Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Model Building
From
"Justina Fischer" <[email protected]>
To
[email protected]
Subject
Re: st: Model Building
Date
Tue, 26 Apr 2011 14:14:23 +0200
Dear Stefan,
your question is a bit out of the scope of this list - we discuss specific methodological issues only.
You could select important variables through a general-to-specific approach.
However, in general it is better to make a theory-based selection.
Good luck
Justina
-------- Original-Nachricht --------
> Datum: Tue, 26 Apr 2011 14:07:38 +0200
> Von: Stefan Nijssen <[email protected]>
> An: [email protected]
> Betreff: st: Model Building
> Dear Statalist members,
>
> I am trying to find the best indicators (independent variables,
> corporate fundamental data) to predict the dependent variable (the
> risk factor; 'oas'). I want to create a model with as few variables as
> possible to best predict 'oas'. So I need to make a selection of all
> variables available, see below. However, first thing to do seems to be
> finding the correct form with which the independents interact with the
> dependent. Plotting the variables separately with 'oas' I find some of
> them to be linear, some clearly quadratic and others fractional
> polynomial. To me it seems logical to converge the variables into
> their correct form as to best work with them, puzzling which to
> include and which not. I thought of using the .reg function to test
> the function. I do not see how to create a quadratic variable (other
> than generating var*var), and fractional polynomial will be even more
> difficult, before using them in the regression. Can anyone provide
> suggestions on what to do?
>
> After doing so, I was thinking of using Multiple Discriminant Analysis
> to reduce the number of variables.
>
> Yours,
>
> Stefan Nijssen
>
>
> The dataset:
>
>
> oas ebit sales intcov totass totdeb ltdeb totcap worcap margin operex dtoe equity lev rating2
> 85 5380643 28251654 13.19 43681540 14452051 10497732 30656052 6427401 14.15 24461264 71.32 20265092 0.52 2
> 303 281856.9 2665473 3.54 3796766.31 1508258.5 1315873.5 3223983 68471 7.31 2550578.3 79.66 1893310.5 0.7 6
> 463 1364563 7401812.5 3.08 22017880 7853000 6879250 14402250 291750 7.88 6122000 107.53 7302908.5 0.94 4
> 198 2647250 13573438 3.09 44021380 17441250 15316000 27260250 -1575500 8.91 11377000 148.59 11738033 1.3 4
> 269 3704500 14422250 2.07 35880445.63 18933500 17032000 25258250 2136250 3.23 11825250 448.16 4224695.5 4.03 4
> 427 173537.5 6206356 2.37 4271637.5 639125 635425 1476400 1042875 0.56 5841525 77.84 821048.94 0.77 5
> 135 1641008 19334660 12.26 21852596.13 3422023.5 1842737.8 9437302 838316.31 5.18 18850387 45.76 7479015.5 0.25 4
> 145 4551831 44197292 3.18 72634330.63 19065608 15252120 40214560 8678020 7.76 40345364 77.59 24572248 0.62 3
> 150 4194342 14754657 5.45 28717164 13835568 11898647 19494606 3414371.8 18.76 11092639 218.77 6324361.5 1.88 3
> 140 1438059 3687984.5 1.49 24024376.88 17841316 16468203 21458064 12.31 3140013.3 521.25 3422778.3 4.81 3
> 220 203325.6 676520.69 1.15 7101090.5 3507231 2940892 6296144 13.52 618380.5 134.85 2600887 1.13 4
> 256 4631625 12534625 4.86 50502630 13211750 12422000 31765500 979500 20.93 8783500 70.73 18680452 0.66 4
> 138 261468 829771.25 1.51 7099677.69 3731297 3351377 6441615 34.88 710694.5 122.2 3053434.5 1.1 4
> 148 261468 829771.25 1.51 7099677.69 3731297 3351377 6441615 34.88 710694.5 122.2 3053434.5 1.1 4
> 695 82975.38 904324.31 1.14 1665280.06 775164.75 741634.5 1455926.9 -8168.0601 0.28 899990 113.89 680625.81 1.09 6
> 94 216452.8 1611485.3 3.15 2646279.44 1288793.6 1276829.4 2134875.8 424008 4.87 1539896 151.24 852151.31 1.5 6
> 394 71108.94 470080.44 1.45 790061.69 497222.25 497222.25 691091.25 125072.25 3.06 405778.5 269.81 184284.36 2.7 6
> 121 3494500 15628314 6.26 35815069.38 9345333 8841667 20532666 -706000 11.92 12375667 79.9 11696775 0.76 4
> 340 205203.3 593503.31 9.72 1973646.38 934802.25 923577.25 1677409.8 -89585.25 18.62 122.96 760249.06 1.21 6
> 166 889048.6 1494797.3 2.82 11312311.38 6567463.5 5966816.5 10616108 38.11 444483.75 164.13 4001440 1.49 4
> 583 176160.1 308049.94 4.86 1076181.94 591622.5 349243.75 743215 27.91 1214527.3 159.18 371663.03 0.94 5
> 180 1447188 18371130 11.08 41088878.75 2391000 2151000 7259000 5.24 4664822 49.77 4803857.5 0.45 4
> 450 541709 6160482.5 2.85 8880104 4277432 3606781 6622840 1553109.5 2.34 223.4 1914718 1.88 5
> 298 3863553 77601392 2.44 85151294.19 31085222 18770020 34849728 6661573.5 1.52 17478500 208.22 14929207 1.26 5
> 128 1534585 9863095 4.59 10252978.56 4923419.5 4713170 6494518 777069.5 8.59 6020838.8 298.73 1648123.8 2.86 4
> 274 460957.8 4364300 10.08 14315121.25 1396855 883192.75 4599718 8.27 8585884.3 39.18 3564997.3 0.25 4
> 53 2605694 18664554 9.39 18346915 6482850 5699125 11169575 1040000 9.47 7014269.5 131.28 4938091.5 1.15 3
> 181 525481.3 2691643.8 38.87 3703062.5 800775 800775 3187250 629400 13.14 3851485.5 33.25 2408527 0.33 4
> 434 304058.6 8118761 7.02 3632280.88 1160131.8 1101497 2577599 1261795.5 1.47 16293825 79.96 1450958.1 0.76 4
> 286 531000 6554125 1.26 14792500 6698000 6041000 8780000 719666.69 1.59 2532000 280.79 2385441 2.53 5
> 122 1228381 9417844 7.81 12637412.5 4106456.3 3509531.3 8877925 611050 9.21 5949666.7 79.18 5186393 0.68 3
> 135 7207145 26375682 5 76487644 41771588 36765752 66292060 -5526529 11.74 8008593.8 151.55 27562908 1.33 4
> 153 7169938 29623442 2.66 132017312.5 71461000 45556248 58932752 10.66 548.05 13039079 3.49 3
> 138 2290250 10252062 16.78 15527253.13 1828187.5 1676500 11110500 3320000 14.48 21547524 19.38 9433068 0.18 3
> 357 1276806 15411878 1.81 24708428.75 11674496 5704248 12501244 3870498.5 2.23 25365250 173 6748263.5 0.85 5
> 198 175700.8 1007057.3 2.63 3038026.31 1233305.8 1148982.5 2275610.8 133983.5 13.72 108.62 1135431.5 1.01 4
> 148 302575 3533750 6.92 3164375 957000 817000 2513250 548750 4.61 8107937.5 56.22 1702165.5 0.48 4
