An inferential model which utilizes surname comparisons in inferring legitimacy status is developed and validated. Criterion validation is employed to assess the level of agreement between the inferential approach and the conventional reporting procedure. Data for the analysis are based on a sample of birth certificates contained in files of the National Center for Health Statistics for calendar year 1973. Results indicate that despite excessive error within some categories of the control variables, the inferential method is generally adequate to obtain reliable estimates of illegitimacy.

The text of this article is only available as a PDF.
You do not currently have access to this content.