Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Why does TRUNCREG cannot find the MLE estimate?

From   dave fournier <>
Subject   st: RE: Why does TRUNCREG cannot find the MLE estimate?
Date   Fri, 09 Sep 2005 08:03:29 -0700

  > -----Original Message-----
  > From: [mailto:owner-
  >] On Behalf Of Li, Shaling (lis1)
  > Sent: Saturday, September 03, 2005 4:01 PM
  > To:
  > Subject: st: Why does TRUNCREG cannot find the MLE estimate?
  > Dear Statalist members,
  > I use TRUNCREG command to run regression with truncated sample. My
  > regression is to regress return on deps, a bivariate regression.
Return is
  > right-skewed with a fat tail and deps is left-skewed also with a fat
  > Model: Return = a+ b*deps + error ;
  > Truncation point: return = 0;
  > My command is "truncreg return deps, ll(0)" and "truncreg return deps,
  > ul(0)"
  > For the right-truncated sample, it works well and produce the same
  > as I could get from SAS. But for the left-truncated sample, STATA shows
  > that it "could not calculate numerical derivatives, missing values
  > encountered" (showed below). SAS also fails to generate any stable
  > for the left-truncated sample (either fail to generate a result as does
  > STATA, or generate random results


I you can't fit the left truncated sample with STATA or SAS I
suggest you try the little truncated regression example program
on the AD Model Builder website. ADMB uses exact derivatives calculated
by automatic differentiation techniques. This makes it very stable
numerically. You can find the TRUNCREG example on the page


Please let me know if you find it useful.


David A. Fournier
P.O. Box 2040,
Sidney, B.C. V8l 3s3

Internal Virus Database is out-of-date.
Checked by AVG Anti-Virus.
Version: 7.0.300 / Virus Database: 267.10.18 - Release Date: 8/31/05

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index