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, is already up and running.

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

RE: st: RE: mvreg with vce(robust)?

From   "Nick Cox" <>
To   <>
Subject   RE: st: RE: mvreg with vce(robust)?
Date   Mon, 12 Jul 2010 14:43:13 +0100

I don't think -mvreg- can do this. I can't see any sign that -mvreg- uses Mata, so I don't know what to make of your speculation. I guess that you must do these regressions separately. 


Peter Velte

The issue is as follows: -mvreg- runs much faster on an 8-core server than a loop of -reg- while generating the same results in my case (balanced panel). I assume that is due to the superior parallelization of the Mata code used in -mvreg-. The only difference is that -mvreg- cannot compute heteroskedasticity robust standard errors.

In practical terms assume the following multiple-equation regression:

mvreg portfolio1 portfolio2 portfolio3 = rmrf smb hml mom

Now, instead of ordinary standard errors I want to compute heteroskedasticity robust standard errors for each of the three regressions
portfolio1 = rmrf smb hml mom
portfolio2 = rmrf smb hml mom
portfolio3 = rmrf smb hml mom

Hope that clarifies my question.

"Nick Cox" <>

> Two short answers: 
> 1. In general, hidden options are rare in commands like -mvreg-. If an
> option isn't documented, it usually doesn't exist. 
> 2. What would that look like, theoretically or practically, given that
> -mvreg- is specifically for several dependent variables? 

Peter Velte
> is there a way to perform mvreg with Newey-West-heteroskedasticity-robust
> standard errors?

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index