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, statalist.org is already up and running.


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

RE: st: strong instruments


From   Cameron McIntosh <cnm100@hotmail.com>
To   STATA LIST <statalist@hsphsun2.harvard.edu>
Subject   RE: st: strong instruments
Date   Mon, 7 Nov 2011 22:31:29 -0500

It shouldn't be too difficult -- those would just be instruments that have high correlations with the endogenous regressors.
Murray, M.P. (2006). Avoiding Invalid Instruments and Coping with Weak Instruments. Journal of Economic Perspectives, 20(4), 111-132.http://www.eui.eu/Personal/Guiso/Courses/Econometrics/Murray_IV_jep_06.pdf
But you say you did not get significant results with 2SLS or ivreg2... perhaps when you use the simultaneous equation approach you may be observing suppression effects. How do the the path coefficients compare to the zero-order correlations?
Shieh, G. (2006). Suppression situations in multiple linear regression. Educational and Psychological Measurement, 66(3), 435-447.
Maassen, G.H., & Bakker, A.B. (2001). Suppressor variables in path models: definitions and interpretations. Sociological Methods & Research, 30(2), 241-270.http://www.beanmanaged.eu/pdf/articles/arnoldbakker/article_arnold_bakker_64.pdf
Cam
> From: donsaane@yahoo.fr
> To: statalist@hsphsun2.harvard.edu
> Subject: st: strong instruments
> Date: Mon, 7 Nov 2011 21:06:13 -0500
> 
> I'm running a 3sls model (I tried ivreg2 or 2sls, and I didn't get
> significant results) , and I wondering if my instruments are strong. Can we
> just see it with the output results? 
> as example: pdvavg4 is an instrument for j30f. we see that pdvavg4 is
> significant. It is enough to say that pdvavg4 is a strong instrument?
> thanks
> 
> reg3 (emploi: emploi = j30f j30b) (j30b = taxeavg4 b5 a2 b2a b2b
> b2c a4a a7 a6a  ) (j30f = pdvavg4 b5 a2
> b2a b2b b2c a4a a7 a6
> > a)
>  
> Three-stage least-squares regression
> ----------------------------------------------------------------------
> Equation          Obs  Parms        RMSE    "R-sq"       chi2        P
> ----------------------------------------------------------------------
> emploi            131      2    .4052919   -0.1658       3.45   0.1784
> j30b              131      8    .9394929    0.2112      37.17   0.0000
> j30f              131      8    .9930078    0.2500      45.75   0.0000
> ----------------------------------------------------------------------
>  
> ----------------------------------------------------------------------------
> --
>              |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
> Interval]
> -------------+--------------------------------------------------------------
> --
> emploi       |
>         j30f |  -.0895928   .0645908    -1.39   0.165    -.2161883
> .0370028
>         j30b |   .1245075   .0755103     1.65   0.099      -.02349
> .272505
>        _cons |   .0341791   .2257434     0.15   0.880    -.4082698
> .4766279
> -------------+--------------------------------------------------------------
> --
> j30b         |
>     taxeavg4 |   .9566036   .1901856     5.03   0.000     .5838467
> 1.32936
>           b5 |    .011787   .0073776     1.60   0.110    -.0026729
> .0262469
>           a2 |   -.004885     .15014    -0.03   0.974     -.299154
> .289384
>          b2a |   .0032782   .0052013     0.63   0.529    -.0069162
> .0134726
>          b2b |    .004151   .0063073     0.66   0.510     -.008211
> .016513
>          b2c |  -.0580875   .0315122    -1.84   0.065    -.1198504
> .0036753
>          a4a |  -.0025426   .0044695    -0.57   0.569    -.0113026
> .0062174
>           a7 |   .0132198   .2282933     0.06   0.954    -.4342267
> .4606664
>          a6a |  (omitted)
>        _cons |  -23.56414   14.58883    -1.62   0.106    -52.15771
> 5.02944
> -------------+--------------------------------------------------------------
> --
> j30f         |
>      pdvavg4 |   .9825736   .1833886     5.36   0.000     .6231387
> 1.342009
>           b5 |  -.0090748   .0077313    -1.17   0.240    -.0242279
> .0060782
>           a2 |  -.0717486   .1705269    -0.42   0.674    -.4059751
> .2624778
>          b2a |  -.0106844   .0054099    -1.97   0.048    -.0212877
> -.0000812
>          b2b |  -.0118935   .0065061    -1.83   0.068    -.0246453
> .0008583
>          b2c |   -.109557   .0328635    -3.33   0.001    -.1739684
> -.0451457
>          a4a |  -.0003704    .004611    -0.08   0.936    -.0094079
> .0086671
>           a7 |   .1681194    .237539     0.71   0.479    -.2974484
> .6336873
>          a6a |  (omitted)
>        _cons |   19.01283   15.26012     1.25   0.213    -10.89645
> 48.92212
> ----------------------------------------------------------------------------
> --
> Endogenous variables:  emploi j30b j30f 
> Exogenous variables:   taxeavg4 b5 a2 b2a b2b b2c a4a a7 a6a pdvavg4
> ---------------------------------------
> 
> 
> *
> *   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index