Statalist


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

Re: st: AW: Problem with xtivreg2


From   Nils Braakmann <nilsbraakmann@googlemail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: AW: Problem with xtivreg2
Date   Thu, 17 Dec 2009 17:21:29 +0100

Thanks Mark,

the idea to create the variables manually could indeed solve the
problem. I will try that. Thanks. I will also report the results to
the list, which may take some weeks, however, as the research data
center has its well-earned Christmas holiday now. As a sidenote, the
strange thing is that the command worked with L2 (see the first
version where I used first and second lags), but not when I add third
lags. That makes me think that maybe the problem is not with the lags
but with the combination of estimating the equation in first
differences and the -first- option (or this combined with using 2sls).
However, I would be suprised to learn that I am the first person to
estimate a differenced equation with 2sls and want to have a look at
the first stage, so others should have encountered the same problem
before.

Best,
Nils

On Thu, Dec 17, 2009 at 4:17 PM, Schaffer, Mark E <M.E.Schaffer@hw.ac.uk> wrote:
> Nils,
>
> I will have a look at this and see if I can replicate it.  But have you tried the very simple fix of creating the L2 variables as new variables instead of having xtivreg2 do them?
>
> That is, instead of
>
> xtivreg2 `depvar' `indepvars' `exovars' (overall_coeff_var
> overall_coeff_var_sq = L2.overall_coeff_var L2.overall_coeff_var_sq
> L3.overall_coeff_var L3.overall_coeff_var_sq), fd cluster(idnum) first
>
> you do
>
> gen double L2overall_coeff_var=L2.overall_coeff_var
> gen double L2overall_coeff_var_sq=L2.overall_coeff_var_sq
> gen double L3overall_coeff_var=L3.overall_coeff_var
> gen double L3overall_coeff_var_sq=L3.overall_coeff_var_sq
>
> and use these in the estimation command.
>
> Internally, to implement the FD estimator xtivreg2 using the D time-series operator, and it might not be handling the case of D combined with L properly.
>
> Cheers,
> Mark
>
>> -----Original Message-----
>> From: owner-statalist@hsphsun2.harvard.edu
>> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of
>> Nils Braakmann
>> Sent: Thursday, December 17, 2009 1:02 PM
>> To: statalist@hsphsun2.harvard.edu
>> Subject: Re: st: AW: Problem with xtivreg2
>>
>> Nope. In fact,  I would like to avoid having to do this if possible.
>> The code runs in a research data center, which means that all output
>> has to be checked for confidentiality, and I am not sure whether they
>> would allow me to use -trace- (using it obviously increases their work
>> load by a lot). I'll try to recreate the error using data I have on my
>> pc, but I'm not sure if this works. I basically hoped for an easy
>> solution in the spirit of "Your variable name is too long", but if
>> this problem turns out to be more difficult, I'll have to think of
>> something else...
>>
>> Best,
>> Nils
>>
>> On Thu, Dec 17, 2009 at 1:36 PM, Martin Weiss
>> <martin.weiss1@gmx.de> wrote:
>> >
>> > <>
>> >
>> > Have you -trace-d the error yet?
>> >
>> >
>> >
>> > HTH
>> > Martin
>> >
>> >
>> > -----Ursprüngliche Nachricht-----
>> > Von: owner-statalist@hsphsun2.harvard.edu
>> > [mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag
>> von Nils Braakmann
>> > Gesendet: Donnerstag, 17. Dezember 2009 13:27
>> > An: statalist@hsphsun2.harvard.edu
>> > Betreff: st: Problem with xtivreg2
>> >
>> > Dear all,
>> >
>> > I  am just revisiting an old paper (running under version
>> control for
>> > version 9.2 under a version 10.2 maching in a research data center)
>> > and encounter a strange problem with xtivreg2.
>> >
>> > In february I ran the following code:
>> >
>> > xtivreg2 `depvar' `indepvars' `exovars' (overall_coeff_var
>> > overall_coeff_var_sq = L.overall_coeff_var L.overall_coeff_var_sq
