SDA: Survey Documentation and Analysis

SDA is a set of programs for the documentation and Web-based analysis of survey data. SDA was developed, distributed and supported by the Computer-assisted Survey Methods Program (CSM) at the University of California, Berkeley until the end of 2014. Beginning in 2015, CSM is managed and supported by the Institute for Scientific Analysis, a private, non-profit organization, under an exclusive continuing license agreement with the University of California. CSM also develops the CASES software package.

To see how it all works, test-drive SDA at our demonstration SDA Archive. Browse the documentation for a survey and get fast data analysis results. The SDA Archive includes several datasets, including the General Social Survey (GSS), the American National Election Study (ANES), and the Survey of Consumer Finances (SCF). You can also look at some other archives that use SDA software.

For information on obtaining SDA software and services, see the SDA Software and Services page.

For video tutorials on using the SDA 4 user interface see the SDA YouTube Channel.

SDA Features

Documentation:

Codebooks: SDA can produce both HTML and print-format codebooks. The documentation for each study contains a full description of each variable, indexes to the variables, and links to study-level information.

DDI (Data Documentation Initiative) compatibility: SDA programs can produce DDI-format metadata from SDA datasets and from other metadata formats. SDA also provides an online utility that converts DDI metadata to SDA's own metadata format (DDL).

Analysis:

Various analysis types are available: frequencies and crosstabulation, comparison of means, correlation matrix, comparison of correlations, multiple regression, logit/probit regression.

Fast results: SDA was designed to produce analysis results very quickly -- within seconds -- even for large datasets with millions of cases and thousands of variables. Although many of our users assume we are using some sort of super computer to achieve these speeds, the secret lies solely in the method of storing the data and the design of the programs. The SDA Archive on our site runs on a low-cost (Intel) Linux server -- although SDA can also be run on Windows.

Creation of new variables with recode and compute procedures: SDA includes procedures to create new variables based on the content of existing variables through recode or compute specifications.

Complex standard errors: Data collected from stratified and/or cluster samples require special procedures to calculate standard errors and confidence intervals. SDA uses those special procedures for percentages, means, differences between means, and regression coefficients.

Charts: SDA produces various chart types: bar charts, stacked bar charts, line charts and pie charts.

Disclosure specifications for confidentiality: The analysis programs can be configured to suppress output that may compromise the confidentiality of survey respondents. The analysis programs will all read a disclosure configuration file (if one has been created for a study), and will enforce the specifications in that file.

Other Capabilities:

Subsetting: Users can generate and download a customized subset of an SDA dataset. In addition to generating a data file, the subset procedure produces a codebook for the subset and data definitions for SAS, SPSS, Stata and DDI. The subset can include both the original dataset variables and new variables created with recode or compute.

Searching: SDA provides searching both within a single study (at the variable level) and across studies (at both the variable and study level).

SDA Manager:

For managers of an SDA archive, the SDA software package includes an SDA Manager webapp. The SDA Manager consolidates all of the management functions for an SDA archive into one web interface. Using this web app the manager of an SDA archive can:

Import SPSS .sav files, Stata .dta files, CSV files and TSV files and automatically convert them into SDA datasets.
Create and configure personal user workspaces. These user workspaces enable analysts to create and store recoded and computed variables in their own private storage areas. For groups -- such as college classes -- the leader or instructor can make their created variables accessible to the group to use in their own analysis projects.
Configure dataset-level access control -- specifying which users can access which datasets.
Generate reports on usage of the datasets in the archive.
Troubleshoot problems.

Awards

American Association for Public Opinion Research (AAPOR): Warren J. Mitofsky Innovators Award

American Political Science Association (APSA): Best Instructional Software Award

For information on how to set up your own SDA data archive see the relevant documentation. For information on current SDA development efforts, see the projects page. Also, for recent events check the news.

If you've experienced any problems with our site or would just like to make suggestions or comments, send e-mail to: sda@berkeley.edu