张俊妮《概率统计》北大光华-lecture13.pptVIP

* Lecture 13 Conditional Expectation and Variance Bivariate Normal Distribution Conditional Expectation Suppose X and Y are random variables with joint p.f. or p.d.f. f(x,y), let f1(x) denote the marginal p.f. or p.d.f. or X, for any value of x such that f1(x)0, let g(y|x) denote the conditional p.f. or p.d.f. of Y given X=x. The conditional expectation of Y given X , denoted by E(Y|X), is specified as a function of X: The Conditional Expectation Is a Random Variable E(Y|X) is a function of the random variable X, so it is itself a random variable with its own distribution. The distribution of E(Y|X) can be derived from the distribution of X. We can find the mean and the variance of E(Y|X). Theorem. For any random variables X and Y, E[E(Y|X)]=E(Y). Proof. Assume for convenience that X and Y have a continuous joint distribution, then Conditional Variance Let Var(Y|x) denote the variance of the conditional distribution of Y given X=x, i.e., Variance and Conditional Variance Eve’s Law Proof. Example. Customers with Coupons Suppose that the number of customers coming to certain McDonald store in a day follows a Poisson distribution with parameter l. Suppose that each customer independently presents a coupon with probability p (and no coupon with probability q=1-p). What are the expectation and variance of the number of customers using coupons in a day? Solution. Customers with Coupons Let N denote the number of customers in a day. Let X denote the number of customers using coupons in a day. Solution. Customers with Coupons The Bivariate Normal Distribution Suppose that Z1 and Z2 are independent random variables, each of which has a standard normal distribution. For any constants such that define X1 and X2 as follows: X1 and X2 are said to have a bivariate normal distribution. Marginal Distributions Since both X1 and X2 are linear combinations of Z1 and Z2, the marginal distribution of both X1 and X2 are normal