>> > L2.overall_coeff_var L2.overall_coeff_var_sq), fd gmm robust
>> >
>> > and got the following results:
>> >
>> > Warning - collinearities detected
>> > Vars dropped:  D.year_d7 D.year_d6 D.year_d5
>> >
>> > FIRST DIFFERENCES ESTIMATION
>> > ----------------------------
>> > Number of groups =      1022                    Obs per group: min =
>> > 1
>> >                                                               avg =
>> > 2.6
>> >                                                               max =
>> > 7
>> >
>> > 2-Step GMM estimation
>> > ---------------------
>> >
>> > Statistics robust to heteroskedasticity
>> >
>> >                                                      Number of obs =
>> > 2627
>> >                                                      F( 24,  2602) =
>> > 4.62
>> >                                                      Prob > F      =
>> > 0.0000
>> > Total (centered) SS     =  113.3549125
>> Centered R2   =
>> > -0.0026
>> > Total (uncentered) SS   =    113.83846
>> Uncentered R2 =
>> > 0.0017
>> > Residual SS             =  113.6464909                Root
>> MSE      =
>> > .208
>> >
>> >
>> --------------------------------------------------------------
>> --------------
>> > --
>> >             |               Robust
>> > D.           |
>> > log_return~d |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
>> > Interval]
>> >
>> -------------+------------------------------------------------
>> --------------
>> > --
>> > overall_co~q |
>> >         D1. |   6.448465   5.537348     1.16   0.244    -4.404538
>> > 17.30147
>> > overall_co~r |
>> >         D1. |  -4.672704    3.66052    -1.28   0.202    -11.84719
>> > 2.501784
>> >    year_d13 |
>> >         D1. |   .1064509   .1903947     0.56   0.576    -.2667159
>> > .4796177
>> >    year_d12 |
>> >         D1. |   .0660634   .1644337     0.40   0.688    -.2562208
>> > .3883475
>> >    year_d11 |
>> >         D1. |    .085434   .1305051     0.65   0.513    -.1703513
>> > .3412193
>> >    year_d10 |
>> >         D1. |   .0852973   .0898904     0.95   0.343    -.0908845
>> > .2614792
>> >     year_d9 |
>> >         D1. |    .053293   .0615972     0.87   0.387    -.0674353
>> > .1740213
>> >     year_d8 |
>> >         D1. |   .0145953   .0313659     0.47   0.642    -.0468806
>> > .0760713
>> > work_council |
>> >         D1. |   .0044819   .0428912     0.10   0.917    -.0795833
>> > .0885471
>> > bargain_firm |
>> >         D1. |  -.0117102    .022009    -0.53   0.595     -.054847
>> > .0314266
>> > bargain_br~h |
>> >         D1. |   .0176108   .0160317     1.10   0.272    -.0138109
>> > .0490324
>> >  share_women |
>> >         D1. |  -.3123268   .3655674    -0.85   0.393    -1.028826
>> > .4041721
>> >  invest_head |
>> >         D1. |   3.60e-07   3.37e-07     1.07   0.286    -3.02e-07
>> > 1.02e-06
>> > share_acad~c |
>> >         D1. |  -.1039652   .6003136    -0.17   0.863    -1.280558
>> > 1.072628
>> >  share_other |
>> >         D1. |  -.6331339   .5519297    -1.15   0.251    -1.714896
>> > .4486285
>> > share_whit~l |
>> >         D1. |   .2077333   .4054792     0.51   0.608    -.5869912
>> > 1.002458
>> > share_unsk~d |
>> >         D1. |  -.5069874   .2573503    -1.97   0.049    -1.011385
>> > -.00259
>> >  share_azubi |
>> >         D1. |  -.4534471   1.215144    -0.37   0.709    -2.835085
>> > 1.928191
>> >  share_age50 |
>> >         D1. |   .1681527   .3965507     0.42   0.672    -.6090725
>> > .9453778
>> > share_a~4050 |
>> >         D1. |   .2137222   .3380754     0.63   0.527    -.4488933
>> > .8763378
>> >  share_age30 |
>> >         D1. |  -.3064232   .4795452    -0.64   0.523    -1.246315
>> > .6334681
>> >  firmsize_sq |
>> >         D1. |   3.84e-08   1.06e-08     3.61   0.000     1.76e-08
>> > 5.91e-08
>> >    firmsize |
>> >         D1. |  -.0005478   .0001474    -3.72   0.000    -.0008367
