---------------------------------------------------------------------------------------- log: D:\Anands Documents\Working Papers\Devanbu\Data\commit\commit_apache.txt log type: text opened on: 6 Mar 2007, 12:58:14 . . *reads in event history data from event.dta . use event_apache . sort id year month . save run1, replace file run1.dta saved . clear . . *reads in first e-mail data from first_email.dta . use first-email_apache . sort id year month . . *merges event history and first-email data and removes left-censored ids . merge id year month using run1 . drop _merge . drop if first_email < 1999 (43165 observations deleted) . sort id year month . save run2, replace file run2.dta saved . clear . . *reads in patch data from patch.dta . use patch_apache . sort id year month . . *merges event history and patch data . merge id year month using run2 . . drop _merge . sort id year month . save run3, replace file run3.dta saved . clear . . *reads in node attribute data from node.dta . use node_apache . sort id year month . . *merges the two datasets . merge id year month using run3 . drop _merge . drop if commit==. (52869 observations deleted) . . *create event history variables, time is specified on an annual scale . gen ts=calendar-start_date . gen tf=ts+0.08333333 . stset tf, id(id) failure (commit=1) id: id failure event: commit == 1 obs. time interval: (tf[_n-1], tf] exit on or before: failure ------------------------------------------------------------------------------ 50170 total obs. 0 exclusions ------------------------------------------------------------------------------ 50170 obs. remaining, representing 1445 subjects 30 failures in single failure-per-subject data 4180.888 total analysis time at risk, at risk from t = 0 earliest observed entry t = 0 last observed exit t = 5.916708 . *generate additional variables . gen dev_pct=(devs_cum/people_cum)*100 . gen time_trend=calendar-1995 . gen patch_any=0 . replace patch_any=1 if patches_submitted_cum>0 (5024 real changes made) . gen patch_current=0 . replace patch_current=1 if patches_submitted>0 (433 real changes made) . gen success_pct=(patches_committed_cum/patches_submitted_cum)*100 (45146 missing values generated) . replace success_pct=0 if success_pct==. (45146 real changes made) . . *save data file to be used in further analysis . save commit_apache, replace file commit_apache.dta saved . . *compute descriptive statistics . summ Variable | Obs Mean Std. Dev. Min Max -------------+-------------------------------------------------------- id | 50170 1009.121 589.2725 3 2021 year | 50170 2002.497 1.362705 1999 2004 month | 50170 6.681244 3.363393 1 12 calendar | 50170 2002.971 1.357668 1999 2004.833 between_cum | 50170 139.5205 681.5642 0 16522.8 -------------+-------------------------------------------------------- indegree_cum | 50170 2.627885 4.588433 0 55 outdegree_~m | 50170 2.202113 5.104779 0 60 norm_betwe~m | 50170 .0001313 .0006932 0 .0222581 norm_indeg~m | 50170 .0026193 .0049308 0 .087156 norm_outde~m | 50170 .0022006 .0053021 0 .0779817 -------------+-------------------------------------------------------- between_mo~y | 50170 1.565084 18.50959 0 823.202 indegree_m~y | 50170 .1141718 .6817547 0 19 outdegree_~y | 50170 .0978274 .6494395 0 23 norm_betwe~y | 50170 .0002629 .0031069 0 .133673 norm_indeg~y | 50170 .0014672 .0087702 0 .2375 -------------+-------------------------------------------------------- norm_outde~y | 50170 .0012524 .0082811 0 .302632 sent_monthly | 50170 .2700419 1.972773 0 139 sent_cum | 50170 7.343831 18.18124 1 273 people_mon~y | 50170 88.7995 15.09269 57 126 people_cum | 50170 1426.678 360.7431 455 1875 -------------+-------------------------------------------------------- devs_cum | 50170 46.32462 9.760611 3 57 patches_su~d | 50170 .036177 .7811047 0 58 patches_su~m | 50170 .6967112 5.837152 0 299 patches_co~d | 50170 .0073151 .2718025 0 44 patches_co~m | 50170 .123819 1.805193 0 66 -------------+-------------------------------------------------------- patch_mess~s | 50170 .0180985 .3047579 0 28 patch_mess~m | 50170 .3422563 2.510017 0 84 first_email | 50170 2001.128 1.378218 1999 2004.833 start_date | 50170 2001.128 1.378218 1999 2004.833 commit | 50170 .000598 .0244463 0 1 -------------+-------------------------------------------------------- ts | 50170 1.842441 1.350621 0 5.833374 tf | 50170 1.925775 1.350621 .0833333 5.916708 _st | 50170 1 0 1 1 _d | 50170 .000598 .0244463 0 1 _t | 50170 1.925775 1.350621 .0833333 5.916708 -------------+-------------------------------------------------------- _t0 | 50170 1.84244 1.35062 0 5.833333 dev_pct | 50170 3.288424 .3946067 .6437768 4.166667 time_trend | 50170 7.970587 1.357668 4 9.833374 patch_any | 50170 .1001395 .3001889 0 1 patch_curr~t | 50170 .0086307 .0925005 0 1 -------------+-------------------------------------------------------- success_pct | 50170 1.135625 8.980703 0 100 . correlate (obs=50170) | id year month calendar betwee~m indegr~m outdeg~m norm_b~m -------------+------------------------------------------------------------------------ id | 1.0000 year | -0.0179 1.0000 month | 0.0022 -0.1208 1.0000 calendar | -0.0175 0.9788 0.0852 1.0000 between_cum | -0.0578 0.0402 0.0046 0.0413 1.0000 indegree_cum | -0.0561 -0.0214 -0.0004 -0.0216 0.6946 1.0000 outdegree_~m | -0.0594 -0.0198 -0.0005 -0.0199 0.7586 0.8786 1.0000 norm_betwe~m | -0.0609 -0.0912 -0.0044 -0.0924 0.7901 0.6308 0.6730 1.0000 norm_indeg~m | -0.0503 -0.2073 -0.0112 -0.2104 0.5811 0.9190 0.7960 0.6973 norm_outde~m | -0.0536 -0.1656 -0.0083 -0.1679 0.6541 0.8229 0.9318 0.7461 between_mo~y | -0.0122 -0.0506 -0.0046 -0.0517 0.1939 0.2227 0.2234 0.2870 indegree_m~y | -0.0114 -0.1240 -0.0141 -0.1274 0.1708 0.2870 0.2436 0.2633 outdegree_~y | -0.0186 -0.1070 -0.0129 -0.1100 0.2191 0.2937 0.3187 0.3175 norm_betwe~y | -0.0123 -0.0498 -0.0010 -0.0502 0.1945 0.2209 0.2185 0.2886 norm_indeg~y | -0.0114 -0.1259 -0.0088 -0.1282 0.1713 0.2844 0.2402 0.2638 norm_outde~y | -0.0193 -0.1083 -0.0080 -0.1104 0.2230 0.2944 0.3186 0.3216 sent_monthly | -0.0058 -0.1014 -0.0107 -0.1040 0.1469 0.2404 0.2213 0.2396 sent_cum | -0.0499 -0.0039 0.0005 -0.0038 0.6504 0.8742 0.8408 0.5709 people_mon~y | 0.0015 -0.1885 -0.1956 -0.2296 -0.0125 0.0023 0.0024 -0.0028 people_cum | -0.0179 0.9781 0.0762 0.9975 0.0411 -0.0218 -0.0202 -0.0931 devs_cum | -0.0179 0.9460 0.0644 0.9629 0.0380 -0.0222 -0.0199 -0.1003 patches_su~d | 0.0045 -0.0549 0.0019 -0.0547 0.0285 0.0785 0.0627 0.0569 patches_su~m | -0.0197 -0.0760 0.0641 -0.0630 0.0654 0.2184 0.1548 0.1085 patches_co~d | 0.0065 -0.0276 0.0033 -0.0270 0.0181 0.0599 0.0480 0.0272 patches_co~m | 0.0050 -0.0564 0.0416 -0.0480 0.0483 0.1395 0.1062 0.0758 patch_mess~s | 0.0051 -0.0588 -0.0002 -0.0591 0.0303 0.1000 0.0778 0.0509 patch_mess~m | -0.0182 -0.0798 0.0719 -0.0653 0.0836 0.2361 0.1688 0.1046 first_email | -0.0339 0.5029 0.0384 0.5127 -0.0771 -0.1814 -0.1711 -0.1259 start_date | -0.0339 0.5029 0.0384 0.5127 -0.0771 -0.1814 -0.1711 -0.1259 commit | 0.0031 -0.0143 -0.0057 -0.0155 0.0601 0.0974 0.0808 0.0821 ts | 0.0169 0.4707 0.0465 0.4821 0.1202 0.1634 0.1546 0.0356 tf | 0.0169 0.4707 0.0465 0.4821 0.1202 0.1634 0.1546 0.0356 _st | . . . . . . . . _d | 0.0031 -0.0143 -0.0057 -0.0155 0.0601 0.0974 0.0808 0.0821 _t | 0.0169 0.4707 0.0465 0.4821 0.1202 0.1634 0.1546 0.0356 _t0 | 0.0169 0.4707 0.0465 0.4821 0.1202 0.1634 0.1546 0.0356 dev_pct | 0.0059 -0.3770 -0.0315 -0.3849 -0.0183 0.0095 0.0116 0.0117 time_trend | -0.0175 0.9788 0.0852 1.0000 0.0413 -0.0216 -0.0199 -0.0924 patch_any | -0.0517 -0.0626 0.1176 -0.0386 0.1345 0.2869 0.2197 0.1082 patch_curr~t | -0.0038 -0.0693 -0.0069 -0.0710 0.0331 0.1152 0.0883 0.0471 success_pct | -0.0285 -0.0175 0.0422 -0.0088 0.0422 0.1224 0.0985 0.0295 | norm_i~m norm_o~m betwee~y indegr~y outdeg~y norm_b~y norm_i~y norm_o~y -------------+------------------------------------------------------------------------ norm_indeg~m | 1.0000 norm_outde~m | 0.8711 1.0000 between_mo~y | 0.2701 0.2713 1.0000 indegree_m~y | 0.3641 0.3064 0.6874 1.0000 outdegree_~y | 0.3598 0.3899 0.7483 0.8044 1.0000 norm_betwe~y | 0.2701 0.2659 0.9361 0.6558 0.7112 1.0000 norm_indeg~y | 0.3645 0.3042 0.6613 0.9843 0.7836 0.6736 1.0000 norm_outde~y | 0.3628 0.3917 0.7256 0.7906 0.9844 0.7334 0.7945 1.0000 sent_monthly | 0.3068 0.2844 0.6105 0.8320 0.8069 0.5712 0.8122 0.7898 sent_cum | 0.7808 0.7695 0.2219 0.2930 0.3107 0.2145 0.2870 0.3083 people_mon~y | 0.0071 0.0063 0.0263 0.0396 0.0380 -0.0045 0.0093 0.0106 people_cum | -0.2114 -0.1691 -0.0500 -0.1262 -0.1092 -0.0490 -0.1273 -0.1099 devs_cum | -0.2208 -0.1750 -0.0674 -0.1427 -0.1254 -0.0688 -0.1465 -0.1284 patches_su~d | 0.1088 0.0877 0.1845 0.3287 0.2938 0.1810 0.3292 0.2961 