OLS and GMM regression on insurance data

[Michael Craig]

I have some insurance data and I want to make

a) an OLS regression and

b) an GMM regression

on the data with PM the dependent variable.


However, when I run the regression with xtreg logPM logGDP logLE logDEP logEDU logSOC logFD FMS FMSSQ IN

there are only 53 observations and the results are not plausible as well. (results look better with the fe at at the end for fixed effects). In total there are 180 observations with missing data for only a few of the variables.


By using this:

by CG, sort : regress logPM logGDP logLE logDEP logEDU logSOC logFD FMS FMSSQ IN

it tells me that there is no data for 6 countries (from 10). But there is data.

I do not understand where the problem comes from.


Further, I have no idea how to make a GMM regression on the data. Any suggestions?

* Example generated by -dataex-. To install: ssc install dataex
clear
input long(id index country Year) double(PM GDP LE DEP EDU SOC FD FMS IN FYIN) float(logPM logGDP logLE logDEP logEDU logSOC logFD FMSSQ AM_EM CG)
1  1 1  2 1097.860299799104 29453.585522 79.63414634146342 49.41451031709003         .  5168.51518740056 70.39762013768924 27.306   .044071353620147  .0192819427047746  7.001118  10.29057  4.377443  3.900244         .  8.550341 4.2541595  745.6176 1 1
1  1 1 10 1488.891327097461 41613.636163 81.54390243902441 47.77266022317576         .  7046.43701148079 94.41579019523229 28.705  .0177111716621252  .0305365689681594  7.305787 10.636183 4.4011416 3.8664534         .  8.860277 4.5477085  823.9771 1 1
1  1 1  9 1836.307813941231 40094.833205 81.39512195121952  47.7459755436092         . 6851.806046402449 97.91784890923655 32.796  .0435029854990047  .0273011638006941  7.515512 10.599003 4.3993154  3.865895         .  8.832268  4.584129 1075.5776 1 1
1  1 1 15 2526.674492068091 47638.633438              82.3 50.25970006031974         . 8701.672783785078 108.5461304503356 15.483  .0248792270531403  .0244119522932621  7.834659   10.7714 4.4103713  3.917204         .  9.071271 4.6871753  239.7233 1 1
1  1 1 17  1697.59360407611 50262.606439  82.4487804878049 51.72993235193651 120.96571 8950.764954657121 118.0004015387355 20.757  .0127699094497328   .023025616761236  7.436967 10.825017  4.412177 3.9460366  4.795507  9.099494  4.770688  430.8531 1 1
1  1 1  1 1246.220644285491 28260.390995 79.23414634146343 49.71426641807308         .  5158.36916831735  67.6753587261158  27.43  .0445743514797225  .0196226056080252  7.127871 10.249216 4.3724074  3.906292         .  8.548376  4.214722  752.4049 1 1
1  1 1 11 1829.982729469969 42812.136116 81.69512195121953 47.94845436700014         . 7104.245867089041 100.6992252707777 15.003  .0291834002677376  .0293922928509327  7.512062 10.664577  4.402994 3.8701265         .  8.868448 4.6121383    225.09 1 1
1  1 1  5 1336.781750250902 33886.624494 80.49024390243903 48.70896842041801         .  5848.15365517452 77.52098249735494 32.441  .0234325522482587  .0321237408371173   7.19802 10.430776  4.388136  3.885863         .  8.673882 4.3505487 1052.4185 1 1
1  1 1 13 2026.477002076014 43879.180355 82.04634146341463 49.06719335606529         . 7588.026658790149 101.2808488917262 15.837  .0176278015613193  .0293424343757779  7.614054 10.689196 4.4072843 3.8931906         .  8.934327 4.6178975 250.81056 1 1
1  1 1  7 1428.658221365453 37862.570607 81.04146341463415 48.18525523096908         .  5958.05411071752 83.63053631431109 32.401  .0355528773727028  .0303127855510804  7.264491 10.541718  4.394961  3.875053         .  8.692499  4.426409 1049.8248 1 1
1  1 1  4 1129.318234365733 32203.982172 80.23902439024391 48.91322099835649         .  5656.30742869008 74.79537663295795 25.772  .0273259596616783   .028378818164318  7.029369 10.379846   4.38501  3.890048         .  8.640527  4.314756   664.196 1 1
1  1 1  3 1074.053858758155 30740.962903 79.93658536585367 49.14673656811186         . 5335.401521444681  70.4369007225626 29.453  .0298157453936349  .0228654441980347  6.979196  10.33335 4.3812337 3.8948104         .  8.582119 4.2547174  867.4792 1 1
1  1 1  6  1381.92995273305 35570.808015 80.84146341463415 48.55723253554027         .  5943.52631122635 78.51806865953179 30.669  .0269183168316831  .0338439924806883  7.231236  10.47928   4.39249  3.882743         .  8.690058  4.363329  940.5876 1 1
1  1 1  8 1991.938869576908 39612.856505 81.29268292682927 47.89079729212913         . 6296.463541469751 90.67413697966708 30.311  .0232761128891476  .0286090903015916  7.596864  10.58691  4.398056 3.8689234         .  8.747744 4.5072722  918.7567 1 1
1  1 1 18 1531.115370951627 51993.845657 82.49756097560977 52.59967059572824 113.14216                 . 116.1945077180167  25.45  .0194864740944522  .0189718983390077  7.333752  10.85888  4.412769   3.96271  4.728645         . 4.7552657  647.7025 1 1
1  1 1 12 2146.311883997976 44419.309749 81.89512195121951 48.51375386125373         .  7574.38069839948 99.86516769094649 10.296  .0330385015608744  .0298453095381436  7.671506  10.70143 4.4054394 3.8818474         .  8.932527  4.603821 106.00761 1 1
1  1 1 16 1958.057977422316 47351.047292              82.4  50.9250562135116 118.61086   8776.5166155722 113.2100388451845 17.684  .0150836672165921  .0258455633714651  7.579709 10.765345 4.4115853  3.930355  4.775848  9.079835 4.7292447 312.72385 1 1
1  1 1 14 2080.657670147032  47761.21406 82.14878048780488 49.64057799191978         .   8423.1677116216  105.521229915263 16.833  .0244988864142539  .0282127721102122   7.64044  10.77397  4.408532 3.9048085         .  9.038741  4.658912 283.34988 1 1
2  2 2 13                 . 15572.826188            74.209  45.0795496472828  28.72567                 . 79.05286202089596      .  .0540355339056006   .051765995892498         .  9.653283 4.3068852  3.808429  3.357791         . 4.3701167         . 2 2
2  2 2  9                 . 13396.398248            72.966 47.71544604884465  20.68412                 . 70.48945296717213      .  .0567859390284171  .0720129663033191         .  9.502741  4.289994  3.865255  3.029366         .  4.255463         . 2 2
2  2 2  6                 . 11064.592516            71.896 50.07624270775782    19.087                 . 60.13304445758521      .  .0686953720898965  .0872935385682111         .  9.311505 4.2752204  3.913547 2.9490075         . 4.0965595         . 2 2
2  2 2 12                 . 15131.733843            73.921 45.65736422403059  25.64785                 . 76.82527513705202      .  .0663636935253204  .0468603934453719         .   9.62455  4.302997  3.821165 3.2444596         . 4.3415337         . 2 2
2  2 2 11                 .  14382.76105            73.619 46.29330039808141  24.19849                 . 74.21938014183547      .  .0503872690108066  .0505220140611899         .  9.573786  4.298903  3.834997   3.18629         . 4.3070254         . 2 2
2  2 2 15 207.4383419697807 16396.241834            74.745 44.11169781348571  42.43073                 . 81.90654984086028 18.593  .0632915222712776  .0563420407826781  5.334834  9.704807  4.314082  3.786725  3.747873         .  4.405579 345.69965 2 2
2  2 2  5                 . 10508.408121            71.531 50.89021847281254  17.69126                 . 56.33206510810064      .  .0659718509985962  .0838160633665452         .  9.259931  4.270131  3.929671  2.873071         .  4.031264         . 2 2
2  2 2 16 170.2897087959365 15847.582563            74.994 43.74810575176913  46.04043                 . 88.06962764441465 18.308   .090298071857749  .0592242756393975  5.137501  9.670773  4.317408  3.778448   3.82952         .  4.478128  335.1829 2 2
2  2 2  3                 .  9603.149244            70.813 52.57791745347559  12.62848                 . 55.00498217102859      .   .084501643770833  .0577294727849333         .  9.169847 4.2600427  3.962296 2.5359545         .  4.007424         . 2 2
2  2 2  2                 .  9296.974644            70.462 53.44215568653618   9.78911                 . 58.63617171799618      .  .0684035902487525   .075564085935704         . 9.1374445 4.2550735    3.9786 2.2812705         .  4.071352         . 2 2
2  2 2  1                 .  9091.892265            70.116 54.29089660764595   7.59041                 . 46.48658780841674      .  .0704414105947266  .1934898709252549         .  9.115138  4.250151 3.9943566 2.0268855         .  3.839164         . 2 2
2  2 2 18  212.537341911385 15651.388542            75.456 43.45006074894184  49.07326                 . 93.50880640346449 21.264  .0344636783234738  .0714119541029195  5.359118  9.658315 4.3235497  3.771612 3.8933144         . 4.5380554  452.1577 2 2
2  2 2  4                 .  9785.188819             71.17 51.72325443449373  15.45268                 . 56.52636379879623      .   .147149197228147  .0607763765065169         .  9.188625 4.2650714 3.9459076 2.7377825         .  4.034707         . 2 2
2  2 2 14                 . 16163.011938            74.483  44.5602184175111  32.43367                 . 78.62654255643221      .  .0620433594839825   .055290556691565         .   9.69048 4.3105707 3.7968414  3.479197         . 4.3647094         . 2 2
