Learn R Programming

lllcrc (version 1.2)

Local Log-linear Models for Capture-Recapture

Description

Applies local log-linear capture-recapture models (LLLMs) for closed populations, as described in the doctoral thesis of Zachary Kurtz. The method is relevant when there are 3-5 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.

Copy Link

Version

Install

install.packages('lllcrc')

Monthly Downloads

11

Version

1.2

License

GPL-2

Maintainer

Zach Kurtz

Last Published

October 5th, 2014

Functions in lllcrc (1.2)

construct.vgam

Make a VGAM model
flat.IC

Select an LLM
extract.CI

Use bootstrap output to get CI
ic.fit

Select and fit an LLM
odd.evens

Determine the even-ness of capture patterns
lllcrc-package

Local Log-linear Models for Capture-Recapture
ic.all

Compute an IC for several LLMs
get.IC

Compute an information criterion
AICc.vgam

Compute the AICc for a VGAM model
smooth.patterns

Local averaging for LLLMs
make.hierarchical.term.sets

Generate a universe of hierarchical models.
age.sex.zip

Simulate CRC data with age, sex, and zip code
vgam.crc

Build a VGAM CRC model
patterns.possible

Generate all observable capture patterns
initialize.u.vec

Initialize log-linear parameters
apply.local.ml

Fit LLLMs
french.1

A fake dataset, french.1
make.design.matrix

Construct standard LLM design matrix.
flat.log.linear

Fit an LLM
rates.by.category

Display estimated rates of missingness by category
vgam.crc.boots

Bootstrapping for a VGAM CRC model
pirls

Maximum likelihood for log-linear coefficients
micro.post.stratify

Collapse CRC data through micro post-stratification
summary.lllcrc

Summary of LLLM or VGAM CRC analysis
y.string.to.y.glm

Capture patterns to design matrix
zglm

Maximum likelihood for log-linear coefficients
apply.ic.fit

Select an LLLM at each point
lllcrc

Local log-linear models (LLLMs) for capture-recapture (CRC)
stackydens

Stack local capture pattern frequencies for plotting
local.ml

Maximum likelihood estimation for fixed LLLMs
resample.captures

Tool for bootstrapping
init.pop

Set up a fake population
poptop

Simulate a CRC experiment
ic.wghts

Information criterion model weights
make.patterns.template

Template for capture-pattern counts
lllcrc.boots

Bootstrap for LLLMs
as.num

Conversion to numeric
llcrc.flat.boots

Bootstrapping LLMs
formatdata

Format the CRC data
captures

Simulating captures
plot.llsim

Plot the output of llm.sim
saturated.local

Use odd-even formula to fit saturated LLM
plot.lllcrc

Plot LLLMs
llm.sim

Simulate basic log-linear CRC experiments
pop.to.counts

Put CRC data into LLM vector
patterns

Collapse capture events into capture patterns (strings)
string.to.array

Put LLM vector into a LLM design matrix
summarize.by.factors

Summarize LLLM by factor