Comparative point and interval estimates for the population size \(N\) obtained fitting many alternative behavioural and time effect capture-recapture models. AIC index is reported for each alternative model.
LBRecap.all(data, last.column.count=FALSE, neval=1000, by.incr=1,
which.mod=c("all","standard"), sort=c("default","AIC"))can be one of the following:
an \(M\) by \(t\) binary matrix/data.frame
a matrix/data.frame with \((t+1)\) columns according to the value of last.column.count
a \(t\)-dimensional array or table representing the counts of the \(2^t\) contingency table of binary outcomes \(M\) is the number of units captured at least once and \(t\) is the number of capture occasions.
a logical. In the default case last.column.count=FALSE each row of data represents the complete capture history for each observed unit. When codelast.column.count=TRUE in each row the first \(t\) entries represent one of the possible observed complete capture histories and the last entry (last column) is the number of observed units with that capture history
a positive integer. neval is the number of alternative values of the population size N where the likelihood is evaluated and then maximized. They run from the minimum value M and they are increased by by.incr (see below the description of the by.incr argument). The default value is neval=1000.
a positive integer. by.incr represents the increment on the sequence of evaluated values for \(N\). The default value is by.incr=1.
a character. which.mod selects which models are fitted and compared. In the default setting which.mod="all" all alternative models are fitted including new behavioural models based on alternative meaningful covariates (see Details). When which.mod="standard" the function only fits classical behavioural models with either enduring effects as in \(M_b\), \(M_{c_1b}\), \(M_{c_2b}\) or ephemeral effects as in purely Markovian \(M_{c_1}\) and \(M_{c_2}\)
character. sort selects the order of models.
A data.frame with one row corresponding to each model and the following columns:
model: model considered
npar: number of parameters
AIC: Akaike's information criterion
Nhat: estimate of population size
Ninf: lower \(95 \%\) confidence limit
Nsup: upper \(95 \%\) confidence limit
The available models are: \(M_0\), \(M_b\), \(M_t\), \(M_{c_1}\), \(M_{c_1b}\), \(M_{c_2}\), \(M_{c_2b}\), \(M_{mc}\),\(M_{mc_{int}}\), \(M_{mc_{count}}\) and \(M_{mc_{count.int}}\).
This function LBRecap.all can be computing intensive for high values of neval.
Alunni Fegatelli, D. and Tardella, L. (2016), Flexible behavioral capture<U+2013>recapture modeling. Biometrics, 72(1):125-135. doi:10.1111/biom.12417
Alunni Fegatelli D. (2013) New methods for capture-recapture modelling with behavioural response and individual heterogeneity. http://hdl.handle.net/11573/918752
Alunni Fegatelli D., Tardella L. (2012) Improved inference on capture recapture models with behavioural effects. Statistical Methods & Applications Applications Volume 22, Issue 1, pp 45-66 10.1007/s10260-012-0221-4
Farcomeni A. (2011) Recapture models under equality constraints for the conditional capture probabilities. Biometrika 98(1):237--242
Otis D. L., Burnham K. P., White G. C, Anderson D. R. (1978) Statistical Inference From Capture Data on Closed Animal Populations, Wildlife Monographs.
Yang H.C., Chao A. (2005) Modeling animals behavioral response by Markov chain models for capture-recapture experiments, Biometrics 61(4), 1010-1017
# NOT RUN {
data(greatcopper)
LBRecap.all(greatcopper)
# }
Run the code above in your browser using DataLab