2  2 2  8                 . 12632.619712            72.618 48.45965328438713  20.52122                 . 68.35919862134917      .  .0364127299102654  .0816307490754326         .  9.444037  4.285213 3.8807316 3.0214596         . 4.2247763         . 2 2
2  2 2 10                 . 13343.494423              73.3 46.99178832631434  22.44306                 . 76.09041943969183      .  .0488803479876804  .0539403146633731         .  9.498784 4.2945604  3.849973 3.1109815         . 4.3319225         . 2 2
2  2 2  7                 . 11724.612121             72.26 49.24145144264349  20.21919                 . 63.24977946767969      .  .0418356812896902   .086944330867245         .  9.369446 4.2802706  3.896736  3.006632         .  4.147092         . 2 2
2  2 2 17  188.855590219272 15385.778312             75.23 43.57751288574445  48.01902                 .  93.8529196194168 17.222  .0873912829959879   .067206436208786  5.240983  9.641199   4.32055  3.774541  3.871597         .  4.541729  296.5973 2 2
3 10 3 15 27.45750108116428 13349.524984 83.98048780487807 34.61668733228773  49.91353                 . 191.5502869185237      .  .0192164341593894  .0264832577950445 3.3126395  9.499236 4.4305844  3.544336  3.910292         .   5.25515         . 2 3
3 10 3  2                 .  3215.672512 81.42439024390245 38.11092687544469  18.15428                 . 141.0856249600857      .   .007191324368115  .0185455438869345         .  8.075791  4.399675  3.640501  2.898906         .  4.949367         . 2 3
3 10 3  6                 .  5077.604087 81.62926829268292 36.22953392791624  25.98963                 . 151.0858035625865      .  .0177641616843146  .0105744055568988         .  8.532595  4.402188  3.589875 3.2576976         .  5.017848         . 2 3
3 10 3  7                 .  5868.230134 82.37560975609757 35.38946461424734         .                 . 157.4945324828235      .   .016494331013998  .0134316253801473         .  8.677308  4.411289  3.566414         .         .  5.059391         . 2 3
3 10 3 10 15.37628186830521  8340.610606 82.77560975609757 33.32688955633926   37.0384                 . 175.0914008315385      . -.0072817133417307  .0359850149919746  2.732826  9.028892 4.4161334 3.5063646  3.611955         .  5.165308         . 2 3
3 10 3 17 38.74817812884204 15411.798699 84.22682926829269 36.89183871442637  50.48851                 . 209.4512597790614      .  .0200000000000002  .0283062803616522  3.657084  9.642889 4.4335136   3.60799  3.921746         .  5.344491         . 2 3
3 10 3 16 30.60889791572468 14350.358392 84.27804878048782 35.78459352428555  51.05413                 . 202.9580964915483      .   .014370245139476  .0317828872952685 3.4212906   9.57153 4.4341216 3.5775175 3.9328864         .     5.313         . 2 3
3 10 3 12 18.45659869209079 10330.747358  83.4219512195122 33.12943597706474  43.45983                 . 174.5277128346875      .  .0555389705904324  .0296772207002584  2.915422   9.24288 4.4239116  3.500422  3.771837         .  5.162084         . 2 3
3 10 3 11 17.09405511678584  9290.279906 82.97804878048782 33.11310160235261         .                 . 176.1266180826603      .  .0317532798075574  .0268793970756098  2.838731 9.1367235 4.4185762  3.499929         .         .  5.171203         . 2 3
3 10 3 14 23.88820006188392 12290.324176 83.83170731707318 33.80678619916333  46.81655                 . 186.6093886825658      .  .0262104902701091  .0330916703184411  3.173385  9.416568  4.428811 3.5206616  3.846237         .  5.229018         . 2 3
3 10 3  1                 .  2922.239364 80.87804878048782 38.65032180812501         .                 . 135.5804160347636      .  .0034780625680719  .0514323854070903         .  7.980105 4.3929424  3.654555         .         .  4.909565         . 2 3
3 10 3 13 20.82077893232743 11285.566263 83.48048780487807 33.33604352922704  44.96641                 . 180.8735686119054      .  .0261952616488542  .0374861486155453 3.0359514   9.33128  4.424613  3.506639  3.805916         .  5.197798         . 2 3
3 10 3  8                 .  6842.746986  82.3268292682927 34.57598631104812  30.78669                 . 149.3719776535651      .  .0481676531343752  .0152922267093239         .  8.830944  4.410697 3.5431595 3.4270825         .   5.00644         . 2 3
3 10 3 18 41.93147479614396 16633.148693 84.68048780487806 38.46903456077852   51.3436                 . 204.1748223342321      .  .0159313725490194  .0211984862435658  3.736037  9.719152  4.438885  3.649854   3.93854         .  5.318976         . 2 3
