This page contains two SAS programs that were used for the example in the paper: Li, R., and Wall, M.M. (2002) "A Comparison of Multiple Regression to Two Latent Variable Techniques for Estimation and Prediction", Research Report No. 2002-004, Division of Biostatistics, University of Minnesota.

The example was interested in the relationship between county level mortality rates due to respiratory disease and 5 variables collected at the county level by the census
EDUHS- percent in county with high school education
MEDHHIN - median house hold income (in dollars)
PERCAPIT - per capita income (in dollars)
PUBWATER - percent of households with access to public water
WOOD - percent of household using wood to heat the home
The variable RESP is the log of the age-adjusted respiratory disease death rate

mnfsmethod.sas This program uses the factor score method to fit the data
mnsemmethod.sas This program uses structural equation modeling to fit the data