acmpmle: Conway Maxwell Poisson Modeling of Discrete Data

In degreenet: Models for Skewed Count Distributions Relevant to Networks

Conway Maxwell Poisson Modeling of Discrete Data

Description

Functions to Estimate the Conway Maxwell Poisson Discrete Probability Distribution via maximum likelihood.

Usage

acmpmle(x, cutoff = 1, cutabove = 1000, guess=c(7,3),
    method="BFGS", conc=FALSE, hellinger=FALSE, hessian=TRUE)

Arguments

x	A vector of counts (one per observation).
cutoff	Calculate estimates conditional on exceeding this value.
cutabove	Calculate estimates conditional on not exceeding this value.
guess	Initial estimate at the MLE.
method	Method of optimization. See "optim" for details.
conc	Calculate the concentration index of the distribution?
hellinger	Minimize Hellinger distance of the parametric model from the data instead of maximizing the likelihood.
hessian	Calculate the hessian of the information matrix (for use with calculating the standard errors.

Value

theta	vector of MLE of the parameters.
asycov	asymptotic covariance matrix.
asycor	asymptotic correlation matrix.
se	vector of standard errors for the MLE.
conc	The value of the concentration index (if calculated).

Note

See the papers on https://handcock.github.io/?q=Holland for details.

Based on the C code in the package compoisson written by Jeffrey Dunn (2008).

References

compoisson: Conway-Maxwell-Poisson Distribution, Jeffrey Dunn, 2008, R package version 0.3

See Also

ayulemle, awarmle, simcmp

Examples

# Simulate a Conway Maxwell Poisson distribution over 100
# observations with mean of 7 and variance of 3
# This leads to a mean of 1

set.seed(1)
s4 <- simcmp(n=100, v=c(7,3))
table(s4)

#
# Calculate the MLE and an asymptotic confidence
# interval for the parameters
#

acmpmle(s4)

degreenet documentation built on Sept. 26, 2024, 1:08 a.m.