help for censornb                                                (Joseph Hilbe)

Censored negative binomial regression

censornb depvar [varlist] [if exp] [in range] , censor(varname) [ offset(varname) exposure(varname) cluster(varname) level(#) from(asis) irr robust nolog maximize_options survey_options]

Note: the option censor must be included in the command. A censor variable must use the following numbers to indicate the type of censoring: 1 = not censored, 0 = left censored, -1 = right censored.

aweights, fweights, iweights, and pweights are allowed; see help weights.

censornb provides access to all maximize options; see help maximize.

censornb provides access to all survey options; see help svy.


censornb fits a maximum likelihood censored negative binomial regression of depvar on indepvars, where depvar is a non-negative count variable. The censor option is required. If no observations are censored, a censor variable with all 1's must be specified. Interpret parameter estimates as one would nbreg. censornb is parameterized as a survival model, not as the econometric parameterization found in Greene, Cameron & Trivedi, and elsewhere, although results are similar.

censornb acccepts all of the help maximize options, the constraint() option, and all survey options and capabilities documented in [SVY]; including multi-level surveys; poststratification; and BRR, jackknife, and linearization VCE estimators.

This program uses ml lf method.


+-------+ ----+ Model +------------------------------------------------------------

censor(cenvar) is required. Values of 1 indicate a non-censored, 0 a left censored, and -1 a right censored observation.

offset(varname) specifies a varname in model with coefficient constrained to 1.

exposure(varname) specifies a ln(varname) in model with coefficient constrained to 1.

constraints(constraints) apply specified linear constraints.

+-----------+ ----+ SE/Robust +--------------------------------------------------------


robust specifies that the Huber/White/sandwich estimator of variance is to be used in place of the traditional calculation. robust combined with cluster() allows observations which are not independent within cluster (although they must be independent between clusters). If you specify pweights, robust is implied.

vce(options) allowed. vce() supports robust, opg, and native. vce does not support options bootstrap or jacknife, However, censornb does support the bootstrap and jacknife commands, so these modeling capabilities are allowed.

+-----------+ ----+ Reporting +-------------------------------------------------------- level(#) specifies the confidence level, in percent, for confidence intervals of the coefficients; see help level.

nolog suppresses the iteration log.

+-------------+ ----+ max options +------------------------------------------------------

maximize_options: technique(algorithm_spec), [no]log, trace, hessian, gradient, showstep, shownrtolerance, difficult, iterate(#), tolerance(#), ltolerance(#), gtolerance(#), nrtolerance(#), nonrtolerance, from(init_specs); see maximize.

+-------------+ ----+ svy options +------------------------------------------------------

survey_options are all available. See help svy

Author and support

Joseph Hilbe, Arizona State University: jhilbe@aol.com


censornb is a user authored program. Support is by author. See Hilbe, Negative Binomial Regression, Cambridge Univ. Press, for discussion. Related information can also be obtained at [R] nbreg.


. censornb time hmo age, censor(cenvcar) nolog irr

. censornb time hmo age, censor(cenvar) nolog cluster(provnum)

. bootstrap: censornb deaths smokes a2-a5, censor(cenvar) exposure(pyears) irr nolog

. svyset psuid [pweight=finalwgt], strata(stratid)

. svy: censornb zinc age age2 weight female black orace rural, censor(cv) nolog irr

Also see

Manual: [R] Negative binomial regression; [SVY] Svy: negative binomial

Online: help censornb nbreg