Question

Let X1,X2,...,Xn be iid exponential random variables with unknown mean β.

(b) Find the maximum likelihood estimator of β.

(c) Determine whether the maximum likelihood estimator is unbiased for β.
(d) Find the mean squared error of the maximum likelihood estimator of β.

(e) Find the Cramer-Rao lower bound for the variances of unbiased estimators of β.
(f) What is the UMVUE (uniformly minimum variance unbiased estimator) of β? What is your reason?
(g) Determine the asymptotic distribution of the maximum likelihood estimator of β as n →∞.

Answer 1

P 1 let *, , X2 -. *n belid exponential random vagiable with unknown mean UH [(*): B and roo(%) - B2 f(XB) - 1/82 VB B E xy, o Blo O ow, b) first wo find maximum likelihood education The titih likelihood function is LCX; ) = 유 frai, B) 2 20%; B) T в е -B - 132 xi Il e Ba log on both side 10920861,5), =-nlogß alogh xi 1/B n INS ai "/p2 = B n + Exciso B tools als Á = 142 1/B2 Exi Exi h x Email is maximum likelihood estimatoo of ß CSScanned with CamScanner राष्ट्रीय

ara Cre) To determine the maximum likelihood estimated un biagod. Por B E (Eu (Emi) - ΣΕ(α) n Eno ß n. fp n B MALE is unbiased for B. do Mean Square orras MOSES Elx-Å.2 B Your Ex) rast n ff То Find out cramer-Rao low or bound alogh op + I åxi B2,51 taking 2nd partial derivative of wisit ß 2 o2 loge op? Exi B² p3 n 2 Ezei + 3 22log 2 ap2 taking expection ß² ps CSScanned with CamScanner

El-22log 2 3 t (De-) +1(52) ) + 2 1E() 2. 1 p3 +2nA p) 32 2n | | 32 32 n 32 (ramer-Rao Lowor bound is E (-22logi 이32 D 32 2. B D CSScanned with CamScanner