The DO Loop
Statistical programming in SAS with an emphasis on SAS/IML programs![Reduced models: A way to choose initial parameters for a mixed model](https://blogs.sas.com/content/iml/files/2017/01/ProgrammingTips-2.png)
This article describes how to obtain an initial guess for nonlinear regression models, especially nonlinear mixed models. The technique is to first fit a simpler fixed-effects model by replacing the random effects with their expected values. The parameter estimates for the fixed-effects model are often good initial guesses for the
![Use a grid search to find initial parameter values for regression models in SAS](https://blogs.sas.com/content/iml/files/2018/06/parmsseq2-641x336.png)
When you fit nonlinear fixed-effect or mixed models, it is difficult to guess the model parameters that fit the data. Yet, most nonlinear regression procedures (such as PROC NLIN and PROC NLMIXED in SAS) require that you provide a good guess! If your guess is not good, the fitting algorithm,
![The bootstrap method in SAS: A t test example](https://blogs.sas.com/content/iml/files/2018/06/bootTTest3-640x336.png)
A previous article provides an example of using the BOOTSTRAP statement in PROC TTEST to compute bootstrap estimates of statistics in a two-sample t test. The BOOTSTRAP statement is new in SAS/STAT 14.3 (SAS 9.4M5). However, you can perform the same bootstrap analysis in earlier releases of SAS by using
![The BOOTSTRAP statement for t tests in SAS](https://blogs.sas.com/content/iml/files/2018/06/bootTTest.png)
Bootstrap resampling is a powerful way to estimate the standard error for a statistic without making any parametric assumptions about its sampling distribution. The bootstrap method is often implemented by using a sequence of calls to resample from the data, compute a statistic on each sample, and analyze the bootstrap
![Video: New random number generators in SAS](https://blogs.sas.com/content/iml/files/2018/06/NewRNGSlide-702x336.png)
My 2018 SAS Global Forum paper was about "how to use the random-number generators (RNGs) in SAS." You can read the paper for details, but I recently recorded a short video that summarizes the main ideas in the paper. In particular, the video gives an overview of the new RNGs
![Attrs, attrs, everywhere: The interaction between ATTRPRIORITY, CYCLEATTRS, and STYLEATTRS in ODS graphics](https://blogs.sas.com/content/iml/files/2018/06/attrpriority2-702x336.png)
If you use PROC SGPLOT to create ODS graphics, "ATTRS" are everywhere. ATTRS is an abbreviation of "attributes." Most options that change the attributes of a graphical element end with the ATTRS suffix. For example, the MARKERATTRS option modifies attributes of markers, the LINEATTRS option modifies attributes of lines, and