3 10 3  5                 .  4442.162104 81.82926829268294 36.80137472928614  24.49124                 .  149.793554728117      .  .0382463762400933  .0001221826933479         .  8.398896  4.404635  3.605535 3.1983156         .  5.009258         . 2 3
3 10 3  9                 .  7609.268425 82.37560975609757 33.84788725674929   35.5621                 .  148.840920097004      .   .059252552887092  .0263897083363661         .  8.937122  4.411289 3.5218766 3.5712805         .  5.002878         . 2 3
3 10 3  3                 .  3540.243681 81.42682926829269 37.67869486452201  20.69567                 . 145.3901447273856      . -.0073197550008358  .0033575020728944         .  8.171951  4.399705  3.629095 3.0299244         .  4.979421         . 2 3
3 10 3  4                 .  3949.409942  81.3780487804878 37.27555663423161  23.21699                 . 153.5509353547743      .  .0112760196090496 -.0036793859203845         .  8.281322 4.3991055  3.618338  3.144884         .  5.034032         . 2 3
4  3 4 18 2589.940956382297 44125.387538 82.52439024390245 60.71698778868395    65.629 14027.01944445482                 .      .  .0103228275064674  .0070930377571425   7.85939  10.69479  4.413094 4.1062236 4.1840177   9.54874         .         . 1 4
4  3 4  2 1258.233827590236 27505.760589 79.15853658536587  53.8696747007171  50.44729 7584.988540022641                 .  1.328  .0163478079549599  .0121021099706879  7.137465  10.22215  4.371453  3.986568  3.920929  8.933927         .  1.763584 1 4
4  3 4  4 1738.513361563551 28145.942902 79.11463414634147 53.87257779719822  52.31698 8069.160370574379                 .   .876  .0209847219146922   .012844842953887  7.460786 10.245158  4.370898 3.9866216  3.957321  8.995805         .   .767376 1 4
4  3 4 14 2608.203705628265 39528.473644 82.21951219512196 57.32435107837141  59.84876 12600.09625876144                 .      .  .0086371549786183  .0169947967987992  7.866417 10.584777  4.409393 4.0487256 4.0918207   9.44146         .         . 1 4
4  3 4  9  2782.95280042322 35102.870428 81.21463414634148 53.93670718839765  52.47552 9943.590106139562                 .      .  .0281286194914787  .0182991075146046  7.931268 10.466038 4.3970957  3.987811  3.960347  9.204683         .         . 1 4
4  3 4  5 2171.545267717935 29038.567562 80.16341463414635  53.8212269776174  53.45763  8348.29778839938                 .      .  .0214208964640242  .0157395336011594  7.683194  10.27638  4.384067  3.985668 3.9788895  9.029813         .         . 1 4
4  3 4 10 784.4748113961016 34693.236376 81.41463414634147 54.16892216436289   52.7731 10761.14805910768                 .      .  .0008762047815745  .0197278870299619  6.665014   10.4543  4.399555 3.9921074 3.9660015  9.283697         .         . 1 4
4  3 4 17 2726.451174643621 42067.267459 82.52439024390245 60.07595326388368  64.72768 13448.48473396771                 .      .  .0018333486112385  .0109495639383947  7.910756 10.647025  4.413094 4.0956097  4.170189  9.506621         .         . 1 4
4  3 4 12 2821.429758574704 37447.949543 82.11463414634147 55.33524753178062  55.62573 11540.33461066631                 .      .  .0211159795174997  .0151894553742808  7.944999 10.530707 4.4081163   4.01341  4.018646  9.353603         .         . 1 4
4  3 4  6  2474.42986554262 30504.058784 80.16341463414635 53.76490720211996  53.88233  8762.59592629184                 .   .521  .0174586936380481  .0189494296156951  7.813766 10.325615  4.384067  3.984621 3.9868026  9.078247         .   .271441 1 4
4  3 4  7   2832.2680075115 32441.180776 80.81219512195123 53.83190536965667  53.87542    9172.743864414                 .   .465  .0167512449608728  .0190892485688861  7.948833 10.387184  4.392128  3.985866  3.986674  9.123992         .   .216225 1 4
4  3 4  3    1299.896204639 28528.156107 79.26097560975612 53.89778795762793  50.25169  8072.04177047565                 .  1.264   .019234122872706  .0114059042598852   7.17004 10.258647  4.372746 3.9870894  3.917044  8.996161         .  1.597696 1 4
4  3 4 16 2415.870013238256 40840.848298  82.3219512195122  59.3207255978095  62.78593 13061.72010266636                 .      .  .0003751438051254  .0139367805857881  7.789815 10.617438  4.410638 4.0829587  4.139731  9.477441         .         . 1 4
4  3 4 13 2446.359872901854 37684.198067 81.96829268292684 56.25937341808045  57.90901 11817.01082984986                 .      .  .0195419531613507  .0160624022856062  7.802356 10.536996 4.4063325 4.0299726  4.058873 9.3772955         .         . 1 4
4  3 4 15 2840.687962651603 40144.059485 82.67073170731709 58.38098934232916  61.51048 12931.60588190305                 .      .  .0050775882293796  .0130965038962271  7.951802  10.60023 4.4148655 4.0669904 4.1192074   9.46743         .         . 1 4
