Why are my coefficients getting appended with a 1? It borks a match I do later against the original list that doesn't have the random 1 added to the end.> linearModel[[1]]Call: lm(formula = modelSource ~ +UNITBUILD + UNITDB + ITBUILD + ITDB + UATBUILD + UATDB + HOGANCODE + RCF + ReleaseST1 + ReleaseST2 + ReleaseBLA + Small.Bank.Acquisitions + HLY.NewYear + HLY.MLK + HLY.PRES + HLY.MEMORIAL + HLY.J4 + HLY.LABOR + HLY.COLUMBUS + HLY.VETS + HLY.THANKS + HLY.XMAS + HLY.ELECT + HLY.PATRIOT + EOM, data = mcReg) Coefficients: (Intercept) UNITBUILD1 UNITDB1 405.8326 -8.5675 13.5029 ITBUILD1 ITDB1 UATBUILD1 33.0950 -6.1938 0.2625 UATDB1 HOGANCODE1 RCF1 -3.7793 -3.4825 5.3243 ReleaseST11 ReleaseST21 ReleaseBLA1 13.6911 -9.4573 -3.3526 Small.Bank.Acquisitions1 HLY.NewYear1 HLY.MLK1 36.6445 -92.5360 22.1168 HLY.PRES1 HLY.MEMORIAL1 HLY.J41 7.1886 -13.0013 -14.3520 HLY.LABOR1 HLY.COLUMBUS1 HLY.VETS1 -0.9740 -16.9177 16.2969 HLY.THANKS1 HLY.XMAS1 HLY.ELECT1 -15.9056 -65.9887 -10.9916 HLY.PATRIOT1 EOM1 -20.2531 15.4775 Now all the variables with a 1 appended are factors so is that normal behavior? (if so then I can adjust the match() command to pad a 1 to the master list.)
On Jul 21, 2009, at 2:42 PM, Idgarad wrote:> Why are my coefficients getting appended with a 1? It borks a match I > do later against the original list that doesn't have the random 1 > added to the end. > >> linearModel[[1]]The linearModel function that is easiest to find appears (on the basis of its help page anyway) to be designed as a dialog control function rather than to be used in the manner you are illustrating. Of course I could be wrong about which package you are using, and the the appropriate use of linearModel, but why not see if you don't get more expected results with: lm(formula = modelSource ~ +UNITBUILD + UNITDB + ITBUILD + ITDB + UATBUILD + UATDB + HOGANCODE + RCF + ReleaseST1 + ReleaseST2 + ReleaseBLA + Small.Bank.Acquisitions + HLY.NewYear + HLY.MLK + HLY.PRES + HLY.MEMORIAL + HLY.J4 + HLY.LABOR + HLY.COLUMBUS + HLY.VETS + HLY.THANKS + HLY.XMAS + HLY.ELECT + HLY.PATRIOT + EOM, data = mcReg)> > Call: > lm(formula = modelSource ~ +UNITBUILD + UNITDB + ITBUILD + ITDB + > UATBUILD + UATDB + HOGANCODE + RCF + ReleaseST1 + ReleaseST2 + > ReleaseBLA + Small.Bank.Acquisitions + HLY.NewYear + HLY.MLK + > HLY.PRES + HLY.MEMORIAL + HLY.J4 + HLY.LABOR + HLY.COLUMBUS + > HLY.VETS + HLY.THANKS + HLY.XMAS + HLY.ELECT + HLY.PATRIOT + EOM, > data = mcReg) > > Coefficients: > (Intercept) UNITBUILD1 > UNITDB1 > 405.8326 -8.5675 > 13.5029 > ITBUILD1 ITDB1 > UATBUILD1 > 33.0950 -6.1938 > 0.2625 > UATDB1 > HOGANCODE1 RCF1 > -3.7793 -3.4825 > 5.3243 > ReleaseST11 ReleaseST21 > ReleaseBLA1 > 13.6911 -9.4573 > -3.3526 > Small.Bank.Acquisitions1 HLY.NewYear1 > HLY.MLK1 > 36.6445 -92.5360 > 22.1168 > HLY.PRES1 HLY.MEMORIAL1 > HLY.J41 > 7.1886 -13.0013 > -14.3520 > HLY.LABOR1 HLY.COLUMBUS1 > HLY.VETS1 > -0.9740 -16.9177 > 16.2969 > HLY.THANKS1 HLY.XMAS1 > HLY.ELECT1 > -15.9056 -65.9887 > -10.9916 > HLY.PATRIOT1 EOM1 > -20.2531 15.4775 > > Now all the variables with a 1 appended are factors so is that normal > behavior? (if so then I can adjust the match() command to pad a 1 to > the master list.) > > ______________________________________________ > R-help at r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code.David Winsemius, MD Heritage Laboratories West Hartford, CT
Idgarad, I guess that all of your factor variables are indicators with levels "0" and "1". Try changing the levels to "NO", "YES" for one of the variables and see what you get. I think that the output will clarify the (actually not) "random" 1s. -Peter Idgarad wrote:> Why are my coefficients getting appended with a 1? It borks a match I > do later against the original list that doesn't have the random 1 > added to the end. > >> linearModel[[1]] > > Call: > lm(formula = modelSource ~ +UNITBUILD + UNITDB + ITBUILD + ITDB + > UATBUILD + UATDB + HOGANCODE + RCF + ReleaseST1 + ReleaseST2 + > ReleaseBLA + Small.Bank.Acquisitions + HLY.NewYear + HLY.MLK + > HLY.PRES + HLY.MEMORIAL + HLY.J4 + HLY.LABOR + HLY.COLUMBUS + > HLY.VETS + HLY.THANKS + HLY.XMAS + HLY.ELECT + HLY.PATRIOT + EOM, > data = mcReg) > > Coefficients: > (Intercept) UNITBUILD1 UNITDB1 > 405.8326 -8.5675 13.5029 > ITBUILD1 ITDB1 UATBUILD1 > 33.0950 -6.1938 0.2625 > UATDB1 HOGANCODE1 RCF1 > -3.7793 -3.4825 5.3243 > ReleaseST11 ReleaseST21 ReleaseBLA1 > 13.6911 -9.4573 -3.3526 > Small.Bank.Acquisitions1 HLY.NewYear1 HLY.MLK1 > 36.6445 -92.5360 22.1168 > HLY.PRES1 HLY.MEMORIAL1 HLY.J41 > 7.1886 -13.0013 -14.3520 > HLY.LABOR1 HLY.COLUMBUS1 HLY.VETS1 > -0.9740 -16.9177 16.2969 > HLY.THANKS1 HLY.XMAS1 HLY.ELECT1 > -15.9056 -65.9887 -10.9916 > HLY.PATRIOT1 EOM1 > -20.2531 15.4775 > > Now all the variables with a 1 appended are factors so is that normal > behavior? (if so then I can adjust the match() command to pad a 1 to > the master list.) > > ______________________________________________ > R-help at r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > >
Apparently Analagous Threads
- Drop a part of an array\list\vector?
- Problem with predict() and factors
- Holiday Gift Perl Script for US Holiday Dummy Regressors
- Opps Correct Version of Holiday Regressor Perl Script
- *****SPAM***** Location Based Services in Oracle 9i, iSeminar- Today, 7/15 @2PM EST