I guess you're using Stata 8 and the -dagumfit-
program published by Stephen Jenkins in STB-48
or available on SSC.
As is documented in its help, -dagumfit- leaves
behind estimates of its parameters in global
macros S_b, S_d, S_h. Therefore you can superimpose
a density estimate on a histogram by doing something
like this:
u auto
dagumfit mpg
histogram mpg , plot(function ///
(($S_b*$S_d*$S_h)*x^(-$S_d-1)]/[1 + $S_h*x^(-$S_d))^($S_b+1), ra(mpg))
Stephen will be talking in Berlin on Monday on his work
on income distribution fitting: see
http://www.stata.com/support/meeting/2german/abstracts.html#jenkins
The work now includes 4 parameter distributions. I can't say at what
point all related programs will be made public.
Nick
[email protected]
V�n Tr�nh
> I'd like to impose a dagum fitted curve on my histogram (of an income
> variable). Would you adivise me how to to that please?
>
> To Stepehn and Nick - thanks very much for having written the
> programmes on
> dagumfit and pdagum, qdagum. Have you written a similar
> programme on the 4
> parameter Dagum model at all?
*
* 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/