> 475 99679.25 1465177 1.81 1858617.19 748078.25 742457.75 1568498.5 313015.75 -0.95 14234758 90.51 826491.63 0.9 6
> 289 2436011 27316448 4.6 28189748.88 8609682 7675119 20332920 3673255.8 5.42 865382.5 69.78 12338324 0.62 4
> 103 2452813 10048750 5.11 26310131.25 7940250 7482000 16065750 207500 13 1933380.3 92.79 8557226 0.87 4
> 135 476165.8 1923645 7.62 2265192.5 1438719.3 1311237.5 1466039.4 514408.94 18.31 25573162 297.72 483245.78 2.71 4
> 123 2574000 11116812 10.43 153419556.3 33804752 5405250 19493000 5.13 7645500 254.22 13297439 0.41 3
> 253 830500 11135625 3.18 15503938.75 3523000 3214500 9670000 1689500 7.75 79675488 55.41 6358632 0.51 4
> 210 5349000 20837010 4.72 60373010 16.07 34782286 3
> 90 1939410 4605238 25.42 14894076.5 2775585.3 2702085.3 11760652 240683 26.16 1486366.5 29.26 9486748 0.28 3
> 295 210577 880666.25 0.79 8760320.75 5247260 4437147.5 7444190 -2.57 8077500 225.08 2331312.8 1.9 5
> 220 1270822 26866490 4.22 13348663.75 3895161.5 3553098.3 9396833 213236 2.27 9792500 65.25 5969596 0.6 4
> 185 1270822 26866490 4.22 13348663.75 3895161.5 3553098.3 9396833 213236 2.27 9792500 65.25 5969596 0.6 4
> 237 1213502 7020566 8.06 8162819.31 3180375 3008315 6756995 342366.75 8.14 3416891.3 86.02 3697358 0.81 4
> 111 891058 3396809.8 4.04 9885560 3760772.8 3623771.3 8834517 526434.5 10.02 809219.5 83.96 4479243.5 0.81 4
> 135 2280688 12996000 2.96 40561443.13 11723500 10693500 21409250 1287500 8.76 26055367 122.16 9596644 1.11 3
> 394 764500 4659875 0.72 23815319.38 13790250 13193500 18387000 -646000 3.06 26055367 431.41 3196571.8 4.13 5
> 395 148101 1340106.8 4.86 1958709.31 505149.5 490077 1696372.8 532718.75 7.45 5944816 41.81 1208202.6 0.41 5
> 242 883022.4 7233008.5 4.46 9438240.25 6107244.5 6066794.5 10428866 238687.25 5.2 2475224.3 146.53 4167819.3 1.46 4
> 172 2340448 11540884 3.61 35344855 11808253 10971290 19517114 1249746.5 10.48 10630750 143.54 8226454.5 1.33 4
> 234 121671.3 1099781.5 3.15 3085560.06 803425.75 698507.63 2078448.5 992426.06 7.4 2785500 58.16 1381510 0.51 5
> 184 2841823 15281568 3.86 40004167.94 17852298 14944255 24606332 -4342231.5 13.36 1272444 226.75 7873097 1.9 4
> 151 7169938 29623442 2.66 132017312.5 71461000 45556248 58932752 10.66 548.05 13039079 3.49 3
> 397 657883.1 2219391.3 1.8 7770782.31 5632487 5559101 7325540 34978 9.15 9446279 752.49 748515.69 7.43 5
> 403 -149778.2 1765832.5 -3.06 779485.94 337975.5 315692.5 468990 200225.5 -14.17 943569.19 437.64 77226.828 4.09 5
> 111 1874938 5725187.5 20.17 16386063.13 1866250 1808250 16321750 4051000 51.21 15559530 13.25 14087564 0.13 4
> 254 1450000 18632000 2.37 22328000 3.01 25365250 5
> 495 167043.8 3405106.3 0.93 4236662.5 2610375 2593175 3129425 354350 -1.69 1880957.8 660.03 395491.88 6.56 6
> 282 489044.6 1045975.8 1.53 11641917.63 5937713 5483499.5 11472368 41.14 1852443.5 120.51 4927358 1.11 4
> 88 6313813 75159320 11.51 46344378.75 11193250 9788250 28615312 2874750 4.8 4830750 60.11 18622440 0.53 4