4  3 4  1 1396.273983172584 26098.315685 79.05609756097562 53.76192350669626  50.60308    7197.915465923                 .   .928   .016759598872093  .0123431530381812  7.241562 10.169626 4.3701577 3.9845655 3.9240124  8.881547         .   .861184 1 4
4  3 4  8 2921.006323006394 34095.407473 81.11219512195123 53.86296817437313  52.94754  9568.87610729745                 .   .539  .0148799805953858  .0191699359700687  7.979683 10.436918 4.3958335  3.986443  3.969302  9.166271         .   .290521 1 4
4  3 4 11 784.3284534958414 35909.162325 81.66341463414635 54.63090591788482  54.88172   11144.767619187                 .      .  .0153112270420924   .015618948693472  6.664828 10.488748  4.402606    4.0006 4.0051804  9.318726         .         . 1 4
5  4 5 13 1335.776172287351 43359.541048 80.53902439024391 52.09539734068673         . 10636.96260989536                 . 30.114   .020084909216701  .0168368897230606  7.197268 10.677282  4.388742 3.9530766         .   9.27209         .   906.853 1 5
5  4 5 14 1491.196823435077 44993.667838 80.49024390243903 52.13209520800223  61.38684 11109.38652588058                 . 27.374   .015047209800535  .0162571879724763  7.307334 10.714277  4.388136  3.953781 4.1171956  9.315546         .  749.3359 1 5
5  4 5 10  1391.87131810585 37472.754357 79.83658536585368  51.5319812559294         . 9984.240670879079                 . 26.803  .0031273762987172  .0194335897305231  7.238404  10.53137  4.379982 3.9422026         .  9.208763         .  718.4008 1 5
5  4 5 12 1452.951052010811 42541.513126 80.43658536585367 52.00975112225448         . 10491.58796713412                 . 27.424  .0207517452479837  .0158413971907484  7.281352 10.658236 4.3874693  3.951431         .  9.258329         .  752.0758 1 5
5  4 5  9 1547.202069436113 38432.448211 79.73658536585367 51.20103956068923         . 9301.805440508331                 .  24.26  .0262838174873985  .0162452817640648  7.344203 10.556658 4.3787284   3.93576         .  9.137964         .  588.5476 1 5
5  4 5 18 1204.043064615385 52055.309073 80.99024390243903 53.42641775393285  70.24665 13040.37547587723                 . 24.614  .0150949655801608  .0108523580290558  7.093441 10.860062 4.3943286  3.978305 4.2520127  9.475805         .   605.849 1 5
5  4 5  6 1362.038380722494 32236.740986 78.93170731707318  49.8912304037017         .  8457.95373249682                 . 10.684  .0154690965159041  .0150897838059445  7.216738 10.380862  4.368583  3.909845         .  9.042863         . 114.14786 1 5
5  4 5 17  1185.01576509998 49515.862019 80.99024390243903 52.91457286992035  69.58059 12409.17018058159                 . 25.274  .0049174862477081  .0140192098291109  7.077511 10.810048 4.3943286  3.968679 4.2424855  9.426191         .  638.7751 1 5
5  4 5  5 1293.688722683263 31712.774026 78.68048780487807  49.4440472933971         .   8224.7079436431                 . 11.208  .0166573340932676  .0129291832751804  7.165253 10.364475  4.365395  3.900842         .  9.014898         . 125.61926 1 5
5  4 5 15 1501.359219584478 47011.280402 81.09024390243904 52.24468345842248  65.50391 11615.07704892214                 . 26.036  .0090679794851568  .0140098664351036  7.314126 10.758142 4.3955626  3.955938   4.18211   9.36006         .  677.8733 1 5
5  4 5 11 1409.560251283583  39673.86048 79.98780487804879 51.79374579978381         .  10274.3396485056                 . 26.976  .0110380916115812   .016727598171613  7.251033 10.588448  4.381874 3.9472694         .  9.237405         .  727.7046 1 5
5  4 5  4  1135.45955798965  30235.93514 78.38048780487806 48.94460142118769         . 8022.500670696201                 . 14.179  .0103422776551069  .0126830983466294  7.034793 10.316787  4.361575  3.890689         . 8.9900055         . 201.04404 1 5
5  4 5  1 811.1997167111933 27454.769488 77.92682926829269  47.4073731274062         . 6969.942329918561                 . 14.959  .0144026818676794  .0131837497343991  6.698514 10.220295   4.35577  3.858778         .  8.849362         .  223.7717 1 5
5  4 5  8 1423.937535497493 36822.840138 79.53414634146343 50.80302623158958         .  8864.73053482212                 . 22.816  .0229834179696226  .0144902093805174  7.261181 10.513874 4.3761864  3.927956         .  9.089836         .  520.5699 1 5
5  4 5  3 895.9787058789228  29504.28924 78.22926829268293 48.42843557769053         .   7683.5070038808                 . 15.067  .0142080560518857  .0137202259852999  6.797916  10.29229  4.359644  3.880087         .  8.946832         .  227.0145 1 5