patches_su~m | 0.2573 0.1842 0.2023 0.2931 0.2463 0.2023 0.2975 0.2498 patches_co~d | 0.0708 0.0593 0.1157 0.2369 0.2068 0.1043 0.2288 0.1999 patches_co~m | 0.1624 0.1257 0.1702 0.2551 0.2266 0.1623 0.2510 0.2232 patch_mess~s | 0.1265 0.1013 0.2108 0.3975 0.3423 0.1977 0.3900 0.3379 patch_mess~m | 0.2529 0.1834 0.1749 0.2975 0.2449 0.1708 0.2979 0.2454 first_email | -0.2534 -0.2269 0.0051 0.0076 -0.0030 0.0026 0.0053 -0.0049 start_date | -0.2534 -0.2269 0.0051 0.0076 -0.0030 0.0026 0.0053 -0.0049 commit | 0.1121 0.0976 0.2051 0.2495 0.2386 0.1980 0.2437 0.2311 ts | 0.0471 0.0627 -0.0571 -0.1357 -0.1075 -0.0532 -0.1342 -0.1059 tf | 0.0471 0.0627 -0.0571 -0.1357 -0.1075 -0.0532 -0.1342 -0.1059 _st | . . . . . . . . _d | 0.1121 0.0976 0.2051 0.2495 0.2386 0.1980 0.2437 0.2311 _t | 0.0471 0.0627 -0.0571 -0.1357 -0.1075 -0.0532 -0.1342 -0.1059 _t0 | 0.0471 0.0627 -0.0571 -0.1357 -0.1075 -0.0532 -0.1342 -0.1059 dev_pct | 0.0417 0.0411 -0.0435 -0.0226 -0.0241 -0.0519 -0.0299 -0.0305 time_trend | -0.2104 -0.1679 -0.0517 -0.1274 -0.1100 -0.0502 -0.1282 -0.1104 patch_any | 0.2576 0.1952 0.1001 0.1701 0.1575 0.1000 0.1708 0.1585 patch_curr~t | 0.1356 0.1046 0.1815 0.3678 0.3065 0.1702 0.3592 0.3028 success_pct | 0.1064 0.0854 0.0644 0.1239 0.1069 0.0556 0.1188 0.1018 | sent_m~y sent_cum people~y people~m devs_cum ~bmitted patche.. ~mmitted -------------+------------------------------------------------------------------------ sent_monthly | 1.0000 sent_cum | 0.3070 1.0000 people_mon~y | 0.0320 0.0065 1.0000 people_cum | -0.1035 -0.0038 -0.2108 1.0000 devs_cum | -0.1133 -0.0019 -0.1652 0.9578 1.0000 patches_su~d | 0.4163 0.1143 0.0028 -0.0548 -0.0562 1.0000 patches_su~m | 0.3087 0.2653 -0.0031 -0.0627 -0.0697 0.3636 1.0000 patches_co~d | 0.2759 0.0887 0.0125 -0.0277 -0.0222 0.6471 0.2583 1.0000 patches_co~m | 0.2674 0.1777 0.0051 -0.0477 -0.0514 0.3128 0.7449 0.3505 patch_mess~s | 0.5011 0.1474 0.0124 -0.0596 -0.0565 0.8022 0.3741 0.5766 patch_mess~m | 0.3283 0.3020 0.0004 -0.0655 -0.0670 0.3645 0.8559 0.2840 first_email | 0.0079 -0.1262 -0.0948 0.5138 0.4987 -0.0112 -0.0509 -0.0038 start_date | 0.0079 -0.1262 -0.0948 0.5138 0.4987 -0.0112 -0.0509 -0.0038 commit | 0.3285 0.1389 0.0017 -0.0155 -0.0141 0.1419 0.1343 0.0983 ts | -0.1126 0.1249 -0.1341 0.4784 0.4590 -0.0436 -0.0114 -0.0232 tf | -0.1126 0.1249 -0.1341 0.4784 0.4590 -0.0436 -0.0114 -0.0232 _st | . . . . . . . . _d | 0.3285 0.1389 0.0017 -0.0155 -0.0141 0.1419 0.1343 0.0983 _t | -0.1126 0.1249 -0.1341 0.4784 0.4590 -0.0436 -0.0114 -0.0232 _t0 | -0.1126 0.1249 -0.1341 0.4784 0.4590 -0.0436 -0.0114 -0.0232 dev_pct | -0.0047 0.0088 0.1467 -0.4149 -0.1485 0.0124 -0.0064 0.0259 time_trend | -0.1040 -0.0038 -0.2296 0.9975 0.9629 -0.0547 -0.0630 -0.0270 patch_any | 0.1606 0.2998 -0.0124 -0.0390 -0.0407 0.1388 0.3578 0.0807 patch_curr~t | 0.3857 0.1480 0.0280 -0.0710 -0.0699 0.4964 0.2974 0.2884 success_pct | 0.1188 