COMPoissonReg (version 0.3.5)

constantCMPfitsandresids: Determining COM-Poisson Fitted Values and Residuals

Description

Computes estimated lambda values, fitted values, and residuals.

Usage

constantCMPfitsandresids(betahat, nuhat, x, y)

Arguments

betahat

Maximum likelihood estimate for beta

nuhat

Maximum likelihood estimate for nu

x

matrix of size nxp

y

column vector of length n

Value

A numeric array of suitable size.

Details

Computes estimated fitted values, and associated residuals from a COM-Poisson regression with constant dispersion parameter, nu. n=number of records and p=number of predictors.

References

A Flexible Regression Model for Count Data, by Sellers & Shmueli, http://ssrn.com/abstract=1127359