> 673 208767.2 1667810.8 3.63 4546824.94 1645275 1597527.8 3205995.3 223982 2.09 119.55 1376223.4 1.16 6
> 174 3437022 16215220 20.79 22440903.44 2870735.8 2700069.5 15749543 553035.44 15.19 3464900 22.07 13010359 0.21 4
> 291 620937.5 4919500 1.58 12033875 5722750 5328250 11385000 5.69 899246 99.49 5752085.5 0.93 5
> 251 635663.2 5151291.5 2.3 11796880.63 4114660 3877029 7108709 625312 4.83 66319563 128.3 3207061.5 1.21 3
> 167 2272879 4815855 3.23 23966016.5 15652777 13834359 19795184 -1222408.3 17.89 4711750 315.43 4962361.5 2.79 3
> 362 1003063 12248125 2.37 19027438.75 8657250 8311250 11229000 1662750 3.42 28858140 304.93 2839094.3 2.93 4
> 331 463412.5 6453806 2.42 11235206.25 2038125 1763075 4383075 655125 2.54 2585588.2 103.16 1975788.9 0.89 5
> 103 5324313 20861712 5.36 32989254 13284815 11314448 22144602 -1795919.3 14.67 11037750 125.72 10566881 1.07 3
> 141 1015455 2310940.5 3.55 10346050.81 5348817 4468707 6851732.5 -1116425 25.63 6050225 226.44 2362108.3 1.89 4
> 249 2698201 66511396 5.52 55476209.69 8321952 6954835 21678672 5420935 1.6 67.71 12290354 0.57 4
> 177 308608.8 4755793.5 5 7111222.56 2697911.3 2422615.5 4696201.5 155167.75 2.97 45529518 122.28 2206399.3 1.1 4
> 158 208231.3 1145226.5 2.61 5489118.69 3711619.5 2487834 4474727.5 290544.31 7.84 4836920.7 215.55 1721909.8 1.44 4
> 228 214846.5 1954261.5 14.83 1382212.69 303568.69 211785.5 919402.44 365864.19 7.69 24998013 42.97 706466.56 0.3 2
> 380 289061.9 2952063.8 13.45 41551293.13 1763195 1763195 4019890 6.47 65.41 2695604.8 0.65 4
> 62 1500929 6863926.5 33.75 8073281.06 1510279.3 1256916.8 6292660 2462186.5 15.58 45862000 29.81 5066563.5 0.25 3
> 124 4245063 64668880 8.07 55944753.75 10268500 9524250 12723500 -412500 4.1 67165934 141.78 7242559 1.32 3
> 90 934812.5 13388062 3.38 13214000 5620333.5 5001000 8263666.5 792000 3.54 79633947 295.58 1901437.9 2.63 3
> 110 1939410 4605238 25.42 14894076.5 2775585.3 2702085.3 11760652 240683 26.16 1486366.5 29.26 9486748 0.28 3
> 66 3574500 33506944 7.84 33455756.25 7570750 5821250 14858750 2200250 6.89 1747963.5 86.97 8705514 0.67 3
> 126 1519000 11223500 4.23 30125940.63 6946000 6210750 24405500 780000 14.75 2601187 38.49 18045074 0.34 3
> 139 249274.1 517294.5 2.53 3403218.81 2355742.8 2355742.8 3261016.3 46849.5 18.34 5501541.6 276.13 853120.44 2.76 4
> 135 1006275 10111125 9.08 9886887.5 2134675 922675 4769675 699100 7 60788000 57.17 3733744.3 0.25 4
> 158 1009592 8659594 11.25 5911334.31 2466590.8 2236040.8 3724760.8 1979503.1 6.41 12409000 177.08 1392895 1.61 4
> 190 285465.6 803813.44 1.39 9263513.5 4316608 3688907.8 8473394 34.31 3416891.3 117.32 3679423.5 1 4
> 161 1869978 43084524 3.59 20332604.38 5643430.5 4631572 12001716 1488398.4 4.53 29747000 89.03 6338796.5 0.73 4
> 138 797618.9 2740491.5 2.19 12481629.25 7343072 6740469.5 8567194 70079.938 10.97 9313000 414.8 1770257.4 3.81 4
> 378 460957.8 4364300 10.08 14315121.25 1396855 883192.75 4599718 8.27 8585884.3 39.18 3564997.3 0.25 4
