# Re: st: Newey estimations

 From "Clive Nicholas" To statalist@hsphsun2.harvard.edu Subject Re: st: Newey estimations Date Thu, 3 Aug 2006 00:51:30 +0100 (BST)

```Evelyn Colino de Cantero wrote:

[...]

> Does somebody knows what is the exactly procedure Stata
> follows to test parameters under linear reg. with Newey-West
> std. errors estimators?

Why use a wimpish, water-pistol version of OLS Newey-West in Stata when
you can use a OLS Newey-West package that's chock-full with AK47s, Desert
Eagles and Kalashnikovs? An example:

. webuse grunfeld

. ivreg2 invest mvalue kstock, bw(2) robust small

OLS regression with robust standard errors
------------------------------------------
Heteroskedasticity and autocorrelation-consistent statistics
kernel=Bartlett; bandwidth=2
time variable (t):  year
group variable (i): company

Number of obs =      200
F(  2,   197) =   113.16
Prob > F      =   0.0000
Total (centered) SS     =  9359943.917              Centered R2   =   0.8124
Total (uncentered) SS   =  13620706.07              Uncentered R2 =   0.8711
Residual SS             =  1755850.432              Root MSE      =    94.41
----------------------------------------------------------------------------
|               Robust
invest |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-----------+----------------------------------------------------------------
mvalue |   .1155622   .0085916    13.45   0.000     .0986189    .1325054
kstock |   .2306785    .058479     3.94   0.000     .1153533    .3460037
_cons |  -42.71437   14.04683    -3.04   0.003    -70.41583   -15.01291
----------------------------------------------------------------------------

. ivreg2 invest mvalue kstock time, bw(2) robust small

OLS regression with robust standard errors
------------------------------------------
Heteroskedasticity and autocorrelation-consistent statistics
kernel=Bartlett; bandwidth=2
time variable (t):  year
group variable (i): company

Number of obs =      200
F(  3,   196) =    79.84
Prob > F      =   0.0000
Total (centered) SS     =  9359943.917              Centered R2   =   0.8127
Total (uncentered) SS   =  13620706.07              Uncentered R2 =   0.8713
Residual SS             =   1753085.77              Root MSE      =    94.57
----------------------------------------------------------------------------
|               Robust
invest |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-----------+----------------------------------------------------------------
mvalue |   .1163783   .0085026    13.69   0.000     .0996099    .1331467
kstock |   .2213351   .0667831     3.31   0.001     .0896294    .3530408
time |   .7737904   1.782941     0.43   0.665    -2.742421    4.290002
_cons |  -49.14306   15.96811    -3.08   0.002    -80.63443   -17.65169
----------------------------------------------------------------------------

> Is still valid to use the "test" command for this pourpose?

Yes:

. test time

( 1)  time = 0

F(  1,   196) =    0.19
Prob > F =    0.6648

All of which is to say, download -ivreg2- from SSC. The -bw(2)- option is
Newey-West.

Hope all that helps. :)

CLIVE NICHOLAS        |t: 0(044)7903 397793
Politics              |e: clive.nicholas@ncl.ac.uk
Newcastle University  |http://www.ncl.ac.uk/geps

Whereever you go and whatever you do, just remember this. No matter how
many like you, admire you, love you or adore you, the number of people
turning up to your funeral will be largely determined by local weather
conditions.

*
*   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/
```