Patrick W�hrle Guimar�es--
Looking briefly around in Stata, I have not seen an estimator for the
parameters of a power law distribution, and I can see how it might be
hard to write one that you had faith in, since some power
law-distributed variables have no finite mean or variance. Perhaps
you could instead specify the distribution as lognormal? This paper
discusses these two related families of distributions:
http://stat-www.berkeley.edu/users/aldous/Networks/1089229510.pdf
Does anyone on the list know of a method to test whether a lognormal
or power-law distribution fits the data better? It seems like such a
method would have broad applicability to some of the arguments in that
paper...
On 3/4/07, Patrick W�hrle Guimar�es <[email protected]> wrote:
I would like to estimate a power law (or Pareto distribution) for a
large dateset with complex design (income distribution) using
pseudo-log likelihood estimators. I tried to check if there is a
do-file for estimating Power law but i didnt find. Is there anybody
that did this for a large dataset with complex design? Best regards...
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
