关键词 > STATS310/732
STATS 310/732 Introduction to Statistical Inference SEMESTER 1, 2021
发布时间:2022-06-02
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
STATS 310/732
Introduction to Statistical Inference
SEMESTER 1, 2021
1. Let the random variables X1 ,X2 have the joint density function f(x1 ,x2 ) = 2e−x1 −x2 , x1 ≥ x2 ≥ 0.
(a) Find the conditional density function f1 (x1 |x2 ), including its support.
[6 marks] (b) Find the probability density function of Y = X1 + X2 , including its support.
[6 marks]
[12 marks]
2. Let X ∼ N(µ,σ2 ) and Y ∼ Gamma(k,λ) (for k > 1) independently. In terms of the parameters, nd E(X/Y).
[6 marks]
3. Let θ = (θ 1, . . . , θp)T be an unbiased estimator of a vector parameter θ = (θ1 , . . . ,θp )T ,
(a) E(Ui ) = 0, for i = 1, . . . ,p.
[6 marks]
(b) Cov(θ i,Uj ) = 0, for any i = j .
[6 marks] [12 marks]
4. Let x1 ,x2 , . . . ,xn be a random sample drawn independently from a distribution with probability density function
f(x;θ) = e− √x , x > 0, θ > 0.
(a) Find the method-of-moments estimator θ 1 of θ . [5 marks]
(b) Find the maximum likelihood estimator θ 2 of θ . (You do not need to perform
(c) Find the Fisher information.
[5 marks]
(d) Find a new parametrisation λ = g(θ) so that the maximum likelihood estima-
tor λ is the minimum variance unbiased estimator of λ . Justify your answer.
[20 marks]
5. Consider a probability density function that has the form f(x;θ) = cθ 1 θ2(2)e−x 1 −x2 2 , x,θ 1 ,θ2 > 0,
where θ = (θ1 ,θ2 ) and c is a constant. Let x1 , . . . ,xn be a random sample drawn independently from the distribution.
(a) Find the MLE θ of θ . (You do not need to perform the second derivative test.)
[5 marks]
(c) What is the limiting distribution of √n(θ 1 − θ 1 ), as n → ∞ ? [5 marks]
[5 marks] [20 marks]
6. Let X have a distribution with density function
f(x;θ) = θ(θ + 1)(1 − x)x − 1 , 0 < x < 1, θ > 0.
One is interested in testing
H0 : θ = 1 vs. H1 : θ > 1.
(a) Let C = {x : x < a } be the critical region of some test at the signi cance level of α for a single observation x from the distribution. Find the value of a0.05 .
[5 marks]
(b) For a random sample x1 , . . . ,xn independently drawn from the distribution, does the uniformly most powerful test exist at the signi cance level of α? Explain why.
[5 marks] [10 marks]
7. Let Y1 ,Y2 ,Y3 be independent normally-distributed random variables with
E(Y1 ) = β1 , E(Y2 ) = β1 + 2β2 , E(Y3 ) = −2β1 + β2
and a common variance σ 2 .
(a) Find the least squares estimator β of β = (β1 ,β2 )T . [5 marks]
θ = d1 Y1 + d2 Y2 + d3 Y3
[5 marks]
[5 marks] [15 marks]
8. Show that the straight line represented by the linear regression model
which is a least squares t from n observations (x1 ,y1 ), . . . , (xn ,yn ), passes through the point (x, y), where x = n− 1 xi and y = n− 1 yi .
[5 marks]
9. For a decision-making problem, the following table gives R(di ,θj ), the risk of each candidate decision rule di for each state of nature θj :
θ 1 θ2
10
12
13
15
15
17
18
20
(a) Find all admissible rules.
[5 marks]
(b) Find the minimax rule(s). Justify your answer.
[5 marks] [10 marks]
10. Assume that X ∼ U(0, 1) if = θ 1 , or X ∼ Beta(2, 1) if = θ2 . Let the action space be {a1 ,a2 } and the loss matrix be
θ 1 θ2
0
20
Given the prior probabilities P( = θ1 ) = 0.6 and P( = θ2 ) = 0.4, nd the Bayes rule.
[5 marks]
11. Assume that a parameter θ ≥ 0 has a posterior density of the form
π(θ|x) ