Secondary analysis of large national databases offers promise for research of families. In this article, issues that the secondary analyst must consider when choosing a database for research of families are described. Potential advantages and limitations of databases are discussed. Strategies to minimize potential limitations are highlighted.

Secondary analysis provides a useful method for the development of new knowledge. Larger samples can be constructed, and secondary analysis can be enhanced when data sets are combined. A standardized method for combining large data sets is crucial, yet literature on methods for combining large data sets for secondary analysis is lacking. The purpose of this article is to outline and explain the process of combining two or more large data sets (n = 276, n = 125) for secondary analysis by using these authors' previous work with large oncology and AIDS caregiver data sets.

No abstract