Resource Library

This archive contains datasets from articles in the Journal of the American Statistical Association.

This page from the Social Security Administration's website gives links to various tables of data about Medicare, Social Security, Taxes, etc. Data files are available as pdf, html, or Excel files.

This site provides links to tests and quizzes for the Statistics and Data Analysis for Public Policy and Sociology course at Duke University for 1992 through 1995.

MacAnova is a free, noncommercial, interactive statistical analysis program for Windows 95/98/NT, Windows 3.1 with Win32s, Macintosh and Unix. MacAnova has many capabilities but its strengths are analysis of variance and related models, matrix algebra, time series analysis (time and frequency domain), and (to a lesser extent) uni-variate and multi-variate exploratory statistics.

Lisp-Stat is an extensible statistical computing environment for data analysis, statistical instruction and research, with an emphasis on providing a framework for exploring the use of dynamic graphical methods. The object-oriented programming system is also used as the basis for statistical model representations, such as linear and nonlinear regression models and generalized linear models. Many aspects of the system design were motivated by the S language.

This site gives the outlines and shows the lessons for psychology 340/341: Advanced Statistical Methods.

This site describes what to do with data sets instead of simply presenting theory and methods as they appear in standard textbooks. It emphasizes statistical practices.

The ICPSR provides access to a large repository of social science and political data. Data sets can be constructed and downloaded for use in most popular statistical packages.

This page has data sets used by UCLA statistics classes. The html files in the second column contain descriptions of a particular data set and a link to the data at the end of the file. There are also .dat and .dta files that contain just data, with no description.

This page discusses disadvantages of large datasets with regard to Simpson's Paradox.