Statalist The Stata Listserver

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

Re: st: Two Stata questions

From   Richard Goldstein <>
Subject   Re: st: Two Stata questions
Date   Tue, 31 Jan 2006 14:47:23 -0500

1. use -egen- with the cut option

2. robust reports Huber-White t-statistics; cluster takes this
to another level when you have clustered data; what is N when
one has clustered data?  That is, I think, the reason, why there
is no adjusted R2 and is also the reason not to use the adjusted
R2 from regress without the cluster option


Krishna R. Kumar wrote:

I am new to Stata. I have two questions.

The first relates to data management. I would like to create categorical variables by partitioning a continuous variable into two or more equal size groups, i.e. groups with equal number of observations. In SAS, PROC RANKS does this quite easily with the "groups" option. Is there a way to do such a transformation with Stata. "autocode" partitions at pre-set cut-offs but that would require figuring out the median first and then inserting it as a cutoff into "autocode."

The second relates to the "cluster" option of the "regress" command. This produces Huber-White t-stats. A by-product is that the log does not include an adjusted R-square. Can someone tell me why? Also, is there anything wrong with obtaining the adjusted R-square by running "regress" without the "cluster" option and reporting it alongside the Huber-White t-statistics?

Thanks in advance.

Krishna Kumar

Krishna R. Kumar, Ph. D.
Professor of Accountancy
School of Business GOV 406
The George Washington University
Washington DC 20052
Ph (202) 994-5976
Fax (202) 994-5164 *

*   For searches and help try:

© Copyright 1996–2021 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index