Hi,
When running the log-logistic AFT regression with the i. command, the regression runs without problems.
However, I want to examine the effect of all the levels of the factor variables, therefore I suppress the constant term and use the ibn. command. Unfortunately, this results in a never-ending process in Stata. I hope someone is able to offer some help.
Below the commands I have used, and the corresponding output.
Output with the use of i.
When using ibn.
Kind regards,
Michael
When running the log-logistic AFT regression with the i. command, the regression runs without problems.
However, I want to examine the effect of all the levels of the factor variables, therefore I suppress the constant term and use the ibn. command. Unfortunately, this results in a never-ending process in Stata. I hope someone is able to offer some help.
Below the commands I have used, and the corresponding output.
Code:
. stset E_Date, failure(AllButDiss==1) id(Strategy_Number) enter(time P_Date) origin(time P_Date)
id: Strategy_Number
failure event: AllButDiss == 1
obs. time interval: (E_Date[_n-1], E_Date]
enter on or after: time P_Date
exit on or before: failure
t for analysis: (time-origin)
origin: time P_Date
------------------------------------------------------------------------------
1,197 total observations
0 exclusions
------------------------------------------------------------------------------
1,197 observations remaining, representing
1,197 subjects
431 failures in single-failure-per-subject data
3,031,231 total analysis time at risk and under observation
at risk from t = 0
earliest observed entry t = 0
last observed exit t = 8,216
. format _origin %td
Code:
. streg i.ComplexityOfStrategy i.Amount_of_addons Rushed2 i.Distance_Class Rushed_Strategy IVA IQA GDPA Hofstede Management_Participation ib(frequent).Entrytype Syndication PE_Experience PF_Experience PE_Experience_Total PF_Experience_Total logPFassets HOT_IPO HOT_MNA i.CountryGroup i.Exitgroup i.IndustryFE, dist(loglogistic)
failure _d: AllButDiss == 1
analysis time _t: (E_Date-origin)
origin: time P_Date
enter on or after: time P_Date
id: Strategy_Number
Fitting constant-only model:
Iteration 0: log likelihood = -794.10373
Iteration 1: log likelihood = -641.39899
Iteration 2: log likelihood = -625.25804
Iteration 3: log likelihood = -622.63158
Iteration 4: log likelihood = -622.62781
Iteration 5: log likelihood = -622.62781
Fitting full model:
Iteration 0: log likelihood = -622.62781 (not concave)
Iteration 1: log likelihood = -352.75977
Iteration 2: log likelihood = -248.90424
Iteration 3: log likelihood = -218.59155
Iteration 4: log likelihood = -216.41335
Iteration 5: log likelihood = -216.39369
Iteration 6: log likelihood = -216.39088
Iteration 7: log likelihood = -216.3904
Iteration 8: log likelihood = -216.39029
Iteration 9: log likelihood = -216.39027
Iteration 10: log likelihood = -216.39026
Loglogistic AFT regression
No. of subjects = 917 Number of obs = 917
No. of failures = 299
Time at risk = 2162758
LR chi2(59) = 812.48
Log likelihood = -216.39026 Prob > chi2 = 0.0000
----------------------------------------------------------------------------------------------------------------------
_t | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-----------------------------------------------------+----------------------------------------------------------------
ComplexityOfStrategy |
Less simple | -.0954882 .0552878 -1.73 0.084 -.2038503 .0128738
Complicated | .0107155 .1176821 0.09 0.927 -.2199372 .2413682
Hardest | .0024944 .1019187 0.02 0.980 -.1972626 .2022514
|
Amount_of_addons |
Two | .0456722 .0675602 0.68 0.499 -.0867434 .1780878
Three | .143727 .0881328 1.63 0.103 -.0290101 .3164641
More | .175721 .090347 1.94 0.052 -.0013558 .3527978
|
Rushed2 | -.2387015 .0614137 -3.89 0.000 -.3590701 -.118333
|
Distance_Class |
Close | -.1921864 .1024587 -1.88 0.061 -.3930018 .008629
Far | -.1300751 .0847157 -1.54 0.125 -.2961148 .0359645
Furthest | -.1107476 .1129013 -0.98 0.327 -.3320302 .1105349
|
Rushed_Strategy | -.144368 .0963647 -1.50 0.134 -.3332394 .0445033
IVA | .0835171 .0710105 1.18 0.240 -.0556609 .2226951
IQA | .1179008 .0664508 1.77 0.076 -.0123404 .2481419
GDPA | .0739022 .0862538 0.86 0.392 -.0951521 .2429566
Hofstede | -.0141526 .0756615 -0.19 0.852 -.1624463 .1341412
Management_Participation | -.0003944 .0739337 -0.01 0.996 -.1453017 .144513
|
Entrytype |
Divisional | .1910839 .0765114 2.50 0.013 .0411243 .3410435
Financial | .0607783 .0732364 0.83 0.407 -.0827625 .2043191
Privatization | 2.336045 1499.755 0.00 0.999 -2937.13 2941.802
Public Private | -.0417583 .1592139 -0.26 0.793 -.3538118 .2702952
Receivership | .1329239 .4155704 0.32 0.749 -.681579 .9474268
|
Syndication | -.065033 .0715985 -0.91 0.364 -.2053634 .0752974
PE_Experience | -.0706476 .0863322 -0.82 0.413 -.2398557 .0985604
PF_Experience | -.0175077 .0674334 -0.26 0.795 -.1496746 .1146593
