. . . ********** ADJUSTMENTS FOR LARGER SIZE PROBLEMS . set maxvar 100 width 1000 (maxvar and maxobs no longer need be set with this version of Stata) . set matsize 100 . . . ********** READ DATA . * See program stjaggia.asc for explanation of the following command . * You need files jaggia.asc and jaggia.dct in your directory . infile using jaggia.dct dictionary using jaggia.asc { _column(1) docno %16.8f "Document Number" _column(17) weeks %17.8f "Weeks" _column(34) numbids %17.8f "Number of takeover bids (after the first)" _column(51) takeover %17.8f "1 if takeover occurred, 0 otherwise" _newline _column(1) bidprem %16.8f "Bid price / price 14 work days before bid" _column(17) insthold %17.8f "Percentage of stock held by insitutions" _column(34) size %17.8f "Total book value of assets inb $billions " _column(51) leglrest %17.8f "Equals one if legal defense by lawsuit" _newline _column(1) realrest %16.8f "One if proposed changes in asset structure" _column(17) finrest %17.8f "One if proposed changes in ownership struc" _column(34) regulatn %17.8f "One if intervention by fed regulators" _column(57) whtknght %17.8f "One if mgmt invite friendly 3rd-party bid" * For this example the column numbers are redundant. * Also the long labels need not be given. } (126 observations read) . . . ********** DATA TRANSFORMATIONS . gen sizesq = size*size . label variable sizesq "size squared" . . * Code numbids data as 1 or 0 for binary logit . gen dbids=numbids>0 /* equals 1 if numbids>0 and 0 otherwise */ . . * Code numbids data as 1, 2 or 3 for Stata mlogit . * Here y=1 will be numbids=0 . * y=2 will be numbids=1 . * y=3 will be numbids=2 or more . gen ybids = numbids + 1 . replace ybids = 3 if ybids>3 (23 real changes made) . /* use replace here as modifying existing variable */ . . . ******** CHECK DATA: DESCRIPTIVE STATISTICS . describe Contains data obs: 126 vars: 15 size: 8,064 (99.1% of memory free) ------------------------------------------------------------------------------- 1. docno float %9.0g Document Number 2. weeks float %9.0g Weeks 3. numbids float %9.0g Number of takeover bids (after the first) 4. takeover float %9.0g 1 if takeover occurred, 0 otherwise 5. bidprem float %9.0g Bid price / price 14 work days before bid 6. insthold float %9.0g Percentage of stock held by insitutions 7. size float %9.0g Total book value of assets inb $billions 8. leglrest float %9.0g Equals one if legal defense by lawsuit 9. realrest float %9.0g One if proposed changes in asset structure 10. finrest float %9.0g One if proposed changes in ownership struc 11. regulatn float %9.0g One if intervention by fed regulators 12. whtknght float %9.0g One if mgmt invite friendly 3rd-party bid 13. sizesq float %9.0g size squared 14. dbids float %9.0g 15. ybids float %9.0g ------------------------------------------------------------------------------- Sorted by: Note: dataset has changed since last saved . summarize Variable | Obs Mean Std. Dev. Min Max ---------+----------------------------------------------------- docno | 126 82174.41 2251.783 78001 85059 weeks | 126 11.44898 7.711424 2.857 41.429 numbids | 126 1.738095 1.432081 0 10 takeover | 126 1 0 1 1 bidprem | 126 1.346806 .189325 .9426754 2.066366 insthold | 126 .2518175 .1856136 0 .904 size | 126 1.219031 3.096624 .017722 22.169 leglrest | 126 .4285714 .4968472 0 1 realrest | 126 .1825397 .3878308 0 1 finrest | 126 .1031746 .3054011 0 1 regulatn | 126 .2698413 .4456492 0 1 whtknght | 126 .5952381 .4928054 0 1 sizesq | 126 10.99902 59.91479 .0003141 491.4646 dbids | 126 .9285714 .2585675 0 1 ybids | 126 2.357143 .6127223 1 3 . . . ********** LOGIT REGRESSION . * Use /* and */ as command spans two lines . . logit dbids leglrest realrest finrest whtknght /* > */ bidprem insthold size sizesq regulatn Iteration 0: log likelihood = -32.422149 Iteration 1: log likelihood = -28.206786 Iteration 2: log likelihood = -24.798786 Iteration 3: log likelihood = -24.644545 Iteration 4: log likelihood = -24.630887 Iteration 5: log likelihood = -24.623452 Iteration 6: log likelihood = -24.618042 Iteration 7: log likelihood = -24.616656 Iteration 8: log likelihood = -24.616603 Iteration 9: log likelihood = -24.616603 Logit estimates Number of obs = 126 LR chi2(9) = 15.61 Prob > chi2 = 0.0755 Log likelihood = -24.616603 Pseudo R2 = 0.2407 ------------------------------------------------------------------------------ dbids | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- leglrest | .9712906 .9769986 0.994 0.320 -.9435915 2.886173 