Survey analysis in R

An experimental package for very large surveys such as the American Community Survey can be found here

A port of a much older version of the survey package (version 3.6-8) to S-PLUS 8.0 is available from CSAN (thanks to Patrick Aboyoun at Insightful).

Features:

• Means, totals, ratios, quantiles, contingency tables, regression models, loglinear models, survival curves,rank tests, for the whole sample and for domains.
• Variances by Taylor linearization or by replicate weights (BRR, jackknife, bootstrap, multistage bootstrap, or user-supplied)
• Multistage sampling with or without replacement.
• PPS sampling with or without replacement: Horvitz-Thompson and Yates-Grundy estimators and a range of approximations.
• Post-stratification, generalized raking/calibration, GREG estimation, trimming of weights.
• Two-phase designs. Estimated weights for augmented IPW estimators.
• Graphics
• Support for using multiply imputed data
• Database-backed design objects for large data sets (now with replicate weights, too)
• Some support for parallel processing on multicore computers.
• Multivariate analysis: principal components, factor analysis (experimental).
• Likelihood ratio (Rao-Scott) tests for glms, Cox models, loglinear models.

Comparison shopping:
Alan Zaslavsky keeps a comprehensive list of survey analysis software for the ASA Section on Survey Research Methods.

User-generated ratings and reviews of this package (and others) at crantastic.

• Specifying a survey design
• Creating replicate weights
• Simple summary statistics
• Using supplied replicate weights
• Domain (subpopulation) estimation
• Tables of summary statistics
• Post-stratification and calibration
• Lonely PSUs
• Regression models
• Tests of association
• Stratification within PSUs
• Graphics
• Multiple imputation and ordinal logistic regression
• Database-backed survey objects
• Programming with survey objects

Some examples (in PDF) translated from Stata and SUDAAN examples at UCLA Academic Technology Services.

Notes on the sparse matrix algorithms used in version 3.15 for two-phase designs (and perhaps more widely in future versions)

Anthony Damico has R scripts for downloading and analysing major US government surveys at Github. He reported on comparisons of the survey package with SAS, Stata, SUDAAN in The R Journal 1(2) 37-45

I have a course at statistics.com, which will be repeated as demand permits

I gave a workshop on two-phase designs at the 3rd North American Congress of Epidemiology, in Montreal, June 21,2011

I gave a two-day course for the Washington (DC) Statistical Society, March 23-24 2010. First day on R, second day on the survey package

Norman Breslow and I gave the course at STATISTICALPS 2009, at the beginning of September in the Italian Alps. The course will include an introduction to the survey package, but will focus on two-phase designs in epidemiology. We will have some code and data up soon.

Slides from a short tutorial at the US Census Bureau, August 10.

I gave a tutorial at useR 2009, on the afternoon of July 7, 2009.

A 1.5 hour brief introduction to R, including a bit on the survey package, at the AAPOR conference, Friday May 15, 10:30am.

Tobias Verbeke has packaged data sets and exercises from Sharon Lohr's Sampling: Design and Analysis for use with the survey package.

I gave a short course for the Washington Statistical Society on March 15-16 2007. The first day was on R and the slides are a selection from these. The second day was on the survey package, slides here.

There is an article on version 3.6-12 of the package in the January 2008 issue of Survey Statistician (note: large PDF file)

• Vignettes
• PDF from CRAN
• HTML