ABSTRACT
In 1948, the National Institutes of Health began funding a study aimed at uncovering the predictors of heart disease. The study involved 5209 adult residents of the city of Framingham, Massachusetts. The subjects were given complete physicals, including a battery of lab tests, and they filled out a questionnaire regarding their lifestyles. The probability of an observation can be written in a complicated mess of algebra with all the parameters. The Framingham Study introduced logistic regression to the medical community. This method of examining data has proven so useful in medicine that many issues of the major medical journals will have at least one article that uses logistic regression. One linear model based on a function of the observations, that is widely used in sociology, is the log-linear model. The data are arranged in tables showing the frequencies of some event in terms of different characteristics, like gender, socioeconomic class, or religion.
