The ContionAl Prevalence Estimation (cape) package, allows to estimate and build confidence intervals for proportions, from random samples and census data with participation bias. Measurement errors in the form of false positive and false negative are also included the the inferential procedure. The cape package also contains code for simulation studies and sensitivity analysis reported in the companion paper Guerrier, Kuzmics, and Victoria-Feser (2020).

# Remark on notation

The notation and conventions used in Guerrier, Kuzmics, and Victoria-Feser (2020) are slightly amended for convenience in this package. In particular, we use R1 instead R11, R2 instead of R10, R3 instead of R01 and R4 instead of R00.

# Package installation

The cape package can be installed from GitHub as follows:

# Install devtools
install.packages("devtools")

# Install the package from GitHub
devtools::install_github("stephaneguerrier/cape")

Note that Windows users are assumed that have Rtools installed (if this is not the case, please visit this link).

# How to cite

@Manual{guerrier2020cape,
title = {{cape}: Conditional Prevalence Estimation using Random and Non-Random Sample Information},
author = {Guerrier, S and Kuzmics, C and Victoria-Feser, M.-P.},
year = {2020},
note = {R package},
url = {https://github.com/stephaneguerrier/cape}
}

# Graphical user interface

A Graphical User Interface (GUI) is available with the cape R package. This GUI which can be launched as follows:

gui()

It allows to compare the methods considered in the package as illustrated below:

The license this source code is released under is the GNU AFFERO GENERAL PUBLIC LICENSE (AGPL) v3.0. Please see the LICENSE file for full text. Otherwise, please consult TLDR Legal or GNU which will provide a synopsis of the restrictions placed upon the code.

# References

Guerrier, Stéphane, Christoph Kuzmics, and Maria-Pia Victoria-Feser.

1. “Prevalence Estimation from Random Samples and Census Data with Participation Bias.” http://arxiv.org/abs/2012.10745.