Rcapture (version 1.4-4)

closedp.custom: Customization of a Loglinear Model for Closed Populations Capture-Recapture Experiments

Description

As of version 1.2-0 of Rcapture, these functions are deprecated, but kept for back compatibility. Please use closedpCI.t instead.

The closedp.mX function fits a loglinear model given a design matrix mX. The closedp.h function fits Mh or Mth models for which the form of the column for heterogeneity in the design matrix is determined by the user.

Usage

closedp.mX(X, dfreq=FALSE, mX, mname="Customized model")
closedp.h(X, dfreq=FALSE, m="Mh", h="Poisson", a=2)
# S3 method for closedp.custom
print(x, …)
# S3 method for closedp.custom
boxplot(x, …)

Arguments

X

The matrix of the observed capture histories (see Rcapture-package for a description of the accepted formats).

dfreq

A logical. By default FALSE, which means that X has one row per unit. If TRUE, it indicates that the matrix X contains frequencies in its last column.

mX

The design matrix of the loglinear model. In this matrix, the order of the capture histories is as defined in the histpos.t function.

mname

A character string specifying the name of the customized model.

m

A character string indicating the model to fit, either "Mh"=Mh model or "Mth"=Mth model

h

The character string "Poisson" (\(2^k-1\)) or a numerical function taking only one argument specifying the form of the column for heterogeneity in the design matrix.

a

The value of the exponent's base for a Poisson model.

x

An object, produced by the closedp.mX or the closedp.h function, to print or to plot.

…

Further arguments passed to or from other methods.

Value

n

The number of captured units

results

A table containing the estimated population size and its standard error, the deviance, the number of degrees of freedom and the Akaike's information criterion.

glm

The 'glm' object obtained from fitting the model.

Details

An intercept is added to the model. Therefore, the mX matrix must not contain a column of ones.

The abundance estimation is calculated as the number of captured units plus the exponential of the intercept. Therefore, these functions are not suited for models with a behavioral effect.

In closedp.h, the argument h cannot take the value "Chao" or "Darroch" because these models are already fitted by the closedp function.

The boxplot.closedp.custom function produces a boxplot of the pearson residuals of the customized model.

References

Rivest, L.P. and Baillargeon, S. (2007) Applications and extensions of Chao's moment estimator for the size of a closed population. Biometrics, 63(4), 999--1006.

See Also

closedp, closedp.Mtb

Examples

# NOT RUN {
# HIV data set
mat <- histpos.t(4)
mX2 <- cbind(mat, mat[, 1] * mat[, 2])
closedp.mX(HIV, dfreq = TRUE, mX = mX2)

# Third primary period of mvole data set
period3 <- mvole[, 11:15]
psi <- function(x) { -log(3.5 + x) + log(3.5) }
closedp.h(period3, h = psi)
# }