6 Independence in a Bivariate Distribution 6.1. Introduction We can recognize at least three possible responses to the question, How is Y related to X in a bivariate population?: the conditional pdf's (or pmf's) g 2 (y∣x), the conditional expectation function E(y∣x), and the best linear predictor E*(Y∣X). Correspondingly, we can recognize three pos- sible responses to the question, What does it mean to say that Y is not related to X in the bivariate population? 6.2. Stochastic Independence In any bivariate probability distribution we can write the joint pdf (or pmf) as the product of a conditional and a marginal pdf (or pmf): f(x, y) = g 2 (y∣x)f 1 (x) for all (x, y) such that f 1 (x) ≠ 0. To start, we say that Y is stochastically independent of X iff , where does not depend on x. In other words, the conditional probability distribution of Y given x is the same for all x-values; that is, the conditional probability distribution does not vary with--"is indepen- dent of"--X. One implication of stochastic independence is immediate: the marginal pdf of Y is. -58- |