5  4 5  7 1343.923240878634  34630.81647  79.1317073170732 50.36474055945103         . 8663.245048135199                 . 21.857  .0157742825864226  .0153030667355894  7.203349   10.4525  4.371114  3.919291         .  9.066845         .  477.7285 1 5
5  4 5  2 810.1438708049825 28670.377684 78.32926829268293 47.91595923048067         . 7284.569561950721                 . 15.441  .0198385693617829  .0126519650595459  6.697212  10.26362 4.3609214  3.869449         .  8.893514         .  238.4245 1 5
5  4 5 16 1219.145730014433 47683.547301 80.64146341463415  52.5216312802673  67.74687 11855.08352997462                 . 26.715  .0051442053951781  .0151979870723915  7.105906 10.772342 4.3900127  3.961225 4.2157784  9.380512         .  713.6912 1 5
6  5 6  3 959.1939796638943 28716.197174 80.22926829268295 49.43872681646052  55.55179 6704.944878157261                 . 24.506  .0246532319171164  .0219690081457158  6.866093 10.265217  4.384888  3.900734  4.017316    8.8106         .   600.544 1 6
6  5 6 17 1891.892866830823 39178.403316 83.24390243902438 55.85919803881293  60.93733 11087.87992246116                 . 33.063 -.0009401665691573  .0146436546265775  7.545333  10.57588  4.421775 4.0228343  4.109846  9.313608         .  1093.162 1 6
6  5 6 10 1947.548119890621 34329.471244 81.63658536585366 52.31357727136171  66.54997   9305.0031806862                 . 30.838  .0077476813138738  .0229208944313563  7.574327  10.44376 4.4022775  3.957256  4.197953  9.138308         .  950.9822 1 6
6  5 6 11 2054.935204076115 34831.193927 82.03658536585367 52.68488148543309   65.7743  9447.61304075948                 . 30.225  .0152551602118248   .020056957465658     7.628 10.458268 4.4071655 3.9643285  4.186229  9.153518         .  913.5506 1 6
6  5 6 18 1861.765214227288 41200.047746 83.24390243902438 56.18840007684454    61.933 11595.34143763424                 . 32.098  .0122653316645808  .0088943558551596   7.52928 10.626195  4.421775 4.0287104 4.1260533  9.358358         . 1030.2816 1 6
6  5 6 15 2441.995478139681 36194.916674 83.09024390243904 54.97990714025158  61.70275 10266.32616541336                 . 31.311  .0024104742982677  .0186845472727478  7.800571 10.496674  4.419927  4.006968 4.1223283  9.236625         .  980.3787 1 6
6  5 6  1 692.4684453199379 27076.174998 79.77804878048782  48.3877359861389  49.81127 6140.064204296459                 .  2.393  .0253768532095005  .0298081051900514  6.540263  10.20641 4.3792486 3.8792465  3.908241   8.72259         .  5.726449 1 6
6  5 6  7 1657.342112757711 32262.115849 81.28292682926829 51.57928339241149   66.1078  7839.37153014851                 . 28.458  .0209084391012755  .0242301474921842  7.412971  10.38165  4.397936   3.94312 4.1912866  8.966914         .  809.8578 1 6
6  5 6  8 1557.704663259427 33905.682103 81.43414634146342 51.87262622314731  66.68297  8184.15354602214                 . 37.653    .01829741122024  .0228415044581682  7.350969 10.431338 4.3997946  3.948791 4.1999497  9.009955         . 1417.7484 1 6
6  5 6  2 771.8497527824046 28042.643168 80.12682926829268 48.85809342154929  52.87731 6431.580210580799                 .   .954  .0278516542713555  .0244126306710655   6.64879 10.241482 4.3836107   3.88892 3.9679744  8.768975         .   .910116 1 6
end
label values id id
label def id 1 "AUS", modify
label def id 2 "BRA", modify
label def id 3 "CHINA", modify
label def id 4 "FRA", modify
label def id 5 "GER", modify
label def id 6 "ITA", modify
label values index index
label def index 1 "1", modify
label def index 2 "10", modify
label def index 3 "2", modify
label def index 4 "3", modify
label def index 5 "4", modify
label def index 10 "9", modify
label values country country
label def country 1 "Australia", modify
label def country 2 "Brazil", modify
label def country 3 "China", modify
label def country 4 "France", modify
label def country 5 "Germany", modify
label def country 6 "Italy", modify
label values Year Year
label def Year 1 "2000", modify
label def Year 2 "2001", modify
label def Year 3 "2002", modify
label def Year 4 "2003", modify
label def Year 5 "2004", modify
label def Year 6 "2005", modify
label def Year 7 "2006", modify
label def Year 8 "2007", modify
label def Year 9 "2008", modify
label def Year 10 "2009", modify
label def Year 11 "2010", modify
label def Year 12 "2011", modify
label def Year 13 "2012", modify
label def Year 14 "2013", modify
label def Year 15 "2014", modify
label def Year 16 "2015", modify
label def Year 17 "2016", modify
label def Year 18 "2017", modify

