This page contains links to various programs for estimating latent class models. Latent classes are groupings of cases that are assumed to underlie observed categorical measures, but that have not been measured directly or without error. Latent classes need only be nominal categories, but latent class analysis (LCA) can also be used to test the ordinal qualities of ordinal scales.
Below are links to the following LCA software programs: CDAS/MLLSA, DILTRAN, DISTAN, GLIMMIX, LCAG (no link yet), LEM, Miracle 32, Mplus, Latent GOLD, PANMARK, WinLTA, WINMIRA. These are followed by a brief list of LCA books and book chapters. It is not feasible for me to add example code directly to this site, but I will add links to example code or other information as they are provided.
I no longer actively maintain this page. For more information about LCA, see http://www.john-uebersax.com/stat/index.htm.
Nonetheless, if you have additional information about LCA that you would like to see added to this page, please pass it along: KMarkus@aol.com.
Clifford Clogg's MLLSA program reworked for use on a PC is on its way to becoming part of CDAS. Both are available from Scott Eliason. This version of MLLSA has a much improved command-based user interface, making it much easier to use than earlier versions.
Discussed in Hagenarrs (1993). No contact information at this time.
Tamas Rudas's program DISTAN (DIscrete STatistical ANalysis) does a variety of analyses including LCA. DISTAN is written for a DOS environment. It is currently available from ProGAMMA for a fee. Plans are under way to provide a free WWW download site in the future. DISTAN includes a 200+ page manual. Tamas Rudas can be contacted at email@example.com.
LCA software aimed at mixture modeling. Implements methods from Wedel and Kamakura (1999).
"Statistical Innovations will be releasing Latent GOLD, a new software program that represents a
breakthrough in Latent Class/Mixture Modeling. The program is designed by Jeroen Vermunt (LEM program) and Jay Magidson (SPSS CHAID and GOLDMineR). Our website has tutorials and within the next week a downloadable demo program. The site address is www.latentgold.com or www.latentclass.com." (Slightly edited text submitted by Jason Niles, Marketing Manager, Statistical Innovations.)
I do not have a link or contact information for this program.
Jeroen Vermunt's revised version of LEM is can be downloaded from this page. First, click on "Onderzoeksprogramma en publicaties" and then click on "LEM Program Files". Both DOS and Windows versions are available along with a manual and examples. This page is partially in Dutch, but the information about LEM is in English. There is also information about receiving updates about LEM. (I have had occasional reports of difficulties with this site. If you cannot connect successfully, try again at another time of day.)
This new program by Matthias von Davier is the successor to WINMIRA. The program is available for Win95 and includes several new features not available with WINMIRA. A beta demo version of the program is available through the above link.
Bengt and Linda Muthen's sequel to LISCOMP does LCA among many other things. It is available from Statistical Modeling Innovations for a fee.
This is available from ProGAMMA for a fee.
WinLTA is available from Linda Collins through the above link. The Web page also contains introductory information about WinLTA.
A free student version of Matthias von Davier's WINMIRA is available from the above site. It also contains information about purchasing the full version from ProGAMMA. Click on "Availability of WINMIRA" for additional information. See Miracle 32.
Below is a partial listing of books about LCA. (Additional references will be added in time. Suggestions are welcome.) This list is limited to books published in English. Additional literature exists in other languages.
Clogg, C. C. (1995). Latent Class Models. In G. Arminger, C. C. Clogg, & M. E. Sobel (Eds.) Handbook of statistical modeling for the social and behavioral sciences. New York: Plenum.
Clogg, C. C. (1981). Latent class models for measuring. In R. Langeheine & J. Rost (Eds.) Latent trait and latent class models. New York: Plenum.
Hagenaars, J. A. (1993). Loglinear models with latent variables. Sage Publications.
Hagenaars, J. A. &
McCutcheon, A. L. (2002). Applied
latent class analysis. Cambridge, UK: Cambridge
Heinen, T. (1996). Latent class and discrete latent trait models: Similarities and differences. Thousand Oaks: Sage Publications.
Langeheine, R. & Rost, J. (Eds.) (1988). Latent trait and latent class models. New York: Plenum.
Lazarsfeld, P. F. & Henry, N. W. (1968). Latent structure analysis. Boston: Houghton Mifflin.
McCutcheon, A. L. (1987). Latent class analysis. Sage University Paper series on Quantitative Applications in the Social Sciences, series no. 07-064. Beverly Hills: Sage Publications.
Rost, J., & Langeheine, R.
(1997). Applications of latent trait and latent class
the social sciences. Muenster, Germany:
Wedel, M. & Kamakura, W. A. (1999). Market segmentation: Conceptual and methodological foundations. New York: Springer.