Add Health Data
The Add Health study has collected data of interest to investigators from many disciplines in the social and behavioral sciences and from many theoretical traditions.
Data are available for study from four instruments in Wave I (conducted from September 1994 through December 1995), two surveys in Wave II (conducted from April 1996 through August 1996), several sources in Wave III (collected from August 2001 through April 2002), and one in-home interview in Wave IV (conducted from January 2008 through February 2009).
Add Health data are available in two forms—a public-use dataset and a restricted-use contractual dataset. It is a central concern of the Add Health study that the confidentiality of respondents be strictly protected. Deductive disclosure concerns prevent full access to all data sources. For this reason, the distribution of data will be limited in several ways:
- Public-use data include only a subset of respondents.
- Restricted-use data (more extensive data) will be distributed only to certified researchers who commit themselves to maintaining limited access.
- In no case will geocodes be available to outside researchers.
The rationale for this release structure is to protect the identities of Add Health respondents while allowing access to the data to a wide range of researchers.
Using the Data
Public-use and contractual data offer endless options in the types of analysis, choices of data, and presentation. Users of the Add Health data have found that managing such large, complex datasets can be challenging, involving complicated skip patterns, multiple response categories and choices, inter-questionnaire ID matching, and other advanced data structures. As a service to the research community, Add Health offers the following resources on this website: