Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Yuval Arbel <yuval.arbel@gmail.com> |
| To | statalist <statalist@hsphsun2.harvard.edu> |
| Subject | st: Interpretation of the estimates obtained by the -xtprobit- command |
| Date | Thu, 29 Mar 2012 09:56:52 +0200 |
Dear Statalisters,
I'm attaching below the outcomes obtained for a sample of 8,909
pregnant women who gave birth to 25,052 infants
I have several questions:
1. Is there something equivalent to -dprobit- which permits direct
interpretation of the coefficients?
2. What is the reason -xtprobit- does not permit the fixed-effect option?
3. How can I test statistically the validity of the random-effect
between the constant term of each pregnant women and the variables?
4. I also ran the command -xtlogit- with the -fe- option (attached
below). The algorithm omitted many panels and I got the following
message:
note: multiple positive outcomes within groups encountered.
note: 7307 groups (18043 obs) dropped because of all positive or
all negative outcomes.
I wonder what is the problem caused the algorithm to omit so many panels
I appreciate your assistance
Yuval
. xtprobit private2 hospitalization_num birth_by_operation mother_usa
mother_canada mother_england mother_ethiopia
> mother_switzerland mother_france mother_russia1 former_children1 muslim christian tourist1 immigrant pupil_in_yes
> hiva teacher
Fitting comparison model:
Iteration 0: log likelihood = -8506.5487
Iteration 1: log likelihood = -7708.4231
Iteration 2: log likelihood = -7697.5432
Iteration 3: log likelihood = -7697.5295
Iteration 4: log likelihood = -7697.5295
Fitting full model:
rho = 0.0 log likelihood = -7697.5295
rho = 0.1 log likelihood = -7628.272
rho = 0.2 log likelihood = -7632.6183
Iteration 0: log likelihood = -7628.272
Iteration 1: log likelihood = -7624.7393
Iteration 2: log likelihood = -7558.7882
Iteration 3: log likelihood = -7558.4689
Iteration 4: log likelihood = -7558.4685
Random-effects probit regression Number of obs = 25052
Group variable: index Number of groups = 8908
Random effects u_i ~ Gaussian Obs per group: min = 1
avg = 2.8
max = 17
Wald chi2(16) = 1315.66
Log likelihood = -7558.4685 Prob > chi2 = 0.0000
------------------------------------------------------------------------------
private2 | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
hospitaliz~m | .0129728 .0075312 1.72 0.085 -.0017881 .0277336
birth_by_o~n | 1.077024 .0383647 28.07 0.000 1.00183 1.152217
mother_usa | .8338842 .0495205 16.84 0.000 .7368257 .9309426
mother_can~a | .8395324 .1346013 6.24 0.000 .5757187 1.103346
mother_eng~d | .5693104 .0833725 6.83 0.000 .4059033 .7327175
mother_eth~a | -.6634257 .2664923 -2.49 0.013 -1.185741 -.1411104
mother_swi~d | .9164751 .1478142 6.20 0.000 .6267646 1.206186
mother_fra~e | -.2771848 .1316733 -2.11 0.035 -.5352597 -.0191098
mother_rus~1 | -.2880794 .1155616 -2.49 0.013 -.514576 -.0615828
former_chi~1 | .0101862 .0046692 2.18 0.029 .0010346 .0193377
muslim | -.1308288 .0715678 -1.83 0.068 -.2710991 .0094414
christian | -1.073336 .5447206 -1.97 0.049 -2.140969 -.0057035
tourist1 | .444191 .0793486 5.60 0.000 .2886705 .5997114
immigrant | .1317313 .0493153 2.67 0.008 .0350752 .2283874
pupil_in_y~a | -.0354636 .0331773 -1.07 0.285 -.1004899 .0295627
teacher | -.0135476 .0809299 -0.17 0.867 -.1721673 .1450721
_cons | -1.801318 .0438827 -41.05 0.000 -1.887327 -1.715309
-------------+----------------------------------------------------------------
/lnsig2u | -.9331074 .0921739 -1.113765 -.7524499
-------------+----------------------------------------------------------------
sigma_u | .6271599 .0289039 .5729926 .6864479
rho | .2822947 .0186748 .2471697 .3202877
------------------------------------------------------------------------------
Likelihood-ratio test of rho=0: chibar2(01) = 278.12 Prob >= chibar2 = 0.000
. xtlogit private2 hospitalization_num birth_by_operation mother_usa
mother_canada mother_england mother_ethiopia m
> other_switzerland mother_france mother_russia1 former_children1 muslim christian tourist1 immigrant pupil_in_yesh
> iva teacher,fe
note: multiple positive outcomes within groups encountered.
note: 7307 groups (18043 obs) dropped because of all positive or
all negative outcomes.
Iteration 0: log likelihood = -2159.1289
Iteration 1: log likelihood = -2120.0164
Iteration 2: log likelihood = -2119.4414
Iteration 3: log likelihood = -2119.3205
Iteration 4: log likelihood = -2119.296
Iteration 5: log likelihood = -2119.2909
Iteration 6: log likelihood = -2119.2898
Iteration 7: log likelihood = -2119.2895
Iteration 8: log likelihood = -2119.2894
Iteration 9: log likelihood = -2119.2894
Conditional fixed-effects logistic regression Number of obs = 7009
Group variable: index Number of groups = 1601
Obs per group: min = 2
avg = 4.4
max = 17
LR chi2(16) = 702.85
Log likelihood = -2119.2894 Prob > chi2 = 0.0000
------------------------------------------------------------------------------
private2 | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
hospitaliz~m | .0390685 .0175739 2.22 0.026 .0046242 .0735128
birth_by_o~n | 1.686039 .0937217 17.99 0.000 1.502348 1.86973
mother_usa | 1.468732 .1319606 11.13 0.000 1.210094 1.72737
mother_can~a | 1.5773 .3641062 4.33 0.000 .8636647 2.290935
mother_eng~d | 1.090552 .2185774 4.99 0.000 .6621478 1.518955
mother_eth~a | -1.215727 .7218827 -1.68 0.092 -2.630591 .1991374
mother_swi~d | 1.432616 .3794459 3.78 0.000 .6889158 2.176317
mother_fra~e | -.502122 .3312722 -1.52 0.130 -1.151404 .1471596
mother_rus~1 | -.3725172 .2961963 -1.26 0.209 -.9530514 .2080169
former_chi~1 | .0169162 .0124888 1.35 0.176 -.0075614 .0413938
muslim | -.4356984 .1897871 -2.30 0.022 -.8076743 -.0637226
christian | -13.76266 558.0707 -0.02 0.980 -1107.561 1080.036
tourist1 | .6817092 .2114854 3.22 0.001 .2672056 1.096213
immigrant | .2331337 .1294273 1.80 0.072 -.0205391 .4868065
pupil_in_y~a | -.1166618 .083074 -1.40 0.160 -.2794838 .0461603
teacher | .0254976 .1960549 0.13 0.897 -.3587629 .4097582
------------------------------------------------------------------------------
--
Dr. Yuval Arbel
School of Business
Carmel Academic Center
4 Shaar Palmer Street,
Haifa 33031, Israel
e-mail1: yuval.arbel@carmel.ac.il
e-mail2: yuval.arbel@gmail.com
*
* 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/