Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: Panel data newey-west test statistic


From   Anika Duggal <anikad17@hotmail.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: Panel data newey-west test statistic
Date   Tue, 24 Jan 2012 15:50:12 +0000

Dear all,

PLEASE PLEASE PLEASE help me!!

I have taught myself panel data, so I am not really sure what I am doing.

I am estimating a fixed period and fixed time effects unbalanced panel model and i have detected heteroskedasticity, but I also think I have some form of correlation as my DW statistic was quite low, but critical values are not availiable so I can't be sure.

For ease, I was wondering if there is any way, shape or form that I can calculate Newey-West robust errors to take account for both effects in panel data? I saw that it was listed under time-series options, but then I will have to declare my data as time series rather than panel and I don't know what effect that would have.

I think that if I change my method or estimator now, I will just end up confusing myself more and applying this sorts out both of my problems.

If STATA don't have a method, is there any laymans way of explaining how I can calculate these standard errors by hand?
I am not very comfortable using white standard errors know I know about how they are wrong if correlation is present


Many thanks,

Nikki


*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index