SAS procedures automatically generate many graphs when you turn on ODS graphics. For example, I have written about how to interpret the graphs that are produced automatically when you use PROC PRINCOMP to perform a principal component analysis (PCA). The built-in graphs are well-designed and informative, but this article discusses
Good old Scotch drink! Inspire me, until I lisp and wink, To sing your name! -- Robert Burns (1785) Scotch whisky (spelled without an 'e') is a popular drink that makes up a multi-billion dollar industry. Scotch whisky accounts for almost 75% of Scotland's food and drink exports! Poets
When you implement a numerical algorithm, it is helpful to write tests for which the answer is known analytically. Because I work in computational statistics, I am always looking for test matrices that are symmetric and positive definite because those matrices can be used as covariance matrices. I have previously
A previous article shows how to compute various robust estimates of scale in SAS. In that article, I show how to scale these robust estimators so that they become consistent estimators of the standard deviation (σ) when the data are normally distributed. The scaling factor is related to the expected
Years ago, I wrote an article about the "trap and cap" programming technique. The idea is that programmers should "trap" inputs to functions (like SQRT, LOG, and QUANTILE functions) to avoid domain errors. In addition, when visualizing a function's range, you should "cap" the output to improve graphs of functions
In statistics, the normal (Gaussian) distribution serves as a reference for many statistical quantities. For example, a normal distribution has excess kurtosis equal to zero, and other distributions are classified as leptokurtic (heavier-than-normal tails) or platykurtic (lighter-than-normal tails) in comparison. Similarly, the standard deviation of a normal distribution (σ) is
A previous article shows how to use PROC FCMP to define the PDF, CDF, and quantile functions for the three-parameter Burr XII distribution. I also defined the log-PDF function, which is used during maximum likelihood estimation (MLE) of parameters. This article shows how to fit the Burr distribution to data
SAS supports more than 25 common probability distributions for the PDF, CDF, QUANTILE, and RAND functions. If you need a less-common distribution, you can implement new distributions by using Base SAS (specifically, PROC FCMP) or the SAS/IML language. This article shows how to use call functions related to the three-parameter
There are many ways to visualize the distribution of univariate data. A previous article presents an overview and shows how to use SAS to create histograms, kernel density estimates, box plots, and cumulative distribution plots. This article continues the visualization journey, with an emphasis on dot plots and heat maps.
In a previous article, I presented some of the most popular blog posts from The DO Loop in 2025. In general, popular articles deal with elementary topics that have broad appeal. However, I also write technical articles about advanced topics, which typically do not make it onto a Top 10
