[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: how to simulate an arbitrary distribution

From   "Joseph Coveney" <>
To   "Statalist" <>
Subject   Re: st: how to simulate an arbitrary distribution
Date   Fri, 4 Apr 2008 22:38:06 +0900

Jeph Herrin wrote:

This must have been addressed here before, but I can't
find it.

I have a dataset of 1500 observations, each with an
identifier and a -y- value. -y- is highly skewed, and
nothing I've tried seems to normalize it.

I'd like to simulate the distribution of -y-. Is there
a reasonable way to do this if I can't find a transform
of it that looks like a standard distribution?


Take a look at -jnsn- and -jnsw- for getting estimates of the parameters
that characterize y's distribution, and then feed these values into -ajv- to
stimulate y's distribution.

All three are bundled in the same package on SSC (-findit jnsn-).

Joseph Coveney

jnsn from
 'JNSN': module to fit Johnson distributions / jnsn comprises four commands
 that collectively fit parameters of / Johnson distributions by two methods
 (moment matching and / quantiles), transform a variable into a quasinormal
 deviate / after fitting Johnson distribution parameter estimates, and /

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index