Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Comparing coefficients across sub-samples


From   David Hoaglin <dchoaglin@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Comparing coefficients across sub-samples
Date   Thu, 2 Aug 2012 22:34:48 -0400

James,

The concept underlying "Lisa's formula" is quite basic; you should be
able to find it in almost any introductory book on mathematical
statistics or probability ("variance of a sum or difference [or, more
generally, a linear combination] of independent random variables").
It is not a "big" enough concept to be called a theorem, let alone be
named after someone.  I should be able to dig up a reference if
needed.

The only part of the formula that might need justification is the use
of the estimates for var(B1) and var(B2) and then referring z to a
standard normal distribution.  That step relies on having "large"
samples, but it should be OK, and it is very commonly done.

David Hoaglin

On Thu, Aug 2, 2012 at 9:51 PM, Fitzgerald, James <J.Fitzgerald2@ucc.ie> wrote:
> David,
>
> One final thing; if I use this formula how would I reference or justify my use of it? Is it a basic formula I'd find in an econometrics text, or does it have a specific author, or is it founded on a particular theorem?
>
> Any help you can give is much appreciated
>
> James
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index