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

Re: st: qreg SEs

From   Ricardo Ovaldia <>
Subject   Re: st: qreg SEs
Date   Wed, 26 Feb 2003 14:58:27 -0800 (PST)

--- Shinkyu Yang <> first wrote
that the way Stata computes SE was incorrect:

> As far as I know, qreq does not produce the right
> SEs. There are several ways to construct standard 
> error.  I will tell further if you cannot find ways
> to construct SEs.

Frank Eaton <> ask for more

> Please do tell me more, thank you!

--- Shinkyu Yang <> then wrote:
> As others already mentioned, Reference qreg part
> explains bootstrap
> method to construct SEs. My experience told me that
> the  Stata's SEs
> were hardly correct.

This is NOT satisfactory, Shinkyu Yang, you stated
that Stata's SE are wrong but do not provide any
supporting evidence. This leaves us, who routinely use
-qreg-, wandering if you are correct and Stata is
wrong or what? If Stata is computing incorrect SE, I
and I'm sure Stata, would want to know this.

I think that is a terrible disservice to Stata and
users to state on this list that something is computed
incorrectly without providing adequate evidence.


Ricardo Ovaldia, MS
Oklahoma City, OK

Do you Yahoo!?
Yahoo! Tax Center - forms, calculators, tips, more
*   For searches and help try:

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