samplingbook package

CRAN Status Badge CRAN Downloads CRAN LicenseCRAN dependencies statusWebsite

Sampling procedures from the book ‘Stichproben - Methoden und praktische Umsetzung mit R’ by Goeran Kauermann and Helmut Kuechenhoff (2010).

The book introduces the basic principles for sampling and corresponding statistical analysis. The following topics are covered:

  1. Introduction of Basic Sampling Principles
  2. Simple Sample Methods
  3. Model-based Sampling
  4. Design-based Sampling: Horvitz-Thomson Estimate
  5. Grouping of Populations: Stratified and Cluster Sampling
  6. Methods with Multiple Phases
  7. Problems in Real-World Applications

Each chapter concludes with exemplifying real-world applications in R, which utilize the functions from this R package.

Installation

You can install the latest production version from CRAN

install.packages("samplingbook", dependencies = TRUE)

or the current development version from GitHub

library("devtools")
install_github("jmanitz/samplingbook")

Then, load the package

Example: Simple Sample and Estimation of Proportions

In a company with N=300 employees a survey was conducted regarding to improve working conditions. A random sample of n=100 employees was drawn and two questions were asked:

  • Would you support more flexibility in your working hours?
  • Would you support a possibility for child care within the company?

The questions were answered with “yes” by 45 and 2 employees, respectively. Using samplingbook::Sprop(), we can estimate the proportions of support in the entire company:

Sprop(m=45, n=100, N=300)

Thus, between 37% and 53% of all employees, thus between 111 and 159 persons, are estimated to support more flexible working hours.

Sprop(m=2, n=100, N=300)

On the other hand, the survey results that only between 1 and 19 employees would support child care within the company.

The example shows, that in particular the for small proportion estimates, the calculations of exact confidence intervals using the hypergeometric distributions is more appropriate.

Some remarks on exact hypergeometric confidence intervals for proportion estimates can be found in the vignette.

Contributions

  • Goeran Kauermann and Helmut Kuechenhoff for their guidance and ideas
  • Cornelia Oberhauser for proof reading and testing
  • Mark Hempelmann, Shuai Shao, Nina Westerheide, and Manuel Wiesenfarth for contributing source code

Citation

Juliane Manitz, Mark Hempelmann, Goeran Kauermann, Helmut Kuechenhoff, Shuai Shao, Cornelia Oberhauser, Nina Westerheide and Manuel Wiesenfarth (2020). samplingbook: Survey Sampling Procedures. R package version 1.2.4. https://CRAN.R-project.org/package=samplingbook

Use toBibtex(citation("samplingbook")) in R to extract BibTeX references.