The DO Loop
Statistical programming in SAS with an emphasis on SAS/IML programs
The normal distribution is symmetric, which means that it has zero skewness. In certain applications, it is useful to embed the normal distribution into a family that can model positively and negatively skewed data. Azzalini (1985) proposed a method to add a skewness parameter, α, to any symmetric family. He
The Cornish-Fisher (C-F) expansion approximates the quantiles of an arbitrary continuous univariate distribution by using only the mean, variance, skewness, and excess kurtosis of the distribution. Intuitively, you can model the shape of many common probability distributions by using these four moment-based quantities. This article shows how to use SAS
A SAS programmer asked how to implement the generalized inverse Gaussian (GIG) distribution in SAS. The GIG distribution is used as a conjugate prior for the variance of a normal distribution, so it appears in some Bayesian models. As its name implies, the generalized inverse Gaussian distribution includes the inverse