>> > -.0002589
>> >    avg_wage |
>> >         D1. |   .0032925   .0037199     0.89   0.376    -.0039983
>> > .0105834
>> >       _cons |   -.003982   .0268464    -0.15   0.882       -.0566
>> > .048636
>> >
>> --------------------------------------------------------------
>> --------------
>> > --
>> > Anderson canon. corr. LR statistic (underidentification test):
>> > 108.788
>> >                                                   Chi-sq(3) P-val =
>> > 0.0000
>> > Test statistic(s) not robust
>> >
>> --------------------------------------------------------------
>> --------------
>> > --
>> > Cragg-Donald F statistic (weak identification test):
>> > 27.483
>> > Stock-Yogo weak ID test critical values:  5% maximal IV
>> relative bias
>> > 11.04
>> >                                         10% maximal IV relative bias
>> > 7.56
>> >                                         20% maximal IV relative bias
>> > 5.57
>> >                                         30% maximal IV relative bias
>> > 4.73
>> >                                         10% maximal IV size
>> > 16.87
>> >                                         15% maximal IV size
>> > 9.93
>> >                                         20% maximal IV size
>> > 7.54
>> >                                         25% maximal IV size
>> > 6.28
>> > Test statistic(s) not robust
>> > Source: Stock-Yogo (2005).  Reproduced by permission.
>> >
>> --------------------------------------------------------------
>> --------------
>> > --
>> > Hansen J statistic (overidentification test of all instruments):
>> > 1.761
>> >                                                   Chi-sq(2) P-val =
>> > 0.4147
>> >
>> --------------------------------------------------------------
>> --------------
>> > --
>> > Instrumented:         D.overall_coeff_var_sq D.overall_coeff_var
>> > Included instruments: D.year_d13 D.year_d12 D.year_d11
>> D.year_d10 D.year_d9
>> >                      D.year_d8 D.work_council D.bargain_firm
>> > D.bargain_branch
>> >                      D.share_women D.invest_head D.share_academic
>> > D.share_other
>> >                      D.share_whitecol D.share_unskilled
>> D.share_azubi
>> >                      D.share_age50 D.share_age4050 D.share_age30
>> > D.firmsize_sq
>> >                      D.firmsize D.avg_wage
>> > Excluded instruments: L2D.overall_coeff_var_sq L2D.overall_coeff_var
>> >                      LD.overall_coeff_var_sq LD.overall_coeff_var
>> > Dropped collinear:    D.year_d7 D.year_d6 D.year_d5
>> >
>> --------------------------------------------------------------
>> --------------
>> > --
>> >
>> >
>> >
>> > Some days ago, I changed the instruments from lagged first
>> and second
>> > differences to lagged second and third differences, gmm to 2sls and
>> > added clustered standard errors and the option -first- to
>> have a look
>> > at the first stage results. In other words, I ran the
>> following code:
>> > xtivreg2 `depvar' `indepvars' `exovars' (overall_coeff_var
>> > overall_coeff_var_sq = L2.overall_coeff_var L2.overall_coeff_var_sq
>> > L3.overall_coeff_var L3.overall_coeff_var_sq), fd
>> cluster(idnum) first
>> >
>> > This time I get an error message:
>> >
>> > D.overall_coeff_v invalid name
>> > r(198); t=8.63 11:10:53
>> >
>> > As far as I know neither the Stata Version, nor the dataset
>> used have
>> > been changed in the meantime. SAme applies to the macros
>> used for the
>> > dependent and independent variables.
>> >
>> > I'd greatly appreciate any input on this issue as I am a bit (well,
>> > really) lost at present.
>> >
>> > Best,
>> > Nils
>> > *
>> > *   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/
>>
>
>
> --
> Heriot-Watt University is a Scottish charity
> registered under charity number SC000278.
>
>
> *
> *   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   |   What's new   |   Site index