Antonio,
Quoting Antonio Rodrigues Andres <[email protected]>:
> Here is the do file, but still i did not succeed
I think what you posted demonstrates that my guess was correct.
Consider observations 6 and 7 for country 1. The way you've calculated
lsrt_1, the 1-period lagged value in 1981 is the immediately preceding
observation, which is from 1979:
| country year lsrt lsrt_1 lsrt_2 dlsrt |
|-------------------------------------------------------------|
6. | 1 1979 2.452249 2.414159 2.378957 .0380907 |
7. | 1 1981 2.415434 2.452249 2.414159 -.0368152 |
But if you use Stata's lag operators, then the 1-period lagged value in
1981 is missing:
+--------------------------------------+
| country year lsrt_l lsrt_ll |
|--------------------------------------|
6. | 1 1979 2.414159 . |
7. | 1 1981 . 2.452249 |
The latter is correct. The 1-period lagged value for 1981 would be from
1980, and in fact there is no 1980 observation. The 2-period lagged value
should be from 1979, and it is.
If you use Stata's lag operators when you create your data, then you will
be using the same transformed data that xtivreg is using.
Best,
Mark
>
> version 8.0
>
> clear
> set mem 10m
> use "C:\Documents and Settings\User\Desktop\panel_a.dta", clear
> set matsize 800
> tsset country year, yearly
>
> *CHECKING DATA;
>
> describe
> summarize
>
> *SET INDIVIDUAL (i) AND TIME (t) INDEXES;
>
> iis country
> tis year
> sort country year
>
> sort country year
> by country: gen lsrt_1=lsrt[_n-1]
> by country:gen lsrt_2=lsrt[_n-2]
> gen dlsrt=lsrt-lsrt_1
> gen dlsrtl=lsrt_1-lsrt_2
>
> list country year lsrt lsrt_1 lsrt_2 dlsrt
>
>
>
>
> *SET INDIVIDUAL (i) AND TIME (t) INDEXES;
> .
> . iis country
>
> . tis year
>
> . sort country year
>
> .
> . sort country year
>
> . by country: gen lsrt_1=lsrt[_n-1]
> (21 missing values generated)
>
> . by country:gen lsrt_2=lsrt[_n-2]
> (42 missing values generated)
>
> . gen dlsrt=lsrt-lsrt_1
> (21 missing values generated)
>
> . gen dlsrtl=lsrt_1-lsrt_2
> (42 missing values generated)
>
> .
> . list country year lsrt lsrt_1 lsrt_2 dlsrt
>
>
> +-------------------------------------------------------------+
> | country year lsrt lsrt_1 lsrt_2 dlsrt
> |
>
> |-------------------------------------------------------------|
> 1. | 1 1967 2.712653 . . .
> |
> 2. | 1 1968 2.54155 2.712653 . -.171103
> |
> 3. | 1 1969 2.505365 2.54155 2.712653 -.036185
> |
> 4. | 1 1976 2.378957 2.505365 2.54155 -.1264076
> |
> 5. | 1 1978 2.414159 2.378957 2.505365 .0352013
> |
>
> |-------------------------------------------------------------|
> 6. | 1 1979 2.452249 2.414159 2.378957 .0380907
> |
> 7. | 1 1981 2.415434 2.452249 2.414159 -.0368152
> |
> 8. | 1 1982 2.454014 2.415434 2.452249 .0385797
> |
> 9. | 1 1985 2.468911 2.454014 2.415434 .0148969
> |
> 10. | 1 1986 2.546347 2.468911 2.454014 .0774364
> |
>
> |-------------------------------------------------------------|
> 11. | 1 1989 2.508549 2.546347 2.468911 -.0377982
> |
> 12. | 1 1990 2.557495 2.508549 2.546347 .0489459
> |
> 13. | 1 1994 2.549296 2.557495 2.508549 -.008199
> |
> 14. | 1 1996 2.583857 2.549296 2.557495 .0345614
> |
> 15. | 2 1970 3.186564 . . .
