张俊妮《概率统计》北大光华-lecture8.pptVIP

BMI=weight (in kg)/[height (in m)]^2 BMI18.5 underweight 18.5-24.9 normal 25.0-29.9 overweight 30.0 and above obese If we know the joint distribution of height and weight for certain population, can we infer the distribution of BMI in the population? If we know the joint distribution of the number of years of education and annual income for certain population, can we infer the distribution of (annual income/years of education)? Refer back to page 13. * Lecture 8 Functions of a Random Variable Functions of Two or More Random Variables. Functions of A Random Variable Suppose X has a discrete distribution with p.f. f, and Y=r(X), a function of X. The p.f. of Y is: Variable with A Continuous Distribution Suppose X has a continuous distribution with p.d.f. f, and Y=r(X), a function of X. The d.f. G of Y can be derived as: If Y also has a continuous distribution, its p.d.f. g can be obtained by at any y where G is differentiable. Example Suppose X has a uniform distribution on (-1,1), What is the p.d.f for ? Solution: For 0y1, Direct Derivation of p.d.f. Suppose Y=r(X) where r is continuous, and X lies in a certain interval (a,b) over which the function r(x) is strictly increasing. Then r is a one-to-one function which maps (a,b) to (a,b) . It has an inverse function X=s(Y). For any y such that ayb, Suppose s is differentiable over (a,b), then Suppose Y=r(X) where r is continuous, and X lies in a certain interval (a,b) over which the function r(x) is strictly decreasing. Then r is a one-to-one function which maps (a,b) to (a,b) . It has an inverse function X=s(Y). For any y such that ayb, Suppose s is differentiable over (a,b), then Theorem. Let X be a random variable for which the p.d.f. is f and Pr(aXb)=1. Let Y=r(X), and suppose that r(x) is continuous and either strictly increasing or strictly decreasing for axb. Suppose also that r(x) maps axb to ayb, and let X=s(Y) be