> 382 117131.9 3833936.3 0.83 4487341.06 1745101.8 1701066.8 2285959.3 -563982.13 -0.03 142.1 1228074.6 1.39 5
> 151 208231.3 1145226.5 2.61 5489118.69 3711619.5 2487834 4474727.5 290544.31 7.84 4836920.7 215.55 1721909.8 1.44 4
> 116 4890063 42352820 3.52 56689880 31003250 20736750 29766500 6520750 6.26 36745457 382.07 8114494 2.56 3
> 82 3574500 33506944 7.84 33455756.25 7570750 5821250 14858750 2200250 6.89 1747963.5 86.97 8705514 0.67 3
> 524 24693.75 1917095.8 0.3 4842910.5 2551828.8 2541828.8 4099848 254309.75 -7.89 60745750 187.89 1358132.3 1.87 6
> 303 4118070 23985514 3.67 51368068.13 21624580 17601584 39221240 334194.25 7.86 3851485.5 112.13 19284846 0.91 4
> 228 192375 25146066 0.66 25793691.88 8960750 8366500 15105750 1661812.5 -2.61 152.57 5873326 1.42 5
> 184 737062.5 12185125 3.76 7940062.5 2796750 2672500 4059250 744000 2.48 61749079 202.87 1378575.3 1.94 4
> 423 87325 3822237.5 5.05 3747943.75 1763925 1663400 2597250 317500 -1.23 1315678.1 248.3 710393.56 2.34 6
> 379 466187.5 6489375 2.23 9104875 2264000 2219750 5570750 1026000 2.77 68.16 3321474.5 0.67 4
> 239 910430.2 4651478.5 11.83 10495100.56 4125771.5 3549718.8 8499786 943826.5 10.23 38088000 84.04 4909587 0.72 4
> 161 873406.3 7511375 2.17 18747916.25 7086275 5844600 10740275 -1059200 3.25 29747000 144.98 4887676 1.2 4
> 299 128830.6 211611 2.34 2496541.13 1058476.3 943312.5 2455482.3 62.8 2124596.3 74.81 1414886 0.67 4
> 132 3148250 30979816 3.47 58350691.88 13507750 12823500 40106752 7081500 6.43 19916489 51.82 26067302 0.49 4
> 401 249530.3 6599636 2.39 5629625 2183225 2073350 3227037.5 540962.5 -1.34 1606497 220.87 988477.25 2.1 6
> 188 618418.8 22678324 3.19 10654518.75 4798500 3664000 7591000 -94500 1.53 23114125 126.37 3797333 0.96 4
> 194 363687.5 1506875 2.52 4541187.5 2739250 2584250 4162500 229000 17.08 11248250 176.67 1550533.5 1.67 4
> 436 425768.3 2743437.3 2.18 6383088.81 3429510.5 3356849 5539840.5 734827.25 4.5 926003 157.96 2171160.3 1.55 6
> 109 1116125 12794875 7.67 13415937.5 3587250 2831750 6713750 2612500 4.7 3482675 97.8 3668132.3 0.77 4
> 199 1549438 7481125 3.38 22025568.13 9329000 8336250 14727500 480000 12.11 5877000 152.48 6118280 1.36 4
> 170 1077101 8174526.5 6.1 13861322.38 3615055.8 2985167.5 11307444 2278129 7.77 3665766.3 45.31 7978934.5 0.37 4
> 165 453263.9 5882251 3 6683572.69 2720900 2405980 3921994.5 -8847 2.89 6552875 182.63 1489822.5 1.61 4
> 334 258826.6 2780762.3 6.16 2541417.94 908823.25 870188.25 2027089.8 638870.25 4.53 148330 82.8 1097645.8 0.79 5
> 374 113606.7 1290720.5 1.78 2288817 940772.25 940772.25 2498224.8 -4847.25 3.39 27476250 83.56 1125864.4 0.84 6
> 256 4011163 9243569 12.94 29933565.63 13595250 10916250 28680500 564750 35.54 6614862.5 83.17 16346830 0.67 4
> 257 217241.4 3432849 3.89 3286244.25 972853.5 914663 2056043.9 804996.38 3.33 23099750 87.58 1110769.4 0.82 4
> 184 783656.3 5001044 3.98 12044120.63 5744125 5262175 11262750 -1042300 6.64 1095000 101 5687111.5 0.93 4