> |
>
> |-------------------------------------------------------------|
> 16. | 2 1972 3.151164 3.186564 . -.0354004
> |
> 17. | 2 1973 3.094853 3.151164 3.186564 -.0563102
> |
> 18. | 2 1974 3.164042 3.094853 3.151164 .0691881
> |
> 19. | 2 1975 3.182587 3.164042 3.094853 .0185454
> |
> 20. | 2 1976 3.121514 3.182587 3.164042 -.0610731
> |
>
> |-------------------------------------------------------------|
> 21. | 2 1977 3.190412 3.121514 3.182587 .0688984
> |
> 22. | 2 1978 3.210852 3.190412 3.121514 .0204399
> |
> 23. | 2 1979 3.2226 3.210852 3.190412 .0117481
> |
> 24. | 2 1980 3.248157 3.2226 3.210852 .0255563
> |
> 25. | 2 1981 3.29013 3.248157 3.2226 .0419731
> |
>
> |-------------------------------------------------------------|
> 26. | 2 1982 3.307734 3.29013 3.248157 .0176039
> |
> 27. | 2 1983 3.294813 3.307734 3.29013 -.0129201
> |
> 28. | 2 1984 3.287895 3.294813 3.307734 -.0069182
> |
> 29. | 2 1985 3.317431 3.287895 3.294813 .0295362
> |
> 30. | 2 1986 3.338941 3.317431 3.287895 .0215092
> |
>
> |-------------------------------------------------------------|
> 31. | 2 1987 3.304351 3.338941 3.317431 -.03459
> |
> 32. | 2 1988 3.190645 3.304351 3.338941 -.1137056
> |
> 33. | 2 1989 3.210089 3.190645 3.304351 .0194445
> |
> 34. | 2 1990 3.163065 3.210089 3.190645 -.047024
> |
> 35. | 2 1991 3.119796 3.163065 3.210089 -.0432699
> |
>
> |-------------------------------------------------------------|
> 36. | 3 1969 2.724623 . . .
> |
> 37. | 3 1973 2.700287 2.724623 . -.0243354
> |
> 38. | 3 1975 2.785161 2.700287 2.724623 .0848737
> |
> 39. | 3 1976 2.811372 2.785161 2.700287 .0262105
> |
> 40. | 3 1977 2.947806 2.811372 2.785161 .1364348
> |
>
> |-------------------------------------------------------------|
> 41. | 3 1979 3.066484 2.947806 2.811372 .1186774
> |
> 42. | 3 1985 3.140994 3.066484 2.947806 .0745101
> |
> 43. | 3 1988 3.000554 3.140994 3.066484 -.1404402
> |
> 44. | 3 1992 2.924923 3.000554 3.140994 -.0756302
> |
> --more--
>
>
> ivreg dlsrt (dlsrtl=lsrt_2)
> tsset country year
> xtivreg lsrt (lsrt_1=lsrt_2), fd
>
> Instrumental variables (2SLS) regression
>
> Source | SS df MS Number of obs
> =
> 354
> -------------+------------------------------ F( 1, 352)
> =
> 8.73
> Model | -2.29010053 1 -2.29010053 Prob > F
> =
> 0.0033
> Residual | 4.26690113 352 .012121878 R-squared
> =
> .
> -------------+------------------------------ Adj R-squared
> =
> .
> Total | 1.9768006 353 .005600002 Root MSE
> =
> .1101
>
> -------------------------------------------------------------------------
-----
> dlsrt | Coef. Std. Err. t P>|t| [95%
> Conf.
> Interval]
> -------------+-----------------------------------------------------------
-----
> dlsrtl | 1.013682 .3430418 2.95 0.003 .3390123
>
> 1.688351
> _cons | -.001148 .0064632 -0.18 0.859 -.0138594
>
> .0115635
> -------------------------------------------------------------------------
-----
> Instrumented: dlsrtl
> Instruments: lsrt_2
> -------------------------------------------------------------------------
-----
>
> . tsset country year
> panel variable: country, 1 to 21
> time variable: year, 1950 to 1998, but with gaps
>
> . xtivreg lsrt (lsrt_1=lsrt_2), fd
>
> First-differenced IV regression Number of obs =
>
> 272
> Group variable: country Number of groups =
>
> 21
>
> R-sq: within = 0.6984 Obs per group: min =
>
> 1
> between = 0.9997 avg =
>
> 15.9
> overall = 0.9787 max =
>
> 45
>
> chi2(1) =
>
> 0.06
> corr(u_i, Xb) = -0.9785 Prob > chi2 =
>
> 0.8009
>
> -------------------------------------------------------------------------
-----
> d.lsrt | Coef. Std. Err. z P>|z| [95%
> Conf.
> Interval]
> -------------+-----------------------------------------------------------
-----
> lsrt_1 |
> D1 | -.1323335 .5247273 -0.25 0.801 -1.16078
>
> .8961132
> _cons | -.0002588 .0041095 -0.06 0.950 -.0083133
>
> .0077957
> -------------+-----------------------------------------------------------
-----
> sigma_u | .40358129
> sigma_e | .05979004
> rho | .97852333 (fraction of variance due to u_i)
> -------------------------------------------------------------------------
-----
> Instrumented: lsrt_1
> Instruments: lsrt_2
>
> your proposal
>
> tsset country year
> panel variable: country, 1 to 21
> time variable: year, 1950 to 1998, but with gaps
>
> . gen lsrt_l=l.lsrt
> (107 missing values generated)
>
> . gen lsrt_ll=l2.lsrt
> (109 missing values generated)
>
> .
> . list country year lsrt_l lsrt_ll
>
> +--------------------------------------+
> | country year lsrt_l lsrt_ll |
> |--------------------------------------|
> 1. | 1 1967 . . |
> 2. | 1 1968 2.712653 . |
> 3. | 1 1969 2.54155 2.712653 |
> 4. | 1 1976 . . |
> 5. | 1 1978 . 2.378957 |
> |--------------------------------------|
> 6. | 1 1979 2.414159 . |
> 7. | 1 1981 . 2.452249 |
> 8. | 1 1982 2.415434 . |
> 9. | 1 1985 . . |
> 10. | 1 1986 2.468911 . |
> |--------------------------------------|
> 11. | 1 1989 . . |
> 12. | 1 1990 2.508549 . |
> 13. | 1 1994 . . |
> 14. | 1 1996 . 2.549296 |
> 15. | 2 1970 . . |
> |--------------------------------------|
> 16. | 2 1972 . 3.186564 |
> 17. | 2 1973 3.151164 . |
> 18. | 2 1974 3.094853 3.151164 |
> 19. | 2 1975 3.164042 3.094853 |
> 20. | 2 1976 3.182587 3.164042 |
> |--------------------------------------|
> --more--
>
>
>
>
>
>
>
>
>
>
> >>> [email protected] 04/30/04 6:00 PM >>>
> Antonio,
>
> Date sent: Fri, 30 Apr 2004 13:04:56 +0200
> From: "Antonio Rodrigues Andres" <[email protected]>
> To: <[email protected]>
> Subject: st: xtivreg, fd
> Send reply to: [email protected]
>
> > Dear Stata users
> > I am trying a simple dynamic model with the lagged value of the
> dep.
> > variable as regressor. I pretend to obtain the Anderson-Hsiao
> estimator
> > using yit-2 as instrument but i did not succeed. I should get the
> same
> > results using xtivreg, fd and ivreg with the differenced
> variables
> >
> > Does anybody knows why not
> >
> > sort country year
> > by country: gen lsrt_1=lsrt[_n-1]
> > by country:gen lsrt_2=lsrt[_n-2]
>
> Does Stata know at this point that your data are panel data? If
> not,
> some of the lags might be messed up. For example, the 1-period lag
>
> for the first time period of observation 2 should be missing, but
> Stata might be using the latest time period of observation 1
> instead.
> If you use tsset and then time series operators to create the lags,
>
> e.g., l2.lsrt instead of lsrt[_n-2], this won't happen and the lags
>
> will be correct.
>
> Hope this helps.
>
> --Mark
>
> > gen dlsrt=lsrt-lsrt_1
> > gen dlsrtl=lsrt_1-lsrt_2
> >
> > Model yt= alpha* yt-1 + eta _i +ut
> > variables have been already differenced
> >
> > ivreg dlsrt (dlsrtl=lsrt_2) using yit-2 as instrument
> >
> > tsset country year
> > xtivreg lsrt (lsrt_1=lsrt_2), i(country) fd
> >
> > Regards
> > Antonio
> > *
> > * 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/
>
>
> Prof. Mark E. Schaffer
> Director
> Centre for Economic Reform and Transformation
> Department of Economics
> School of Management & Languages
> Heriot-Watt University, Edinburgh EH14 4AS UK
> 44-131-451-3494 direct
> 44-131-451-3008 fax
> 44-131-451-3485 CERT administrator
> http://www.som.hw.ac.uk/cert
> *
> * 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/
>
> *
> * 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/
>
Prof. Mark Schaffer
Director, CERT
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS
tel +44-131-451-3494 / fax +44-131-451-3008
email: [email protected]
web: http://www.sml.hw.ac.uk/ecomes
________________________________________________________________
DISCLAIMER:
This e-mail and any files transmitted with it are confidential
and intended solely for the use of the individual or entity to
whom it is addressed. If you are not the intended recipient
you are prohibited from using any of the information contained
in this e-mail. In such a case, please destroy all copies in
your possession and notify the sender by reply e-mail. Heriot
Watt University does not accept liability or responsibility
for changes made to this e-mail after it was sent, or for
viruses transmitted through this e-mail. Opinions, comments,
conclusions and other information in this e-mail that do not
relate to the official business of Heriot Watt University are
not endorsed by it.
________________________________________________________________
*
* 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/
