Jerry Dallal: Statistical Software

Statistical Software

From the mid-80s to the early 90s I wrote a series of DOS-based shareware statistics programs, which I called STATOOLS(tm). They were intended to help me in my work by providing capabilities missing from commercial packages. If other analysts could use them, too, so much the better. Some STATOOLS(tm) have been made obsolete by updated commercial packages, but others have had surprisingly long lifetimes and show no sign of waning as long as analysts are still willing to use DOS programs. Many of the programs are available by anonymous FTP from the SimTel collection.

STATOOLS(tm) are no longer shareware. They are essentially freeware. Individual users may ignore any shareware notices that appear in the software. These programs may not be added to any commercial product, they may not be sold, and no fee of any kind may be charged for them, including distribution fees. However, these prohibitions are not meant to prohibit sites like SimTel from including STATOOLS(tm) in their collections. Citations are always appreciated!

NOTE: I have been told that the McAfee SiteAdvisor gives a red flag to my site because links to the Simtel site! Yes, there were links...to the download pages for my software! Next to a big red X we read, "When we tested this site we found links to simtel.net, which we found to be a distributor of downloads some people consider adware, spyware or other potentially unwanted programs." Further down the page, in teeny-weeny type, it reads, "In our tests, we found downloads on this site were free of adware, spyware, and other potentially unwanted programs." Too little, too late. With the big red X the damage is done. Therefore, I've removed the live links and put the URLs in square brackets. If you'd like the software, copy and paste the URLs into your browser.

PC-Size: Consultant (sample size calculations) [ http://www.simtel.net/pub/dl/50048.html ]

Logistic regression for Epi Info [ http://www.simtel.net/pub/dl/50011.html ]

Logistic regression for SYSTAT (includes ASCII to SYSTAT conversion program) [ http://www.simtel.net/pub/dl/50021.html ]

Miscellaneous statistical procedures for SYSTAT (normality, unimodality, two-phase regression, Johnson-Neyman ANCOVA, Alternating Conditional Expectations, incomplete paired data, dependent correlations, ...) [ http://www.simtel.net/pub/dl/50037.html ]

Exact randomization tests for SYSTAT (includes ASCII to SYSTAT conversion program) [ http://www.simtel.net/pub/pd/50041.html ]

The Statistician's Swiss Army Knife (probability distributions (normal, t, chi-square, F, binomial, Poisson, studentized range); exact confidence intervals for binomial p's; Fisher's exact test for 2 by 2 tables; exact confidence intervals for an odds ratio from a 2 by 2 table; Mantel-Haenszel test and approximate 95% confidence interval for the common odds ratio; Bartholomew's test for increasing proportions; Bartholomew's test for increasing normal means; one and two sample t-tests from summary statistics; correlation coefficients: test that a population value is 0, confidence interval for a single coefficient, test of equality of two independent coefficients, test of equality of two coefficients from the same correlation matrix)

A version of James Steiger's MULTICORR program that operates directly on SYSTAT system files. MULTICORR tests hypotheses about the elements of a correlation matrix. A complete description can be found at Steiger's website. Professor Steiger has made his source code publicly available, allowing me to attach a SYSTAT-like front end and let the program operate directly on SYSTAT data files. This version and Steiger's should give identical results.

PCT--the routine SYSTAT forgot--for calculating distribution percentiles. PCT is a stand-alone program that operates directly on SYSTAT system files. It includes all 5 definitions of percentiles found in SAS's PROC UNIVARIATE. The download is a self-extracting ARC file that contains the DOS-like executable and a documentation file. I wrote this program in 1993 after a long delay and with some reluctance because I expected SYSTAT to make it obsolete with each update to the software. Yet, it's still useful today!