0.1444 0.0048 -0.0084 -0.0082 0.1006 0.2211 0.1399 | patche.. patch_~s patch_~m first_~l start_~e commit ts tf -------------+------------------------------------------------------------------------ patches_co~m | 1.0000 patch_mess~s | 0.3457 1.0000 patch_mess~m | 0.7328 0.4600 1.0000 first_email | -0.0221 -0.0076 -0.0482 1.0000 start_date | -0.0221 -0.0076 -0.0482 1.0000 1.0000 commit | 0.1338 0.1564 0.1344 -0.0052 -0.0052 1.0000 ts | -0.0257 -0.0517 -0.0165 -0.5051 -0.5051 -0.0103 1.0000 tf | -0.0257 -0.0517 -0.0165 -0.5051 -0.5051 -0.0103 1.0000 1.0000 _st | . . . . . . . . _d | 0.1338 0.1564 0.1344 -0.0052 -0.0052 1.0000 -0.0103 -0.0103 _t | -0.0257 -0.0517 -0.0165 -0.5051 -0.5051 -0.0103 1.0000 1.0000 _t0 | -0.0257 -0.0517 -0.0165 -0.5051 -0.5051 -0.0103 1.0000 1.0000 dev_pct | -0.0015 0.0286 0.0147 -0.1947 -0.1947 0.0098 -0.1882 -0.1882 time_trend | -0.0480 -0.0591 -0.0653 0.5127 0.5127 -0.0155 0.4821 0.4821 patch_any | 0.2056 0.1780 0.4088 -0.0517 -0.0517 0.0625 0.0140 0.0140 patch_curr~t | 0.2576 0.6365 0.3649 0.0043 0.0043 0.1211 -0.0757 -0.0757 success_pct | 0.3689 0.1330 0.2635 0.0131 0.0131 0.0659 -0.0222 -0.0222 | _st _d _t _t0 dev_pct time_t~d patch_~y patch_~t -------------+------------------------------------------------------------------------ _st | . _d | . 1.0000 _t | . -0.0103 1.0000 _t0 | . -0.0103 1.0000 1.0000 dev_pct | . 0.0098 -0.1882 -0.1882 1.0000 time_trend | . -0.0155 0.4821 0.4821 -0.3849 1.0000 patch_any | . 0.0625 0.0140 0.0140 0.0070 -0.0386 1.0000 patch_curr~t | . 0.1211 -0.0757 -0.0757 0.0217 -0.0710 0.2797 1.0000 success_pct | . 0.0659 -0.0222 -0.0222 0.0011 -0.0088 0.3791 0.1695 | succes~t -------------+--------- success_pct | 1.0000 . . *plot Kaplan-Meier survivor function, time axis in years . sts graph, failure _d: commit == 1 analysis time _t: tf id: id . graph save km_commit_apache,replace (file km_commit_apache.gph saved) . graph export km_commit_apache.eps,replace (file km_commit_apache.eps written in EPS format) . . *plot Nelson-Aalen cumulative hazard function, time axis in years . sts graph,na failure _d: commit == 1 analysis time _t: tf id: id . graph save na_commit_apache,replace (file na_commit_apache.gph saved) . graph export na_commit_apache.eps,replace (file na_commit_apache.eps written in EPS format) . . *plot smoothed hazard function, time axis in years . sts graph,hazard failure _d: commit == 1 analysis time _t: tf id: id . graph save haz_commit_apache,replace (file haz_commit_apache.gph saved) . graph export haz_commit_apache.eps,replace (file haz_commit_apache.eps written in EPS format) . . *erase extraneous files . erase run1.dta . erase run2.dta . erase run3.dta . . clear . log close log: D:\Anands Documents\Working Papers\Devanbu\Data\commit\commit_apache.txt log type: text closed on: 6 Mar 2007, 12:58:38 ----------------------------------------------------------------------------------------