Statalist The Stata Listserver


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

st: RE: Finding missing distribution tail and description of the histogram fitted normal curve


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Finding missing distribution tail and description of the histogram fitted normal curve
Date   Fri, 31 Mar 2006 12:30:43 +0100

This is, as I understand it, the problem tackled by -truncreg-, 
except I think you need Harry Potter (and preferably Hermione
too) to help you recover the individual unknown values. 

Note that you do not need predictors (covariates, independent
variables, explanatory variables, regressors, endogenous 
variables, carriers, ...). 

Nick 
n.j.cox@durham.ac.uk 

Fotios Drenos
 
> I have a series of observations that produce a positively skewed 
> distribution.  There is reason to believe that the distribution is 
> normal but the points describing the left tail are missing.  Using a 
> histogram and a normal curve on that seems to be able to give an 
> approximate solution but I can't find a way to obtain the mean and 
> standard deviation of this fitted distribution.  Does anyone know how 
> to obtain those through Stata?  A further complication is that the 
> observations are frequency weighed and they are very few, below 10 
> observations in total.  Any other ideas of how I can find what the 
> expected points in the left tail will be?

*
*   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/



© Copyright 1996–2020 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index