Statistics (I) Final Exam Jan. 17, 2002 10 points for each problem. (1)Using moment-generating functions , show that as the gamma distribution , properly standardized , tends to the standard normal distribution. (2) 【a】Let X 1 ,…,X n be a sample from an N( x , 2 )distribution and Y 1 ,…,Y m be an independent sample from an N( y , 2 )distribution. Show how to use the F 2 S 1 n 2 ( X i X )2 and distribution to find P( x 2 >c),where S x n 1 i 1 Sy Sy 2 1 m ( Y j Y )2 . m 1 j 1 2 【b】Find the approximate variance of Sx by Taylor series expansion. 2 Sy (3)Suppose that X 1 ,…,X n is an i.i.d. sample of size n follows a geometric distribution P(X = k)= p(1-p) k 1 . 【a】Find the method of moments estimate of p. 【b】Find the sampling distribution of the moment estimate derived in 【a】. (4)Assuming that X~ N( 0 , 2 ), find the moment generating function of X and show the even moments of X are 2 n ( 2n )! 2 n . 2 n ( n! ) (5)Assume the joint density of X and Y is f(x,y) = 2 , 0 x y . 【a】Find the best linear predictor(denoted by Ŷ a bX )and the minimum mean square predictor of Y in terms of X. 【b】Compare the mean square prediction errors of the two predictors derived from【a】. (6)Let T be an exponential random variable with parameter , and conditional on T. Let U be uniform on [0,T]. 【a】Find the unconditional mean and variance of U. 【b】 Find the correlation of T and U. (7)Assume U i , i 1,2 , …,n are independent uniform random variables. 【a】Find the density of U ( n ) U ( 1 ) , where U ( n ) and U ( 1 ) are the maximum and minimum of U i ' s , respectively. 【b】Find E( U( n ) U( 1 ) ).