ic.fit

A matrix with one row and 2^k-1 column
  containing cell counts or empirical cell probabilities
  corresponding to all the possible capture patterns.

densi

A list of character vectors, with each
  vector containing column names from the associated
  log-linear design matrix. For example, see the output of
  <code><a href="/link/make.hierarchical.term.sets?package=lllcrc&version=1.1" rd-options="" data-mini-rdoc="lllcrc::make.hierarchical.term.sets">make.hierarchical.term.sets</a>()</code>.

models

If you multiply <code>densi</code> by <code>N</code> and
  then sum over the resulting vector, you should get the
  effective sample size.

The information criterion, such as AIC, AICc,
  BIC, or BICpi.

Logical: TRUE means that we use
  information criterion scores to do model averaging.

averaging

Logical: TRUE means that beta0 will be
  adjusted so that the log-linear model corresponds to cell
  probabilities instead of expected cell counts.

normalized

Logical: TRUE means that the Rasch model is
  a candidate.

rasch

Use an information criterion to select a local log-linear
model

Applies local log-linear capture-recapture models (LLLMs) a for
    closed populations, as described in the ongoing doctoral thesis work of
    Zachary Kurtz in the department of statistics at Carnegie Mellon
    University.  The method is relevant when there are 3-4 capture occasions,
    with auxiliary covariates available for all capture occasions.  As part of
    estimating the number of missing population units, the method estimates the
    "rate of missingness" as it varies over the covariate space.  In addition,
    user-friendly functions are provided to recreate (approximately) the method
    of Zwane and Van der Heijden (2004), which applied the VGAM package in a
    way that is closely related to LLLMs.

ic.fit: Select and fit an LLM

Description

Usage

Arguments

Value

Details