Hi - After all these years of using -nl-, I apparently never tried to use
-test- after estimation. But it doesn't work, even though the (Stata 8,
p.48) manual mentions -test- as a complementary reference at the end of the
-nl-section. So what am I doing wrong (see below)?
. nl vbgfno ml age sex
(obs = 24)
Iteration 0: residual SS = 4427965
.......etc.
Iteration 9: residual SS = 48.2238
Source | SS df MS Number of obs =
24
-------------+------------------------------ F( 6, 18) =
3553.46
Model | 57120.5084 6 9520.08474 Prob > F =
0.0000
Residual | 48.2237977 18 2.67909987 R-squared =
0.9992
-------------+------------------------------ Adj R-squared =
0.9989
Total | 57168.7322 24 2382.03051 Root MSE =
1.636796
Res. dev. =
84.85622
VBGF, ml=b0*(1-exp(-b1*(age-b2))) if sex=1; b3*(1-exp(-b4*(age-b5))) if
sex=2
----------------------------------------------------------------------------
--
ml | Coef. Std. Err. t P>|t| [95% Conf.
Interval]
-------------+--------------------------------------------------------------
--
b0 | 55.97801 1.138011 49.19 0.000 53.58714
58.36888
b1 | .3855844 .0409733 9.41 0.000 .2995027
.4716662
b2 | .1713388 .1489188 1.15 0.265 -.1415279
.4842055
b3 | 61.2333 1.170976 52.29 0.000 58.77317
63.69343
b4 | .2962532 .0277204 10.69 0.000 .2380147
.3544917
b5 | -.0572645 .1691157 -0.34 0.739 -.4125634
.2980343
----------------------------------------------------------------------------
--
(SEs, P values, CIs, and correlations are asymptotic approximations)
. test b0=b3
b0 not found
r(111);
. test [ml]b0=50
equation [ml] not found
r(303);
Thanks
Al Feiveson
*
* 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/
