Dear All,
I m running the command xtlogit, re vce(robust) for my model since my dependent variable is a binary variable. However, I am not sure everthing is correct with my model because the coefficient of the variable "HDI" which represents the Human Development Index of the firm's country is very high (7.134983), is it normal to get such a high coefficient? Could you please check whether I made something wrong?
I m running the command xtlogit, re vce(robust) for my model since my dependent variable is a binary variable. However, I am not sure everthing is correct with my model because the coefficient of the variable "HDI" which represents the Human Development Index of the firm's country is very high (7.134983), is it normal to get such a high coefficient? Could you please check whether I made something wrong?
Code:
. xtlogit GRIDUMMY EF HDI WGI MARKETBANK TRADE LISTEDCOMP pdi i.SIZECODE i.INDUSTRYCODE i.YEAR, re vce(robust)
Fitting comparison model:
Iteration 0: log pseudolikelihood = -6698.6528
Iteration 1: log pseudolikelihood = -5516.0771
Iteration 2: log pseudolikelihood = -5464.7453
Iteration 3: log pseudolikelihood = -5464.424
Iteration 4: log pseudolikelihood = -5464.424
Fitting full model:
tau = 0.0 log pseudolikelihood = -5464.424
tau = 0.1 log pseudolikelihood = -5311.8319
tau = 0.2 log pseudolikelihood = -5166.1068
tau = 0.3 log pseudolikelihood = -5026.4973
tau = 0.4 log pseudolikelihood = -4892.4275
tau = 0.5 log pseudolikelihood = -4763.6494
tau = 0.6 log pseudolikelihood = -4640.6184
tau = 0.7 log pseudolikelihood = -4525.5951
tau = 0.8 log pseudolikelihood = -4426.0644
Iteration 0: log pseudolikelihood = -4525.463
Iteration 1: log pseudolikelihood = -4260.4518
Iteration 2: log pseudolikelihood = -4202.5863
Iteration 3: log pseudolikelihood = -4189.3637
Iteration 4: log pseudolikelihood = -4189.2971
Iteration 5: log pseudolikelihood = -4189.2613
Iteration 6: log pseudolikelihood = -4189.2613 (backed up)
Iteration 7: log pseudolikelihood = -4189.2504
Iteration 8: log pseudolikelihood = -4189.2504
Calculating robust standard errors:
Random-effects logistic regression Number of obs = 10,622
Group variable: ID Number of groups = 3,457
Random effects u_i ~ Gaussian Obs per group:
min = 1
avg = 3.1
max = 7
Integration method: mvaghermite Integration pts. = 12
Wald chi2(51) = 595.56
Log pseudolikelihood = -4189.2504 Prob > chi2 = 0.0000
(Std. Err. adjusted for 3,457 clusters in ID)
------------------------------------------------------------------------------
| Robust
GRIDUMMY | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
EF | -.794144 .0905921 -8.77 0.000 -.9717012 -.6165867
HDI | 7.134983 2.103149 3.39 0.001 3.012887 11.25708
WGI | .0751934 .0091546 8.21 0.000 .0572507 .093136
MARKETBANK | 1.51871 .2081931 7.29 0.000 1.110659 1.926761
TRADE | -.0213453 .0029042 -7.35 0.000 -.0270375 -.0156531
LISTEDCOMP | -.0008253 .0000774 -10.66 0.000 -.000977 -.0006735
pdi | -.0181224 .0094897 -1.91 0.056 -.0367219 .000477
|
SIZECODE |
2 | .0560961 .2327905 0.24 0.810 -.4001649 .5123572
3 | -.7657774 .2692277 -2.84 0.004 -1.293454 -.2381008
|
INDUSTRYCODE |
2 | 1.093076 .6323171 1.73 0.084 -.1462424 2.332395
3 | 1.745545 .8048255 2.17 0.030 .1681159 3.322974
4 | 3.737957 .8479716 4.41 0.000 2.075963 5.39995
5 | .1684474 .8915327 0.19 0.850 -1.578925 1.915819
6 | .8330704 .5392894 1.54 0.122 -.2239174 1.890058
7 | .8476553 .4985822 1.70 0.089 -.1295478 1.824858
8 | 1.616773 .6954972 2.32 0.020 .253624 2.979923
9 | 2.094374 .8336663 2.51 0.012 .4604185 3.72833
10 | 1.820881 .8298653 2.19 0.028 .1943746 3.447387
11 | .8696175 .6657727 1.31 0.191 -.435273 2.174508
12 | 1.660832 .5793592 2.87 0.004 .5253084 2.796355
13 | 1.097648 .6655542 1.65 0.099 -.2068142 2.40211
14 | 1.659405 .6085067 2.73 0.006 .4667541 2.852057
15 | 1.571707 .58902 2.67 0.008 .4172489 2.726165
16 | -.4546692 .7386691 -0.62 0.538 -1.902434 .9930958
17 | 1.141251 .828004 1.38 0.168 -.4816075 2.764109
18 | 2.761143 .5877891 4.70 0.000 1.609097 3.913188
19 | -.6074114 .4955779 -1.23 0.220 -1.578726 .3639034
20 | .1029561 .7489992 0.14 0.891 -1.365055 1.570968
21 | 1.863303 .522451 3.57 0.000 .8393178 2.887288
22 | .6279565 .5842609 1.07 0.282 -.5171739 1.773087
23 | .4604285 .7443967 0.62 0.536 -.9985623 1.919419
24 | -.3339932 .6555017 -0.51 0.610 -1.618753 .9507665
25 | 1.337136 .6721295 1.99 0.047 .0197861 2.654485
26 | 1.878334 .6502785 2.89 0.004 .6038116 3.152856
27 | -.573694 1.223187 -0.47 0.639 -2.971096 1.823708
28 | .3236552 .7054683 0.46 0.646 -1.059037 1.706348
29 | .1539578 1.006267 0.15 0.878 -1.81829 2.126206
30 | 1.959095 .6823053 2.87 0.004 .621801 3.296389
31 | .3510582 .6470255 0.54 0.587 -.9170885 1.619205
32 | 1.460112 .9286049 1.57 0.116 -.3599201 3.280144
33 | 2.15393 1.982011 1.09 0.277 -1.730741 6.038601
34 | -.7165465 .8305085 -0.86 0.388 -2.344313 .9112203
35 | 1.198915 .9832089 1.22 0.223 -.7281388 3.125969
36 | 2.259782 .9301801 2.43 0.015 .4366628 4.082902
37 | .1138347 1.895794 0.06 0.952 -3.601854 3.829523
|
YEAR |
2011 | .0965435 .2068523 0.47 0.641 -.3088796 .5019666
2012 | .2651756 .2275511 1.17 0.244 -.1808164 .7111677
2013 | .6161574 .237699 2.59 0.010 .1502759 1.082039
2014 | .4201237 .2458367 1.71 0.087 -.0617073 .9019548
2015 | .4487022 .251094 1.79 0.074 -.0434331 .9408375
2016 | -.2402657 .2521466 -0.95 0.341 -.7344639 .2539325
|
_cons | -4.033084 1.705101 -2.37 0.018 -7.375021 -.6911467
-------------+----------------------------------------------------------------
/lnsig2u | 2.622093 .0837984 2.457851 2.786335
-------------+----------------------------------------------------------------
sigma_u | 3.710054 .1554483 3.417556 4.027587
rho | .8070953 .0130468 .7802294 .8313867
------------------------------------------------------------------------------
Comment