realrest | -2.722896 .9998005 -2.723 0.006 -4.682469 -.7633233 finrest | -1.466672 1.174169 -1.249 0.212 -3.768001 .8346578 whtknght | 1.192886 .8733564 1.366 0.172 -.5188614 2.904633 bidprem | .8245125 2.483787 0.332 0.740 -4.043621 5.692646 insthold | -1.838749 2.411422 -0.763 0.446 -6.56505 2.887551 size | .3477998 1.019722 0.341 0.733 -1.650819 2.346419 sizesq | .0126493 .1849571 0.068 0.945 -.34986 .3751587 regulatn | -1.141263 .9822149 -1.162 0.245 -3.066369 .7838429 _cons | 2.148372 3.472283 0.619 0.536 -4.657177 8.95392 ------------------------------------------------------------------------------ . . . ********** MULTINOMIAL LOGIT REGRESSION . * Use /* and */ as command spans two lines . . mlogit ybids leglrest realrest finrest whtknght /* > */ bidprem insthold size sizesq regulatn, base(1) Iteration 0: log likelihood = -113.17387 Iteration 1: log likelihood = -97.257288 Iteration 2: log likelihood = -94.068285 Iteration 3: log likelihood = -93.938315 Iteration 4: log likelihood = -93.928321 Iteration 5: log likelihood = -93.923653 Iteration 6: log likelihood = -93.920848 Iteration 7: log likelihood = -93.920078 Iteration 8: log likelihood = -93.920052 Iteration 9: log likelihood = -93.920052 Multinomial regression Number of obs = 126 LR chi2(18) = 38.51 Prob > chi2 = 0.0033 Log likelihood = -93.920052 Pseudo R2 = 0.1701 ------------------------------------------------------------------------------ ybids | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- 2 | leglrest | .7608404 .9915134 0.767 0.443 -1.18249 2.704171 realrest | -2.491699 1.023766 -2.434 0.015 -4.498242 -.4851549 finrest | -1.59277 1.220981 -1.305 0.192 -3.985847 .8003083 whtknght | .688531 .8857705 0.777 0.437 -1.047547 2.424609 bidprem | 2.029602 2.623576 0.774 0.439 -3.112513 7.171717 insthold | -1.374451 2.449291 -0.561 0.575 -6.174972 3.42607 size | .2463185 1.001995 0.246 0.806 -1.717556 2.210193 sizesq | .0112126 .1781473 0.063 0.950 -.3379498 .3603749 regulatn | -1.253124 .9971332 -1.257 0.209 -3.207469 .7012209 _cons | .2118556 3.629646 0.058 0.953 -6.902121 7.325832 ---------+-------------------------------------------------------------------- 3 | leglrest | 1.266351 1.018369 1.244 0.214 -.7296164 3.262319 realrest | -3.009879 1.097278 -2.743 0.006 -5.160504 -.859254 finrest | -1.360264 1.2533 -1.085 0.278 -3.816686 1.096158 whtknght | 1.986737 .9242845 2.149 0.032 .1751729 3.798302 bidprem | -.8765889 2.67741 -0.327 0.743 -6.124217 4.371039 insthold | -2.685882 2.525717 -1.063 0.288 -7.636196 2.264433 size | .5346982 1.011764 0.528 0.597 -1.448323 2.517719 sizesq | -.0004146 .1785617 -0.002 0.998 -.3503891 .34956 regulatn | -.8988701 1.030737 -0.872 0.383 -2.919077 1.121337 _cons | 2.989214 3.691779 0.810 0.418 -4.246539 10.22497 ------------------------------------------------------------------------------ (Outcome ybids==1 is the comparison group) . . . ********** ORDERED LOGIT REGRESSION . * Use /* and */ as command spans two lines . . ologit ybids leglrest realrest finrest whtknght /* > */ bidprem insthold size sizesq regulatn, table Iteration 0: log likelihood = -113.17387 Iteration 1: log likelihood = -99.390361 Iteration 2: log likelihood = -99.030652 Iteration 3: log likelihood = -99.026883 Iteration 4: log likelihood = -99.026882 Ordered logit estimates Number of obs = 126 LR chi2(9) = 28.29 Prob > chi2 = 0.0009 Log likelihood = -99.026882 Pseudo R2 = 0.1250 ------------------------------------------------------------------------------ ybids | Coef. Std. Err. z P>|z| [95% Conf. Interval] ---------+-------------------------------------------------------------------- leglrest | .6810047 .4162756 1.636 0.102 -.1348805 1.49689 realrest | -1.444152 .5618433 -2.570 0.010 -2.545345 -.3429598 finrest | -.3650597 .6492703 -0.562 0.574 -1.637606 .9074867 whtknght | 1.379994 .4080228 3.382 0.001 .580284 2.179704 bidprem | -2.057745 1.020724 -2.016 0.044 -4.058328 -.057162 insthold | -1.206723 1.104672 -1.092 0.275 -3.371841 .9583941 size | .3452522 .2104359 1.641 0.101 -.0671946 .757699 sizesq | -.0131413 .0105102 -1.250 0.211 -.0337408 .0074583 regulatn | -.1334613 .4549199 -0.293 0.769 -1.025088 .7581652 ---------+-------------------------------------------------------------------- _cut1 | -5.03169 1.521626 (Ancillary parameters) _cut2 | -1.664305 1.438983 ------------------------------------------------------------------------------ ybids | Probability Observed ---------|------------------------------------- 1 | Pr( xb+u<_cut1) 0.0714 2 | Pr(_cut1