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]
RE: st: RE: Blown up IV coefficient
From
"Wooldridge, Jeffrey" <[email protected]>
To
<[email protected]>
Subject
RE: st: RE: Blown up IV coefficient
Date
Wed, 9 Mar 2011 13:32:34 -0500
No, sorry. You of course had it right. That's what I get for copying and pasting and not editing very well.
I suspected rank would not be statistically significant. Seems hard to justify IV in that case.
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Shikha Sinha
Sent: Wednesday, March 09, 2011 1:25 PM
To: [email protected]
Subject: Re: st: RE: Blown up IV coefficient
Jeff, thanks.
Should the reduced-form also include the dependent variable
(agr_share) as mentioned by you?
areg roaddum rank ims_hab_pop, absorb(dcode) robust
Sign on rank is expected, but it is statistically insignificant...
Thanks,
Shikha
On Wed, Mar 9, 2011 at 12:24 PM, Wooldridge, Jeffrey <[email protected]> wrote:
> For the IV estimates to be at all convincing, first run the reduced
> form,
>
> areg roaddum rank agr_share ims_hab_pop, absorb(dcode) robust
>
> and look at the sign of the coefficient on rank and its t statistic.
> Hopefully you have a predicted sign for the effect of rank on roaddum.
> If the sign is what you expect, is rank strongly statistically
> significant? The statistics for weak identification provide this
> information, too, but you should estimate the reduced form, anyway. It
> is easier to see what is happening.
>
> My guess is the instrument is weak. Or, the IV could actually be
> endogenous (which cannot be tested, unfortunately).
>
> Jeff
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Shikha Sinha
> Sent: Wednesday, March 09, 2011 12:17 PM
> To: [email protected]
> Subject: st: Blown up IV coefficient
>
> Dear all,
>
> I am estimating an instrumental variable model by using -ivreg2 in
> Stata. The IV estimates are way more than OLS estimate (4.006567).
> Could you advise what could be possible reasons for such a blown up IV
> coeff (49.97424 )? or my interpretation of coeff is incorrect.
>
> areg agr_share roaddum ims_hab_pop, robust absorb(dcode)
>
> Linear regression, absorbing indicators Number of obs =
> 266
> F( 2, 250) =
> 0.66
> Prob > F =
> 0.5182
> R-squared =
> 0.0680
> Adj R-squared =
> 0.0121
> Root MSE =
> 26.294
>
> ------------------------------------------------------------------------
> ------
> | Robust
> agr_share | Coef. Std. Err. t P>|t| [95% Conf.
> Interval]
> -------------+----------------------------------------------------------
> ------
> roaddum | 4.006567 3.572553 1.12 0.263 -3.02957
> 11.0427
> ims_hab_pop | .001926 .0344155 0.06 0.955 -.0658552
> .0697071
> _cons | 34.78717 36.38659 0.96 0.340 -36.87615
> 106.4505
> -------------+----------------------------------------------------------
> ------
> dcode | absorbed (14
> categories)
>
> . xi: ivreg2 agr_share ims_hab_pop i.dcode (roaddum=rank), robust
> i.dcode _Idcode_1-14 (_Idcode_1 for dcode==UP09
> omitted)
>
> IV (2SLS) estimation
> --------------------
>
> Estimates efficient for homoskedasticity only
> Statistics robust to heteroskedasticity
>
> Number of obs =
> 266
> F( 15, 250) =
> 0.88
> Prob > F =
> 0.5891
> Total (centered) SS = 185457.6241 Centered R2 =
> -0.5185
> Total (uncentered) SS = 590824 Uncentered R2 =
> 0.5233
> Residual SS = 281625.775 Root MSE =
> 32.54
>
> ------------------------------------------------------------------------
> ------
> | Robust
> agr_share | Coef. Std. Err. z P>|z| [95% Conf.
> Interval]
> -------------+----------------------------------------------------------
> ------
> roaddum | 49.97424 35.09856 1.42 0.154 -18.81768
> 118.7662
> ims_hab_pop | -.0354515 .0511597 -0.69 0.488 -.1357226
> .0648196
> _Idcode_2 | -39.0505 25.58464 -1.53 0.127 -89.19546
> 11.09446
> _Idcode_3 | -41.62481 26.03165 -1.60 0.110 -92.64591
> 9.396298
> _Idcode_4 | -16.54727 20.19038 -0.82 0.412 -56.11968
> 23.02513
> _Idcode_5 | -41.45807 29.51111 -1.40 0.160 -99.29878
> 16.38264
> _Idcode_6 | -32.93124 16.32568 -2.02 0.044 -64.929
> -.9334909
> _Idcode_7 | -8.880318 13.20529 -0.67 0.501 -34.76221
> 17.00157
> _Idcode_8 | -44.38007 24.23395 -1.83 0.067 -91.87774
> 3.117595
> _Idcode_9 | -44.81575 24.87717 -1.80 0.072 -93.57409
> 3.942605
> _Idcode_10 | -21.14303 12.84912 -1.65 0.100 -46.32684
> 4.040777
> _Idcode_11 | -22.56438 9.922245 -2.27 0.023 -42.01162
> -3.117138
> _Idcode_12 | -12.55903 12.52187 -1.00 0.316 -37.10144
> 11.98338
> _Idcode_13 | -14.25003 9.233117 -1.54 0.123 -32.34661
> 3.846547
> _Idcode_14 | -26.27491 11.42556 -2.30 0.021 -48.66859
> -3.881229
> _cons | 74.88709 53.28162 1.41 0.160 -29.54296
> 179.3171
> ------------------------------------------------------------------------
> ------
> Underidentification test (Kleibergen-Paap rk LM statistic):
> 1.825
> Chi-sq(1) P-val =
> 0.1767
> ------------------------------------------------------------------------
> ------
> Weak identification test (Cragg-Donald Wald F statistic):
> 2.977
> (Kleibergen-Paap rk Wald F statistic):
> 2.488
> Stock-Yogo weak ID test critical values: 10% maximal IV size
> 16.38
> 15% maximal IV size
> 8.96
> 20% maximal IV size
> 6.66
> 25% maximal IV size
> 5.53
> Source: Stock-Yogo (2005). Reproduced by permission.
> NB: Critical values are for Cragg-Donald F statistic and i.i.d. errors.
> ------------------------------------------------------------------------
> ------
> Hansen J statistic (overidentification test of all instruments):
> 0.000
> (equation exactly
> identified)
> ------------------------------------------------------------------------
> ------
> Instrumented: roaddum
> Included instruments: ims_hab_pop _Idcode_2 _Idcode_3 _Idcode_4
> _Idcode_5
> _Idcode_6 _Idcode_7 _Idcode_8 _Idcode_9 _Idcode_10
> _Idcode_11 _Idcode_12 _Idcode_13 _Idcode_14
> Excluded instruments: rank
> ------------------------------------------------------------------------
> ------
>
> Thanks,
> Shikha
> *
> * 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/
>
> *
> * 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/
>
*
* 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/
*
* 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/