about that subject. ... View more

Don't use GPLOT. SGPLOT is so much better. ... View more

https://documentation.sas.com/doc/en/mcrolref/1.0/n10i4tmalsyhgxn1hj4ud13ff074.htm ... View more

Nice! I have always been a big fan of and proponent of the axis table. I love the combination of graphical displays along with the axis table. ... View more

https://documentation.sas.com/doc/en/pgmsascdc/v_053/statug/statug_templt_sect019.htm   See if this example helps.  Search it for circumflex. ... View more

Don't use Optex. Use MktEx.   %mktex(3 3 3, n=17)   Better yet, %mktex(3 3 3, n=9) or %mktex(3 3 3, n=18)   %mktex will use OPTEX if nothing else is better, but it has other methods that often work better.   https://support.sas.com/rnd/app/macros/MktEx/MktEx.pdf   For a very small problem such as this, OPTEX, and most any other reasonable method will work the same. However, for larger problems, %mktex will often work better than OPTEX.   ... View more

Is it correct to use the %mktex macro with n = 144 and the %choiceff macro with nsets = 72?  Unfortunately, I don't understand exactly how the recommended size of the kandidate set relates to the size of the choice sets.   Sure. The candidates are simply profiles that might be included in the final design. 144 seems like a great number. Other numbers would work too.   Is my design able to estimate all parameters? Yes. Your D-efficiency is greater than zero, so yes. There is other output not shown that shows the parameters. ... View more

Have you tried getting rid of the quotes with %PUT? ... View more

A design that approximates a balanced incomplete block design should do the trick. A fully balanced design is not possible with 400 papers and your other constraints. All you need is one simple line:   %mktbibd(b=400,k=2,v=3) ... View more

I'm not even going to begin to figure out what you are doing. However, after writing tens of thousands of lines of macro code over the years, I can tell you my strategy. Never write macro code when you can avoid writing macro code. If you need to process a bunch of macro variables, do it in the context of DATA _NULL_, SYMGET, ordinary DATA step statements, and SYMPUT. Your life will be much easier. ... View more