Thanks to Kit Baum an update of the -sheafcoef- package is now
available from SSC. The -sheafcoef- package computes so-called
sheaf coefficients (Heise 1972), which is a special case of a
model for causal indicators. If we measure the same concept
multiple times, than we have more information about that
variable, but we need a model that can use this additional
information. There are two types: models for effect indicators,
like factor analysis, which assume that the underlying latent
variable influences the observed indicators, and models for
causal indicators, which assume that the observed indicators
influence the latent variable.
Sheaf coeficients are the simplest variant in this family of
models, and it does not imply a testable constraint. It is
mainly useful for comparing the effects of blocks of variables.
For example, we may have a block of variables describing the
home situation and another block of variables that represent
the work situation and we ask ourselves whehter the home
situation or the worksituation is more important for the
dependent variable. A more complete discussion of this package
can be found here: <http://www.maartenbuis.nl/software/sheafcoef.html>.
This update improved the display of the results and is quicker.
To instal typ in Stata -ssc instal, replace-.
-- Maarten
Heise, David R. (1972). Employing nominal variables, induced variables, and block variables in path analysis. Sociological Methods & Research, 1(2): 147--173.
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://www.maartenbuis.nl
--------------------------
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
