Stats 242.3(02) – Assignment 3 Solutions I Suppose that x1, x2, x3, ..., xn is a sample from the gamma distribution with parameters 0 and . That is the density of xi is given by: 0 0 1 x f ( x| ) x e 0 Assume that 0 is a known constant. Find the maximum likelihood estimator of the unknown parameter . n n xi 0 0 1 xi n 0 0 1 i L f ( xi | ) xi e x x x x e 1 2 3 n n 0 i 1 i 1 0 l ln L n 0 ln n ln 0 0 1 ln xi xi i l n 0 II 1 xi 0 if ˆ i i 0 x Suppose that x1, x2, x3, ..., xn is a sample from the density 1x 0 x 1, 1 f (x | ) 0 elsewhere Find i the method of moments estimator of the unknown parameter . 1 1 0 xf ( x | )dx ( 1) x x 1 x 2 1 dx ( 1) 2o 2 1 or 2x 1 and x 1 1 2 x , Thus the method of moments 2 ~ 1 2x estimator is x 1 ii the maximum likelihood estimator of the unknown parameter . n n i 1 i 1 L f ( xi | ) 1xi 1 x1 x 2 x3 x n for 1. n l ln L n ln 1 ln x1 ln x2 ln x3 ln xn . n n l ln x1 ln x 2 ln x3 ln x n 0 if ˆ 1 1 ln xi i Page 1 Stats 242.3(02) – Assignment 2 III Solutions Suppose that x1, x2, x3, ..., xn is a sample from the density 1 0 x 2 1 2 1 f (x | ) 0 elsewhere Find i the method of moments estimator of the unknown parameter . 2 1 0 xf ( x | )dx 2 1 x2 x dx 2 1 22 1 o 2 12 2 1 1 2 22 1 2 ~ x 12 . Thus the method of moments estimator is x 12 ii n L i 1 the maximum likelihood estimator of the unknown parameter . n 1 0 xi 2 1 for all i 2 1 i 1 f ( xi | ) 0 otherwise 1 n max xi 2 1 2 1 0 otherwise n ln 2 1 l ln L 0 2n max xi 1 2 2 1 l 0 max2xi 1 Hence ˆ max2xi 1 since l 0 for max xi 1 / 2 . otherwise max xi 1 2 Page 2 Stats 242.3(02) – Assignment 2 IV Solutions Suppose that X and Y are independent unbiased measurements of the angle and 3 respectively. Namely E(X) = and E(Y) = 3. In addition assume that X and Y have the same variance 2. i) Determine the conditions on a and b that would result in T = aX + bY being and unbiased estimator of . ET EaX bY aE X bEY a b3 a 3b if a + 3b = 1 ii) Determine the values of a and b that would make T = aX + bY the unbiased estimator of with the smallest variance. V Var T Var aX bY a 2Var X b 2Var Y 2 1 a 2 a b a 3 dV 1 a 1 V is minimized when 2a 2 0 da 3 3 1 a 1 1 a 1 18 8 1 7 That is a or 9a = 1 – a and a . Also b 9 8 3 3 24 24 7 1 Hence T 8 X 24 Y . 2 2 Page 3