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

st: Re: obtaining bootstrapped variance covariance matrix using version 6


From   "Michael Blasnik" <[email protected]>
To   <[email protected]>
Subject   st: Re: obtaining bootstrapped variance covariance matrix using version 6
Date   Mon, 21 Jun 2004 08:29:11 -0400

You can get a bootstrapped version of V by using the saving() option of
bootstrap, use the dataset of replications and then calculate the covariance
matrix on the coefficients:

corr b_* , cov


or:

mat accum myV= b_* , deviation nocons
mat myV=myV/(`r(N)'-1)


The e(V) you get at the end of bootstrap is what's left over from the last
ressample.

Michael Blasnik
[email protected]

----- Original Message ----- 
From: <[email protected]>
To: <[email protected]>
Sent: Sunday, June 20, 2004 5:08 PM
Subject: st: obtaining bootstrapped variance covariance matrix using version
6


> Hi.  I am using the bstrap command in version 6 to obtain bootstrapped
> standard errors.  However, I wish to obtain the entire bootstrapped
> variance covariance matrix.  After the bstrap command I typed matrix V =
> e(V) and then matrix list V, but the matrix I get does not appear to be
the
> correct one (the square root of the variances in this matrix do not give
me
> the bootstrapped standard errors).  I'd appreciate any advice on this.
> Thank you!
>
>
> Charlene M. Kalenkoski, Ph.D.
> Ohio University
> Department of Economics
> Bentley Annex 351
> Athens, OH  45701
>
> Phone:  (740) 593-2022
> Fax:  (740) 593-0181


*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index