Thanks to Kit Baum an update of the -hangroot- package
is now available on SSC. -hangroot- will produce a
graph comparing an empirical distribution to a
theoretical distribution. This is done by "hanging" the
histogram bars from the empirical distribution from the
theoretical distribution. This way the deviations from
the theoretical distribution are represented by the
deviations from the horizontal line at y=0, which
makes it easier to spot any patterns in these
deviations. Moreover, the frequencies are plotted on
the square root scale, which will make deviations in
the tails more visable. Examples can be found here: http://www.maartenbuis.nl/software/hangroot.html
As promised in a post to the Statalist yesterday, I
added in this update the Chi square distribution
and added the option to specify the values of the
parameters of the theoretical distribution.
Previously, -hangroot- only used estimated parameters.
This new option can be useful when using -hangroot-
to display results from a simulation, where not only
the distribution a variable should follow is known,
but also the parameters of that distribution.
To install it type in Stata -ssc install hangroot-,
and to up-date type in Stata:
-ssc install hangroot, replace- or -adoupdate, update-
-- Maarten
--------------------------
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/