PE_Experience_Total | -.0020519 .0027999 -0.73 0.464 -.0075396 .0034359
PF_Experience_Total | -.0128685 .0117465 -1.10 0.273 -.0358913 .0101542
logPFassets | .0104936 .0133145 0.79 0.431 -.0156024 .0365896
HOT_IPO | -.035915 .0673371 -0.53 0.594 -.1678933 .0960633
HOT_MNA | -1.332052 .1012851 -13.15 0.000 -1.530567 -1.133537
|
CountryGroup |
United Kingdom | .0518508 .1062872 0.49 0.626 -.1564683 .2601698
Asia | -.2274857 .2098015 -1.08 0.278 -.638689 .1837177
Australia | -.2815091 .2057906 -1.37 0.171 -.6848514 .1218331
United States | -.1388959 .1206453 -1.15 0.250 -.3753563 .0975646
Western Europe | .0622211 .1006128 0.62 0.536 -.1349763 .2594185
Rest of Europe | .1227931 .1191162 1.03 0.303 -.1106704 .3562566
Rest of world | -.6918487 .2667168 -2.59 0.009 -1.214604 -.1690933
Canada | .1686683 .1844434 0.91 0.360 -.1928342 .5301707
|
Exitgroup |
Post Dot-com | .5940238 .3330951 1.78 0.075 -.0588305 1.246878
Buyout Growth | .2989711 .3477749 0.86 0.390 -.3826552 .9805974
Buyout peak | 1.198395 .3562699 3.36 0.001 .5001184 1.896671
Financial Crisis | .6131937 .343153 1.79 0.074 -.0593738 1.285761
Post-Financial Crisis | 2.238238 .3456952 6.47 0.000 1.560688 2.915789
Recent years | 2.399773 .3346468 7.17 0.000 1.743877 3.055669
|
IndustryFE |
Administrative and Support Service Activities | .1317598 .1558593 0.85 0.398 -.1737189 .4372385
Arts, Entertainment adn Recreation | -.1493985 .1943511 -0.77 0.442 -.5303196 .2315227
Constrution | -.2964692 .2165589 -1.37 0.171 -.7209169 .1279784
Education | .1146167 .226205 0.51 0.612 -.328737 .5579704
Electricity, Gas, Steam, and AC supply | -.1123549 .2480989 -0.45 0.651 -.5986199 .3739101
Financial and Insurance Activities | -.0441494 .198536 -0.22 0.824 -.4332728 .3449741
Human Health and Social Work Activities | .0164787 .1491182 0.11 0.912 -.2757875 .3087449
Information and Communication | -.0435149 .1401087 -0.31 0.756 -.3181228 .2310931
Manufacturing | .127394 .1372691 0.93 0.353 -.1416484 .3964365
Other Service Activities | -.0300531 .222353 -0.14 0.892 -.4658569 .4057507
Professional, Scientific, and Technical Motorcycles | -.0745649 .1480577 -0.50 0.615 -.3647528 .2156229
Public Administration adn Defence | 2.759867 407.9724 0.01 0.995 -796.8514 802.3712
Real Estate Activities | -.1176 .2303223 -0.51 0.610 -.5690234 .3338233
Transport and Storage | -.1036479 .176026 -0.59 0.556 -.4486525 .2413568
Water Supply | -.6442967 .2487774 -2.59 0.010 -1.131891 -.156702
Wholesale and Retail Trade | .188224 .1475216 1.28 0.202 -.100913 .477361
|
_cons | 6.542539 .3996965 16.37 0.000 5.759148 7.325929
-----------------------------------------------------+----------------------------------------------------------------
/lngamma | -1.447804 .0479036 -30.22 0.000 -1.541694 -1.353915
-----------------------------------------------------+----------------------------------------------------------------
gamma | .2350859 .0112615 .2140183 .2582273
Code:
. streg ibn.ComplexityOfStrategy ibn.Amount_of_addons Rushed2 ibn.Distance_Class Rushed_Strategy IVA IQA GDPA Hofstede Management_Participation ib(frequent).Entrytype Syndication PE_Experience PF_Experience PE_Experience_Total PF_Experience_Total logPFassets HOT_IPO HOT_MNA ibn.CountryGroup ibn.Exitgroup ibn.IndustryFE, noconstant distribution(loglogistic)
failure _d: AllButDiss == 1
analysis time _t: (E_Date-origin)
origin: time P_Date
enter on or after: time P_Date
id: Strategy_Number
note: 4.Amount_of_addons omitted because of collinearity
note: 4.Distance_Class omitted because of collinearity
note: 9.CountryGroup omitted because of collinearity
note: 7.Exitgroup omitted because of collinearity
note: 17.IndustryFE omitted because of collinearity
Fitting full model:
Iteration 0: log likelihood = -1277.4143 (not concave)
Iteration 1: log likelihood = -964.59332 (not concave)
Iteration 2: log likelihood = -716.47672 (not concave)
Iteration 3: log likelihood = -576.60045 (not concave)
Iteration 4: log likelihood = -477.67092 (not concave)
Iteration 5: log likelihood = -430.82136 (not concave)
Iteration 6: log likelihood = -407.18757 (not concave)
Iteration 7: log likelihood = -388.9725 (not concave)
Iteration 8: log likelihood = -374.02856 (not concave)
Iteration 9: log likelihood = -362.46854 (not concave)
Iteration 10: log likelihood = -353.54827 (not concave)
Iteration 11: log likelihood = -347.93093 (not concave)
Iteration 12: log likelihood = -342.38816 (not concave)
Iteration 13: log likelihood = -330.3993 (not concave)
Iteration 14: log likelihood = -327.98006 (not concave)
Iteration 15: log likelihood = -325.48768 (not concave)
Iteration 16: log likelihood = -323.8431 (not concave)
Iteration 17: log likelihood = -322.35456 (not concave)
Iteration 18: log likelihood = -320.75957 (not concave)
Iteration 19: log likelihood = -318.08191 (not concave)
Kind regards,
Michael
Comment