[Carlo Lazzaro]

Michael:
the main issue there is the number of missing values:

. foreach var of varlist id-CG {
  2. count if `var'==.
  3.   }
  0
  0
  0
  0
  23
  0
  0
  0
  31
  37
  46
  43
  0
  0
  23
  0
  0
  0
  31
  37
  46
  43
  0
  0

.

A second source of concern is the scant between panel variation (conditional on the missing values):

. xtset id Year
       panel variable:  id (unbalanced)
        time variable:  Year, 1 to 18, but with gaps
                delta:  1 unit

. xtreg logPM logGDP logLE logDEP logEDU logSOC logFD FMS FMSSQ IN
insufficient observations
r(2001);

. xtreg logPM logGDP logLE logDEP logEDU logSOC logFD FMS FMSSQ IN, fe
note: logLE omitted because of collinearity
note: logDEP omitted because of collinearity
note: logEDU omitted because of collinearity
note: logSOC omitted because of collinearity
note: logFD omitted because of collinearity
note: FMS omitted because of collinearity
note: FMSSQ omitted because of collinearity
note: IN omitted because of collinearity

Fixed-effects (within) regression               Number of obs     =          2
Group variable: id                              Number of groups  =          1

R-sq:                                           Obs per group:
     within  = 1.0000                                         min =          2
     between =      .                                         avg =        2.0
     overall = 1.0000                                         max =          2

                                                F(1,0)            =          .
corr(u_i, Xb)  =      .                         Prob > F          =          .

------------------------------------------------------------------------------
       logPM |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      logGDP |  -2.392099          .        .       .            .           .
       logLE |          0  (omitted)
      logDEP |          0  (omitted)
      logEDU |          0  (omitted)
      logSOC |          0  (omitted)
       logFD |          0  (omitted)
         FMS |          0  (omitted)
       FMSSQ |          0  (omitted)
          IN |          0  (omitted)
       _cons |   33.33147          .        .       .            .           .
-------------+----------------------------------------------------------------
     sigma_u |          .
     sigma_e |          .
         rho |          .   (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(0, 0) = .                           Prob > F =      .

If your dataset cannot be improved collecting the missing values or imputing them after a careful diagnosis of the underlying misssing mechanism), I suspect that you cannot go any far with your analysis.

