The data sources described in this catalog fall into four broad categories: publicly available data sets, restricted use data sets, published tables (with or without on-line tabulation capability), and published tables with special tabulations available. Each of these data source types is described briefly below.
Publicly available data sets are collections of raw data records, usually in numeric format that can be downloaded or transmitted by disk, CD, or email to users for analysis. These may contain one record per person, per interaction, or per household. The researcher can access the data in these data sets in order to seek answers to specific questions he/she has. However, analysis of these data sets requires the appropriate computer equipment, a data analysis program (e.g., SAS, SPSS), and a data analyst skilled in handling raw numeric data. Additionally, analysis of some datasets from research efforts that used complex sampling procedures to select respondents may require the use of software designed to correctly estimate variances, such as WesVar or SUDAAN. These data are termed "publicly available" because all identifying information has been removed to allow their use by researchers other than those who collected the data. Publicly available data may be free to users or there may be a fee for acquiring the data. In some cases, potential users may have to complete a data access form and confidentiality agreement. Some examples of publicly available data sets included in this catalog are the American Housing Survey, the National Health Interview Survey, and the Adoption and Foster Care Analysis and Reporting System.
Restricted use data sets are also collections of raw data records that researchers can analyze in a way similar to the publicly available data sets. They also require computer equipment and special software to analyze. They differ from publicly available data sets in that their use is carefully monitored and restricted. Usually, these restrictions are in place to protect confidential information stored in the data set (e.g., names, addresses, income). Holders of restricted use data sets always require potential secondary users to complete a data access agreement. Some data sources require that potential users also submit a proposal for how they will use the data (e.g., research questions to be addressed), proof of financial support for the analyses, and personal information on the users. Some sources may also require that the users perform their analyses in a designated location. There may or may not be a charge for access to these data sets. Some examples of restricted use data sets included in this catalog are the National Survey of Family Growth and the American Community Survey (full sample).(7)
In some cases, data sources that will not permit access to the raw data, or have extremely limited access to the raw data, have developed on-line analytical capability that will allow public users to conduct some analyses on their own. Users may or may not have full access to the data and types of analyses may be restricted. One example of a data source that allows very limited access to the data but has on-line analytical capabilities included in this catalog is the American Community Survey (full sample).
Data sources that supply only published tables will not allow secondary users access to the raw data. Once the data are collected and analyses are completed, large tabular volumes containing the results from the analyses are published. Potential users can report only the information presented in these tables. For this catalog, these data sources are included only if the published tables have been determined to be of use to researchers and policy makers interested in issues related to the health and well-being of American Indians, Alaska Natives, or other Native Americans. Some examples of data sources that supply only published tables included in this catalog are the Pediatric Nutrition Surveillance System and the Pregnancy Nutrition Surveillance System.
Data sources that both supply published tables and conduct special request tabulations typically do not allow users access to the raw data and have large published tabular volumes. They, however, also have staff that can perform additional analyses at user request to address questions not covered in the tabular volume. The complexity of the additional analyses that can be conducted may vary across sources as will the possible charge for these special requests. Two examples of data sources included in this catalog that conduct special request tabulations are the Resource Patient and Management System, which is the program reporting database for the Indian Health Service, and the Census of Agriculture.
"report.pdf" (pdf, 1.56Mb)
"apa.pdf" (pdf, 107.76Kb)
"apb.pdf" (pdf, 88.97Kb)
"apc.pdf" (pdf, 233.07Kb)