Rcapture (version 1.3-1)

openp: Loglinear Models for Open Population Capture-Recapture Experiments

Description

This function computes various demographic parameters using a loglinear model for open populations in capture-recapture experiments.

Usage

openp(X, dfreq=FALSE, m=c("up","ep"), neg=TRUE, keep=rep(TRUE,2^I-1))

## S3 method for class 'openp':
print(x, \dots)

## S3 method for class 'openp':
plot(x, main="Scatterplot of Pearson Residuals", \dots)

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.

m

This argument is a character string taking the value "up" (up = unconstrained probabilities) or "ep" (ep = equal probabilities). If m is set to "up" (the default), no constraint is set on the loglinear parameters. Therefore

keep

This option is useful to fit the model on a subset of the possible capture histories. keep is a logical vector of length $2^I-1$ taking the value TRUE for a history kept and FALSE for a history put aside. In this

neg

If this option is set to TRUE, relevant negative gamma parameters are set to zero. This insures that the estimated survival probabilities belong to [0, 1] and that the births are positive.

x

An object, produced by the openp function, to print or to plot.

main

A main title for the plot

...

Further arguments to be passed to methods (see print.default and plot.default).

Value

• n
  The number of captured units
• model.fit
  A table containing the deviance, degrees of freedom and AIC of the fitted model.
• trap.fit
  A table containing, for the models with an added trap effect, the deviance, degrees of freedom and AIC.
• trap.param
  The estimated trap effect parameters and their standard errors. For m="up", the $I-3$ first rows of trap.param are estimations of the differences $logit$(capture probability after a capture)- $logit$(capture probability after a miss) for periods 3 to $I-1$. The last row gives a pooled estimate of these differences calculated under the assumption that they are homogeneous.
• capture.prob
  The estimated capture probabilities per period and their standard errors.
• survivals
  The estimated survival probabilities between periods and their standard errors.
• N
  The estimated population sizes per period and their standard errors.
• birth
  The estimated number of new arrivals in the population between periods and their standard errors.
• Ntot
  The estimated total number of units who ever inhabited the survey area and its standard error.
• glm
  The 'glm' object obtained from fitting the loglinear model
• loglin.param
  The loglinear model parameters estimations and their standard errors, calculated by the glm function.
• u.vector
  The Ui statistics, useful for the survival probabilities calculation, and their standard errors
• v.vector
  The Vi statistics, useful for the population sizes estimation, and their standard errors
• cov
  The covariance matrix of all the demographic parameters estimates.
• neg
  The position of the gamma parameters set to zero in the loglinear parameter vector.

Details

The function openp generates statistics to test the presence of a trap effect. The plot.openp function produces a scatterplot of the Pearson residuals of the model versus the frequencies of capture. If the data matrix X was obtained through the periodhist function, the dfreq argument must be set to TRUE. Standard errors are calculated by linearization.

References

Baillargeon, S. and Rivest, L.P. (2007) Rcapture: Loglinear models for capture-recapture in R. Journal of Statistical Software, 19(5), http://www.jstatsoft.org/v19/i05. Rivest, L.P. and Daigle, G. (2004) Loglinear models for the robust design in mark-recapture experiments. Biometrics, 60, 100--107.

See Also

closedp, periodhist, robustd

Examples

data(duck)
op.m1 <- openp(duck, dfreq=TRUE)
plot(op.m1)

# To remove the capture history 111111.
keep2 <- apply(histpos.t(6),1,sum)!=6
op.m2 <- openp(duck, dfreq=TRUE, keep=keep2)
op.m2

# To remove the capture histories with 5 captures or more
keep3 <- apply(histpos.t(6),1,sum)<5
op.m3 <- openp(duck, dfreq=TRUE, keep=keep3)
op.m3


data(mvole)
mvole.op<-periodhist(mvole,vt=rep(5,6))
openp(mvole.op, dfreq=TRUE)