Survey Censored Poisson Regression ------------------------------
^svyset^ [pweight=var], strata(strataid) psu(psuid)
^svycepois^ depvar [varlist] [^if^ exp] [^in^ range] [, ^cen^sor(^var^)^ l^evel ^eform^ ^off^set(^var^) ^e^xposure(^var^) ^R^obust ^CL^uster(^var^) ]
One must ^svyset^ the data prior to using ^svycepois^. An example is given above, but look in the user manual for complete information.
The ^censor^ option is required. If no observations are censored, all values of the censor variable have the value of ^1^. Left censoring is indicated with censor values of ^0^; right censoring with values of ^-1^. A non-censored model is identical to a survey Poisson model.
^pweights^ are allowed, but defined in svyset; see help @weights@.
^level^(^#^) specifies the confidence level, in percent, for confidence intervals. The default is ^level^(^95^) or as set by ^set level^.
^eform^ reports estimated coefficients transformed to incidence ratios, i.e., e to the power of b rather than b. Standard errors and confidence intervals are similarly transformed. This option affects how results are displayed, not how they are estimated.
^offset^(^varname^) specifies a variable that is to be entered directly into the log-link function with coefficient constrained to be 1. One must log (ln) the offset variable prior to entering it as an offset.
^exposure^(^varname^) specifies a variable that is to be entered directly into the log-linked function. ^exposure^ is the natural log of the variable entered as an offset.
^robust^ specifies that the Huber/White/sandwich estimator of variance is to be used in place of the traditional calculation; see [U] 23.14 Obtaining robust variance estimates. robust combined with cluster() allows observations which are not independent within cluster (although they must be independent between clusters).
^cluster^(^varname^) specifies that the observations are independent across groups (clusters) but not necessarily within groups. varname specifies to which group each observation belongs; e.g., ^cluster^(^personid^) in data with repeated observations on individuals. cluster() can be used with pweights to produce estimates for unstratified cluster-sampled data, but see help svypoisson for a command especially designed for survey data. Specifying cluster() implies robust. Do not use cluster with strata().
Examples -------- . ^svyset [pw=age], strata(drug) /* meaningless example */ . ^svycepois studytim died drug2 drug3, censor(cenvar) eform^ . ^svyset [pw=citysize], strata(ziparea) . ^svycepois infected cases cd4 cd8, eform e(cases)^
Author ------ ^Joseph Hilbe^ Arizona State University jhilbe@@aol.com
Also see -------- Manual: [R] poisson, svypoisson On-line: help for @svypoisson@