ABSTRACT
Bivariate regression is often inadequate for social science theory given that we typically expect that more than one variable explains the outcome. For example, we wrote our research questions about distance to include not only the adult’s earnings as a predictor of distance from the mother, but also the adult’s age and number of brothers and sisters and the mother’s age and years of schooling. We will add these additional variables, beyond earnings, to the model in this chapter (and in Chapter 10 we will add the adult’s gender and race-ethnicity as predictors as well). In this chapter, we will focus on a basic understanding of how to interpret and test coeffi cients estimated from the model. In later chapters we will elaborate on this understanding, for example discussing in more detail how and why coeffi cient estimates change when other variables are added to the model.