[Scott Merryman]

Because you have a lot of missing values. For example, country 2 has all missing values for logSOC so that country would be dropped:

. l  logPM logGDP logLE logDEP logEDU  logSOC logFD FMS FMSSQ IN if CG == 2

     +----------------------------------------------------------------------------------------------------------+
     |    logPM     logGDP      logLE     logDEP     logEDU   logSOC      logFD      FMS      FMSSQ          IN |
     |----------------------------------------------------------------------------------------------------------|
 19. |        .   9.653283   4.306885   3.808429   3.357791        .   4.370117        .          .   .05403553 |
 20. |        .   9.502741   4.289994   3.865255   3.029366        .   4.255463        .          .   .05678594 |
 21. |        .   9.311505    4.27522   3.913547   2.949008        .    4.09656        .          .   .06869537 |
 22. |        .    9.62455   4.302997   3.821165    3.24446        .   4.341534        .          .   .06636369 |
 23. |        .   9.573786   4.298903   3.834997    3.18629        .   4.307025        .          .   .05038727 |
     |----------------------------------------------------------------------------------------------------------|
 24. | 5.334834   9.704807   4.314082   3.786725   3.747873        .   4.405579   18.593   345.6996   .06329152 |
 25. |        .   9.259931   4.270131   3.929671   2.873071        .   4.031264        .          .   .06597185 |
 26. | 5.137501   9.670773   4.317408   3.778448    3.82952        .   4.478128   18.308   335.1829   .09029807 |
 27. |        .   9.169847   4.260043   3.962296   2.535954        .   4.007424        .          .   .08450164 |
 28. |        .   9.137444   4.255074     3.9786   2.281271        .   4.071352        .          .   .06840359 |
     |----------------------------------------------------------------------------------------------------------|
 29. |        .   9.115138   4.250151   3.994357   2.026886        .   3.839164        .          .   .07044141 |
 30. | 5.359118   9.658315    4.32355   3.771612   3.893314        .   4.538055   21.264   452.1577   .03446368 |
 31. |        .   9.188625   4.265071   3.945908   2.737782        .   4.034707        .          .    .1471492 |
 32. |        .    9.69048   4.310571   3.796841   3.479197        .   4.364709        .          .   .06204336 |
 33. |        .   9.444037   4.285213   3.880732    3.02146        .   4.224776        .          .   .03641273 |
     |----------------------------------------------------------------------------------------------------------|
 34. |        .   9.498784    4.29456   3.849973   3.110981        .   4.331923        .          .   .04888035 |
 35. |        .   9.369446   4.280271   3.896736   3.006632        .   4.147092        .          .   .04183568 |
 36. | 5.240983   9.641199    4.32055   3.774541   3.871597        .   4.541729   17.222   296.5973   .08739128 |
     +----------------------------------------------------------------------------------------------------------+

[Michael Craig]

Thank you very much for taking the time on this issue.

There are some missing values. Let me explain some background:

PM (dependent variable) is the life insurance amount per capita.
There are 10 countries with data from 2000 to 2017 (annual) on economic and social factors (8x OECD and 2x emerging countries)
2 countries lack some inputs: China and Brazil. Other countries are covered better but there are still some missing values, like for Australia, Japan and Germany.
What is often missing is data on education (logEDU). -> I could drop this variable potentially.
Dropping China and Brazil from the set is possible and would result in no missing values for PM (but I would like to have them included actually if possible).


Would you suggest to drop variables with lots of missing values? (drop logEDU and potentially drop FD and also drop FMS).

Shall I exclude China and Brazil or is there a way around?

However, I cannot drop everything :-(

Data cannot be gathered (not in OECD database)

[Carlo Lazzaro]

Michael:
dropping variables or panels with (too many) missing values is obviously arbitrary (unless missingness is not informative), as you end up with a made-up subsample of the original study population.
That said, I was wondedring whether (some of) those data could not be obtained from country-specific websites.

[Michael Craig]

Carlo,

you suggestion makes perfect sense but in this case time is the ultimate constraint. Gathering the data form other sources would require further assessment on so many technical details for a set of countries. Some data may also not be available or comparable especially regarding China. And Brazil is also so volatile that it can distort the result (I assume only).

And dropping some of the variables (a study on determinants of life insurance demand) is also not that much of a problem, given that education is very ambiguous and the other two variables are more relevant in emerging countries but not in the U.S. Germany Japan France and the like...

So I think this is now my only option. So I am gonna try it. Thanks for your valuable input, which was a good mix of technical knowledge and a critical stance on the methodological side of the calculation (which is fundamental and can sometimes be forgotten in case of immersion in statistical details). Thanks!

[Michael Craig]

Michael:
dropping variables or panels with (too many) missing values is obviously arbitrary (unless missingness is not informative), as you end up with a made-up subsample of the original study population.
That said, I was wondedring whether (some of) those data could not be obtained from country-specific websites.

Carlo, excluding China and Brazil and variable logFD and optionally logEDU leads to better results, using the xtreg command.

if you have a short hint on how I can perform a GMM regression on the data, this would be of great help.

Any suggestion on GMM is greatly appreciated.

Thanks so much...

[Carlo Lazzaro]

Michael:
see example #11 under -gmm- entry in Stata .pdf manual.