abun_oi-class: abun_oi class

In ecnuliuyang/AbunOI: Semiparametric empirical likelihood inference for abundance from one-inflated capture-recapture data

Description

A S4 class is used to present the data, model specification, and maximum empirical likelihood (EL) estimation results under one-inflated count regression models.

Slots

model

character specification of "zt" (zero-truncated model without one-inflation), "ztoi" (zero-truncated one-inflated model), or "oizt" (one-inflated zero-truncated model).

dist

character specification of count regression model family, "poisson" or "binomial".

N

number representing the maximum EL estimate of abundance N.

ci

vector representing the EL ratio confidence interval of abundance.

beta

vector representing the maximum EL estimate of regression coefficients in count regression model.

eta

vector representing the maximum EL estimate of regression coefficients in logistic regression model for one-inflation.

alpha

number representing the maximum EL estimate of the probability of never being captured.

loglikelihood

number representing the log-EL value.

AIC

number representing the Akaike Information Criterion value.

prob

vector representing the probability masses of individual covariates.

nit

number representing the number of iterations of EM algorithm.

pars_trace

matrix. Row shows the value of parameters in each iteration of EM algorithm.

loglikelihood_trace

vector. Element represents the value of log-likelihood in each iteration of EM algorithm.

y

vector specifying the number of times that individuals were captured.

K

number specifying the number of capture occasions.

x

matrix specifying the individual covariates in count regression model.

z

matrix specifying the individual covariates in one-inflated regression model.

epsilon

positive convergence tolerance ε. The iterations converge in EM algorithm when the increase of the log-EL is less than ε.

maxN

number specifying the largest searching value for N in EM algorithm.

maxN_ci

number specifying the largest searching value for calculating the confidence interval of N.

level

number specifying the nominal level of confidence interval of N.

maxit

integer specifying the maximal number of iterations in EM algorithm.

start_beta

vector specifying the starting value of the coefficient β in count regression model in EM algorithm.

start_eta

vector specifying the starting value of the coefficient η in one-inflated regression model in EM algorithm.

ecnuliuyang/AbunOI documentation built on Feb. 13, 2022, 4:32 p.m.