Model fitting of flexible behavioural recapture models based on conditional probability reparameterization and meaningful partial capture history quantification also referred to as
meaningful behavioural covariate
Details
Package:
BBRecapture
Type:
Package
Version:
0.1
Date:
2013-12-18
License:
GPL-2
This BBRecap package has been built up to help researchers to fit some relevant classes of
capture-recapture models within the framework of Bayesian inference. Special emphasis is
given on recently developed tools to take into account
flexible behavioral response to capture.
The main function developed in the package relies on the generalized linear model framework
in the spirit of Huggins (1989) and Alho (1990) for regressing the capture occurrence on previous
partial capture histories although shortcuts have been embedded to reduce computational
complexity whenever possible. There are also some functions which fit the same class of models
maximizing the unconditional likelihood as opposed to the most frequently used approach
based on the conditional likelihood (Huggins and Hwang, 2011). There are theoretical arguments
related to the so-called likelihood failure (Alunni Fegatelli and Tardella, 2013; Carle and
Strub, 1978) which support the use of a Bayesian approach for the estimation of the unknown
population size in the presence of behavioral response to capture. Some simulation studies
have been also carried out in Alunni Fegatelli (2013) to highlight the occurrence of the likelihood
failure pathology and the loss of inferential performance of the conditional likelihood
approach even in the absence of failure. In the same circumstances the unconditional likelihood
approach should be preferred to the conditional likelihood but both of them are in any case outperformed
by the Bayesian approach.
Functions in the package are designed to allow minimal efforts by the researcher although
optional arguments often allow for a more customized and refined model building.
Carle, F.L. and Strub, M.R. (1978) A new method for estimating population size from removal data. Biometrics, 34, 621–630.
Huggins, R.M. (1989) On the statistical analysis of capture experiments. Biometrika, 76, 133–140.
Huggins, R. and Hwang, HW (2011) A review of the use of conditional likelihood in capture-recapture experiments. International Statistical Review, 79, 385–400
Farcomeni, A. (2011) Recapture models under equality constraints for the conditional capture probabilities. Biometrika, 98, 237–242
Alunni Fegatelli, D. and Tardella, L. (2012) Improved inference on capture recapture models with behavioural effects. Statistical Methods & Applications, 22:45-66 (DOI: 10.1007/S10260-012-0221-4)
R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(BBRecapture)
Loading required package: HI
Loading required package: locfit
locfit 1.5-9.1 2013-03-22
Loading required package: lme4
Loading required package: Matrix
Loading required package: secr
This is secr 2.10.3. For overview type ?secr
> png(filename="/home/ddbj/snapshot/RGM3/R_CC/result/BBRecapture/BBRecapture-package.Rd_%03d_medium.png", width=480, height=480)
> ### Name: BBRecapture-package
> ### Title: Bayesian Behavioural Capture-Recapture Models
> ### Aliases: BBRecapture-package
> ### Keywords: Behavioural models Likelihood failure Bayesian inference
> ### Unconditional MLE Conditional MLE Capture-recapture
>
> ### ** Examples
>
>
> data(greatcopper)
> out=BBRecap(greatcopper,mod="Mb")
> print(out)
$Model
[1] "mod.Mb"
$prior.N
[1] "Rissanen"
$N.hat.RMSE
[1] 63
$HPD.N
[1] 46 134
>
>
>
>
>
>
> dev.off()
null device
1
>