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]

From |
Richard Williams <richardwilliams.ndu@gmail.com> |

To |
statalist@hsphsun2.harvard.edu, "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |

Subject |
Re: st: nbreg - problem with constant? |

Date |
Fri, 02 Mar 2012 14:11:47 -0500 |

At 01:34 PM 3/2/2012, Simon Falck wrote:

Hi,I have some problems in fitting a negative binomial regressionmodel. It seems that one problem is related to the "constant" as theit inflates the coef. If the constant is removed, some coef arestill unexpectedly high. Since removing the constant bias coefresults implies restrictions, I hope anyone can contribute with someinsights on this matter.I apply the NBREG command to estimate the nr of new firms percountry explained by country-characteristics. The dataset isconsisted of information for 72 countries over 8 years, N=id=576.The information is annual, all regressors are lagged 1 year (t-1).The dv (Y) is the nr of new firms per country and vary between0-204. The indepv (X1-X5) are country-specific attributes. Eachindepv are continuous and vary across countries (id). No interactionterms are used. Some correlation exist, in general <0.3, but up to0.6. The dataset is structured as,id year Y X1 X2 X3X4 X51 2000 10 0.5258504 1.148275 1.6237610.00905698 0.29264972 2000 1 1.105136 0.9730458 0.74272080.03010507 0.17321353 2000 2 1.342283 0.7757816 0.64445640.01280751 0.2596922... The model is estimated with command: nbreg Y X1 X2 X3 X4 X5 Generates results: ----------------- Negative binomial regression Number of obs = 576LRchi2(8) = 387.39Dispersion = mean Prob > chi2 = 0.0000 Log likelihood = -562.09431 Pseudo R2 = 0.2563Y Coef. Std.Err. z P>z [95% Conf. Interval]X1 .3927241 .3024751 1.30 0.194-.2001162 .9855644X2 .6401666 .4818861 1.33 0.184-.3043129 1.584646X3 1.27199 .4352673 2.92 0.003.4188815 2.125098X4 -5.603575 1.724484 -3.25 0.001-8.983502 -2.223648X5 -1.370085 .1557769 -8.80 0.000-1.675402 -1.064768Constant 10.5169 2.30579 4.56 0.0005.997634 15.03617/lnalpha -.2836582 .1966372-.66906 .1017437alpha .753024 .1480725.5121898 1.1071Likelihood-ratio test ofalpha=0: chibar2(01) = 214.48 Prob>=chibar2 = 0.000-----------------The LR-test indicates that Negbin- is preferred over Possion. X1-X2are insignf., while X3-X5 are signf., P<0.05.We can see that the constant is very large, coef=exp(10.5169)=33225.488 and std.err for X4 is quite high (1.72..).

------------------------------------------- Richard Williams, Notre Dame Dept of Sociology OFFICE: (574)631-6668, (574)631-6463 HOME: (574)289-5227 EMAIL: Richard.A.Williams.5@ND.Edu WWW: http://www.nd.edu/~rwilliam * * 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/

**Follow-Ups**:**Re: st: nbreg - problem with constant?***From:*Joerg Luedicke <joerg.luedicke@gmail.com>

**References**:**st: nbreg - problem with constant?***From:*Simon Falck <simon.falck@abe.kth.se>

- Prev by Date:
**Re: st: Re: calculating proportions** - Next by Date:
**Re: st: nbreg - problem with constant?** - Previous by thread:
**st: nbreg - problem with constant?** - Next by thread:
**Re: st: nbreg - problem with constant?** - Index(es):