This Website is devoted to a description of TRYSYS .

TRYSYS is a key-cluster factoring program. Other techniques available for performing dimension reduction lean heavily on orthogonal factor analysis. TRYSYS’s key-cluster factoring has the advantage of not forcing dimensions to be orthogonal, that is, it allows a significant degree of correlation among dimensions. It is arguable that this capability allows its dimensions to approximate those of everyday experience. The program has several other features that are simply not available in the major statistical packages.

TRYSYS is descendent of the BCTRY program, which was developed by Robert C. Tryon at Berkeley during the 1960s. [See Cluster Analysis by Robert C. Tryon and Daniel E. Bailey (New York : McGraw-Hill, 1970) for a description.] BCTRY proved extremely useful for analyzing the relationship among variables on psychological tests and therefore for creating scales, for example, for the MMPI. Tryon also used BCTRY to cluster-analyze socioeconomic variables for the San Francisco Bay Area.

The program was revived in the 1980s by Robert B. Dean and associates thanks to a substantial grant from NIH. The old FORTRAN code was recompiled to run on a PC; many changes were made; and the program was renamed TRYSYS. Most of this work was done by John Bauer of Boulder, Colorado. In addition, PYTHON scripts were developed by William Schulz of Flagstaff, Arizona; these enable TRYSYS to be run easily from a desktop.

For examples of TRYSYS at work, see the social-area analyses of tract-level census data for the Chicago area in 1990, 2000, and 2010, and 2020. Analysis of the two earlier years is available at the website of the University of Chicago Library’s Map Collection. Analysis for 2010 and 2020 is available at the Liberal Landscape website.

This Website provides access to some of the literature on TRYSYS, to a TRYSYS manual, and to the software itself. It also contains information on TRYSYS’s predecessor program, BCTRY.

For additional information, e-mail Robert B. Dean, of Chicago, Illinois, at robertbdean@gmail.com.