I'm going to guess that all variables in the model are class variables and that the "problem" is a note that says: Note: The X'X matrix has been found to be singular, and a generalized inverse was used to solve the normal equations. Terms whose estimates are followed by the letter 'B' are not uniquely estimable. If so, there's nothing wrong with your model or data. You just need to understand how to interpret the parameter estimates. See this usage note: http://support.sas.com/kb/22/585.html If this isn't the problem, post the error message that you get. ... View more

What is important is the number of levels (=unique values) in your classification variables. If each classification variable has 10 levels, then the regression involves approximately 400 dummy variables as regressors. If I recall, you are using GENMOD only because you want to use a parametrerization that is different than the GLM encoding. How long does it take for your problem to run in GLM? GENMOD solves a maximum likelihood problem, which involves an iterative optimization, so it will be slower than GLM on the same problem. For effect coding, the main effects estimate the difference in the effect of each nonreference level compared to the average effect over all four levels. That average effect gets lumped in with the intercept. That's why your Intercept estimate is different than the observed mean. I assume you know that the predicted values you get from GENMOD are the same as you get from GLM. The only difference is how to INTERPRET the parameters. For an example with continuous variables, see http://blogs.sas.com/content/iml/2010/11/10/regression-coefficients-for-different-polynomial-bases/ ... View more

Add a dummy variable to the data set that has the values 1, 2, ...,k, where k is the number of categories. Then use a user-defined format as shown by @Joeldw to map the dummy variable to the categorical values. ... View more

One way to do this is to use the idea of a "contaminated normal distribution," which is a specific kind of mixture distribution. After you define the x variable simulate the y variable as follows: type = rand("Bernoulli", 0.1); /* outlier with 10% probability */ if type=1 then      error = rand("Normal", 0, 10); /* error is N(0, 10) */ else      error = rand("Normal", 0, 1); /* error is N(0, 10) */ y = intercept + beta*x + error; outlier = (abs(error)>3); Change the probability of contamination (0.1), the magnitude of the contamination (10) and the definition of an outlier (3) as your needs require. For more info on the general case of sampling from a mixture distribution, see http://blogs.sas.com/content/iml/2011/09/21/generate-a-random-sample-from-a-mixture-distribution/ Rick ... View more

If you are trying to clear the HTML destination, here's one way to do it in SAS 9.3: http://blogs.sas.com/content/iml/2011/08/29/how-to-clear-the-output-window-in-sas-9-3/ ... View more

The expression x={a b} creates a character matrix with the values "A" and "B". You want to use horizontal concatenation to create a matrix from a and b: x = a || b; For more information on concatenation, download the FREE chapter of my book Statistical Programming with SAS/IML Software from http://support.sas.com/publishing/authors/wicklin.html and look on p. 41. Rick ... View more

Use PROC SGPLOT and use the statement scatter x=x y=y / MARKERCHAR=cell x2axis where x and y are the coordinates in the table and cell is contents of the cell. See p. 11 of Sanjay's paper http://www.pharmasug.org/proceedings/2011/SAS/PharmaSUG-2011-SAS-AD01.pdf ... View more

For example, here's one one approach: u = unique(v); free idx; do i = 1 to ncol(u);    k = loc(x=u);    idx = idx || k; end; print idx; This code isn't maximally efficient because it doesn't preallocate the IDX array (see http://blogs.sas.com/content/iml/2011/06/20/pre-allocate-arrays-to-improve-efficiency/). Still it's not too bad. Use this if your vectors aren't too long. If this step is being used in the innermost loop of a long-running computation, write back. The code can be improved, but at the cost of additional complexitites. ... View more

In SAS 9.3, the function you want is the ELEMENT function teamed up with the LOC function:      idx=loc(element(x,v)); If you haven't upgraded to SAS 9.3,  you can use the UNIQUE-LOC technique, which I recently blogged about. ... View more

As far as I know, the old G-style graphics in PROC IML do not support transparency. If you have SAS 9.22 or later, you can use the SUBMIT/ENDSUBMIT statements in the twocirc module. I think I'd try to solve this problem by using a SUBMIT statement  to call a SAS/GRAPH or ODS Graphics procedure that supports transparency. ... View more

Welcome Sanjay, Dan, Prashant, and Pratik! I am looking forward to learning tips and techniques at the feet of the masters. I will continue to occasionally show graphics as part of modern data analysis on my own blog, but it will be nice to see ODS graphics featured more often in the blog-o-sphere. Best wishes, Rick ... View more