MATH 357: Assignment 2
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
MATH 357: Assignment 2
Due date: Monday, February 20th, at 11:55 pm.
To be submitted online via myCourses
Winter 2023
Provide detailed answers to the following problems.
Problem 1. Let X ~ Gamma(α, β) with the pdf
f (x; α, β) = xa – 1 e –z/β , x > 0.
(a) Find the cumulative distribution function (cdf) of X, call it F .
(b) Using the R software, plot the cdf F (x) versus a range of values of x e [0, 10], with
increment 0.01. This range can be created using the following command in R, x<-seq(0,10,by=0 .01)
Generate five random samples X1 , X2 , . . . , Xn ~ Gamma(1, 4) of sizes
n = 10, 30, 60, 100, 300. Plot the empirical cdf (ecdf) of each of the samples on the same figure that you have the plot of F versus x. Use different colours or characters in R for the six plots on a single figure. Comment on your observations.
Problem 2.
(a) Let X1 , X2 , . . . , Xn be a random sample from a distribution with µ = E(Xi ) and σ 2 = Var(Xi ) < o. Find the asymptotic distribution of these statistics: (i) n(2) , (ii) 1/n , (iii) exp(n ), for both cases of µ 0 and µ = 0.
(b) Consider the random sample in part (a), and assume E(Xi(4)) < o. Show that, ^n(Sn(2) _ σ 2 ) _ N(0, µ4 _ σ4 ) as n → o,
where Sn(2) is the sample variance, and µ4 = E[(X _ µ)4]. What can we say about the asymptotic distribution of the sample standard deviation Sn ?
(c) Let Y ~ Poisson(λ). Find the asymptotic distribution of ^入(Y –)入 , as λ → o.
Problem 2. Let X1 , X2 , . . . , Xn be a random sample of size n from
f(x; θ) = e – (z–9) , x > θ
and f(x; θ) = 0, otherwise.
(a) Show that n (θ + 1), as n → o.
(b) Show that X(1) θ, as n → o.
(c) Using the results of (a)-(b), suggest two consistent estimators of θ which are also unbiased for θ .
(d) Find the UMVUE of θ, if exists.
Problem 4. Let X1 , X2 , . . . , Xn be a random sample from N(µ, 1), where µ e R is unknown.
(a) Find the CRLB for any unbiased estimator of µ2 .
(b) Find the UMVUE of µ2 and compare its variance with the CRLB in part (a).
Problem 5. Let X1 , X2 , . . . , Xn be a random sample from the exponential distribution
with pdf
f (x; θ) = θe –9z , x > 0
and θ > 0 is the unknown parameter.
(a) Show that the estimator T (X1 , . . . , Xn ) = n–乞i111xi is the UMVUE of θ .
(b) Find the variance of T in part (a), and compare it with the CRLB.
(c) For a fixed x0 > 0, find the UMVUE of F (x0 ; θ) = P9 (X1 < x0 ).
Problem 6. Let X1 , X2 , . . . , Xn be a random sample from Poisson(λ). If exists, (a) find the UMVUE of g1 (λ) = λk , for some fixed integer k > 0.
(b) find the UMVUE of g2 (λ) = P入 (X1 = 0).
Problem 7. Let X1 , X2 , . . . , Xn be a random sample from N (µ, σ2 ), with both param- eters unknown.
(a) Show that T (X1 , X2 , . . . , Xn ) = (n , Sn(2)) is a minimal sufficient statistics for this family. (It can be shown that T (X1 , X2 , . . . , Xn ) is also complete). (b) Find the UMVUE’s of µ , σ 2 , and σ .
Problem 8. Assume that X1 , X2 , . . . , Xm and Y1 , Y2 , . . . , Yn are two independent ran-dom samples from N (µ1 , σ 2 ) and N (µ2 , σ 2 ), respectively. The unknown parameters are (µ1 , µ2 , σ 2 ).
(a) Show that T = ( Xi , Yi , Xi(2) + Yi2 ) is a minimal sufficient statistic for this family.
(b) It can be shown that T is also complete. Find the UMVUE of σ 2 .
2023-02-19