Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: package -hangroot- revised on SSC
From
Maarten Buis <[email protected]>
To
[email protected]
Subject
st: package -hangroot- revised on SSC
Date
Wed, 18 May 2011 18:20:29 +0200
Thanks to Kit Baum a new version of the -hangroot- package is now
available from SSC. To install type either -ssc install hangroot,
replace- or -adoupdate, update-.
-hangroot- creates graphs that compare the distribution of a variable
with a theoretical distribution (e.g. a normal/Gaussian distribution).
It is an improvement on a histogram with a normal curve superimposed
on it. By "hanging" the bars from the theoretical distribution, the
deviations from that distribution are now the deviations from the
horizontal x-axis, which makes it much easier to spot patterns in
these deviations. Moreover, large bars (i.e. large counts) tend to be
more variable than small bars (small counts), making them hard to
compare. By plotting on a square root scale the variances across the
different bars tend to become more similar, again helping to find
patterns in the deviations from the theoretical distribution. Several
examples of these graphs can be found here:
http://www.maartenbuis.nl/software/hangroot.html
I made the following changes:
o I added the logistic distribution as one of the theoretical
distributions with which a variable can be compared. The logistic
distribution is a symmetric bell-shaped distribution that is a bit
more peaked than a normal/Gaussian distribution.
o -hangroot- can be used after various distribution fitting programs
available from SSC, like -betafit- and -gammafit-. This new version of
-hangroot- can now be used with the new alternative parameterization
in -gammafit- that also became available today.
o I improved the algorithm for finding estimates of the gamma
distribution when not using -hangroot- after -gammafit-.
o I fixed a bug when using -hangroot- after -betafit- when the
-alternative- option was specified in -betafit-.
I hope some of you will find these graphs as awesome as I do ;)
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/