> 124 3056379 14357249 4.59 33342150.75 10234541 8194759 28248912 -2202470.3 12.42 11947750 53.22 19229048 0.43 4
> 216 1507000 4753312.5 2.42 22919816.88 10170750 8937750 16571000 -1147000 22.37 5857250 150.64 6751580.5 1.32 4
> 458 21857.75 593619.38 0.73 1671891.94 527680.25 527680.25 1276642 -20649.5 -10.31 7815249.8 72.47 728136.13 0.72 6
> 418 246312.5 2375625 1.69 3257500 1373000 1111250 1177500 256000 -7.26 5295897.3 150.4 912883.75 1.22 6
> 172 2724610 10471538 3.23 143644875 28758000 17949500 33301500 12.73 2519033.8 200.86 14317435 1.25 3
> 67 2368938 11843812 36.17 15418313.13 3845750 3457250 10297500 3752750 15.22 1126684.5 57.37 6703416.5 0.52 3
> 97 4194342 14754657 5.45 28717164 13835568 11898647 19494606 3414371.8 18.76 11092639 218.77 6324361.5 1.88 3
> 164 4685525 31993766 16.93 38542137.5 8315263.5 5365503 30877336 8984776 10.4 3126697.1 33.66 24701248 0.22 3
> 410 301443.8 3836112.5 7.63 3715100 818400 807975 2295050 1714600 5.18 4770100 53.81 1520906.9 0.53 5
> 316 341568.8 5010344 3.9 5824387.5 1349100 1158800 3171350 659925 3.69 35305000 67.53 1997778.8 0.58 5
> 404 578698.4 5225987 8.39 4608613.69 2322451 2096578.3 3923313.5 957641.25 5.96 12276334 130.45 1780372.1 1.18 5
> 103 280608.7 15248190 2.12 21072253.19 258442 41405.75 9153858 3116438.8 6.43 3336750 2.99 8643545 0 2
> 329 436017.8 2581652.5 2.03 7615322.38 3674574.5 3289975.5 5682647 -310964.25 7.84 2066750 162.23 2265040 1.45 4
> 93 2730482 6604610 20.19 19711947.31 6410276 4252670.5 15795402 -220168.5 23.81 9042250 55.98 11452034 0.37 4
> 187 256625 12630312 0.86 17435253.75 2786937.5 2722625 11590875 3395437.5 -2.54 9675750 32.06 8692372 0.31 4
> 310 420312.5 26868316 1.49 10527062.5 2925562.5 2717812.5 7616187.5 2085500 0.15 28906844 61.2 4780379.5 0.57 5
> 356 213760.8 5300887 0.91 6745382.88 1771588.3 1716921.3 4461061.5 1109570.6 -5.02 4636325 66.38 2668959 0.64 5
> 103 4000375 48595944 12.84 34264943.13 10314000 8615500 17293250 2912750 4.84 124.19 8305351 1.04 2
> 682 50437.5 4427812.5 -0.36 4294000 1836000 1784000 3107000 817250 -8.4 5169180 189.68 967933.25 1.84 6
> 516 2156274 7025522.5 10.23 16587407.25 6431164 5183735 15193346 4809816.5 8.81 13227272 153.69 4184486.8 1.24 5
> 232 1701713 10523356 2.53 25882452.5 8290750 8074750 16699000 817750 5.6 110.06 7533279 1.07 4
> 162 325877.5 1335745 3.8 3263892.19 2455750 2341250 3755373 -28002 21.52 2146270.5 72.58 3383391.3 0.69 4
> 503 -330050.9 846301.31 -0.4 4443735.75 1975863.8 1975863.8 3686029 161809 -17.04 4655089.4 164.26 1202906.3 1.64 6
> 600 468432.4 894199 18.1 3639089.63 1161216.8 939615.31 2960341 18.6 11051563 77.18 1504654 0.62 5
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
--
Justina AV Fischer, PhD
Senior Researcher
Faculty of Economics
University of Mannheim
homepage: http://www.justinaavfischer.de/
e-mail: [email protected]
papers: http://ideas.repec.org/e/pfi55.html
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/