Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: LR test question


From   "Julia A. Gamas Buentello" <ardilla@bu.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: LR test question
Date   Wed, 25 Jun 2003 12:12:37 -0400

Hi,

I'm running two spatial error model (ML) regressions as follows, but when I
do the lrtest for the second regression it gives me a chi(0) and nothing for
the P value.  What did I do wrong?  Why is it giving me a "." value for the
pr?  Is it caused by the fact that I have ratios and not totals?  Is there
another test I can use?  Any help will be appreciated:

I generated:
shopprodpc=shopprod/pop94
hhpc=pop94/hh94
dens94=area/pop94
Then:


Spatial error model               Number of obs   =134
                                  Variance ratio  =0.305
                                  Squared corr.   =0.275
Log likelihood = 249.77364        Sigma           =0.04

-------------------------------------------------------------------------
--
          |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
Interval]
----------+------------------------------------------------------------
--
shopprodpc|
  avginc94|  -9.27e-11   1.70e-10    -0.55   0.586    -4.26e-10
2.41e-10
    	hhpc|   -.062498   .0109048    -5.73  0.000   -.083871   -.0411251
    dens94|  -9.49e-07   2.14e-07    -4.44  0.000  -1.37e-06   -5.30e-07
      cons|   .3679341   .0562223     6.54  0.000    .257740   4.4781277
----------+--------------------------------------------------------------

    lambda|  -.0057759   .0074804    -0.77   0.440  -.0204373  .0088855
-------------------------------------------------------------------------
Wald test of lambda=0:                 chi2(1) =   0.596 (0.440)
Likelihood ratio test of lambda=0:     chi2(1) =   0.567 (0.451)
Lagrange multiplier test of lambda=0:  chi2(1) =  11.725 (0.001)

Acceptable range for lambda: -1.553 < lambda < 1.000

. lrtest, saving(0)

. spatreg shopprodpc hhpc dens94, weights(W) eigenval(E) model(error)

Weights matrix
 Name: W
 Type: Imported (binary)
 Row-standardized: No

Spatial error model                  Number of obs   =134
                                     Variance ratio  =0.308
                                     Squared corr.   =0.273
Log likelihood = 249.62466           Sigma           =0.04

------------------------------------------------------------------------
--
          |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
Interval]
--------- +-------------------------------------------------------------
--
shopprodpc|
     hhpc |  -.0593628   .0092568    -6.41 0.000    -.0775058   -.0412198
   dens94 |  -8.83e-07   1.75e-07    -5.04 0.000    -1.23e-06   -5.39e-07
     cons |   .3506137   .0464955     7.54   0.000     .2594841 .4417432
----------+-------------------------------------------------------------
   lambda |  -.0068492    .007611    -0.90   0.368    -.0217665
.0080681
------------------------------------------------------------------------
Wald test of lambda=0:                 chi2(1) =   0.810 (0.368)
Likelihood ratio test of lambda=0:     chi2(1) =   0.729 (0.393)
Lagrange multiplier test of lambda=0:  chi2(1) =  11.776 (0.001)

Acceptable range for lambda: -1.553 < lambda < 1.000

. lrtest
Spatreg:  likelihood-ratio test              chi2(0)     =0.30
                                             Prob > chi2 =.



Julia A. Gamas Buentello
Center for Transportation Studies
Boston University Geography Department
675 Commonwealth Ave.
Boston, MA 02215
Tel: 617 358 0204
Fax: 617 358 0205
ardilla@bu.edu

*
*   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/



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