Demographers conventionally group survey respondents into categories. Along the lines of classical set theory, membership in a category is a dichotomous 0-1 variable. In this article, I present an alternative to this yes-no grouping in which observations belong to fuzzy sets, in which the membership is a gradation between 0 and 1, depending on the extent to which a person belongs to the set. The analysis uses data on a sample of women from the 1982 U.S. National Survey of Family Growth, and substantively focuses on reasons for sterilization. The log-multiplicative association model is used to estimate contraceptiveness, i.e., the extent to which sterilization was for a contraceptive purpose, versus a medical purpose.
ASJC Scopus subject areas
- Geography, Planning and Development
- Agricultural and Biological Sciences(all)