Re: st:Why fixed effect estimates are different using Stata and SPSS?

[Steven Samuels <sjhsamuels@earthlink.net>]

The two setups are not comparable.  In your SPSS syntax, you left out  
a statement like:
/RANDOM = INTERCEPT | SUBJECT(id)

-Steve
On Jan 6, 2009, at 7:01 PM, Mandy fu wrote:

> Hi Statalisters,
>
> I find the results I got from estimating a simple fixed effect model
> using Stata are quite different from what using SPSS. I was quite
> confused that since SPSS estimates fixed effect using linear mixed
> model (LMM), while in Stata when estimating LMM, I should use
> -xtmixed- command instead of --xtreg--command.
>
> I'm thinking  I must have misundertood something. Could anyone give me
> some clue ?Thanks so much!
>
> Best wishes,
> Mandy
>
> [The commands and outputs I used are as follows.]
> ----------------------------- 
> STATA----------------------------------------------------------------- 
> -----------
> . xtset id
> . xtreg lnhr lnwg kids ageh agesq disab,fe
> ---------------------------------------------------------------------- 
> ------------------------------------
>         lnhr |      Coef.   Std. Err.      t    P>|t|     [95%  
> Conf. Interval]
>         lnwg |   .1647719   .0189379     8.70   0.000     . 
> 1276448    .2018989
>         kids |  -.0011805   .0062019    -0.19   0.849    -. 
> 0133391    .0109781
>         ageh |   .0142179   .0063804     2.23   0.026     . 
> 0017095    .0267263
>        agesq |  -.0001676   .0000814    -2.06   0.039    -. 
> 0003272   -8.10e-06
>        disab |  -.0628007   .0185922    -3.38   0.001      -. 
> 09925   -.0263514
>        _cons |   6.945659   .1258117    55.21   0.000       
> 6.69901    7.192308
> _____________________________________________________________________
> ----------------------------------SPSS----------------------------
> MIXED lnhr WITH lnwg kids ageh agesq disab
>    E(0.000001, ABSOLUTE)
>   /FIXED=lnwg kids ageh agesq disab | SSTYPE(3)
>   /METHOD=REML
>   /PRINT=SOLUTION.
> ---------------------------------------------------------------------- 
> ---------------
> Parameter Estimate	Std. Error	df	t	Sig.
> Intercept	7.467766	.083797	5314.000	89.117	.000
> lnwg	.082290	.009305	5314.000	8.844	.000
> kids	.007982	.003652	5314.000	2.186	.029
> ageh	-.000745	.004363	5314.000	-.171	.864
> agesq	-1.681402E-6	5.407029E-5	5314.000	-.031	.975
> disab	-.095341	.016312	5314	-5.845	.000
> ---------------------------------------------------------------------- 
> ----------------
> *
> *   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/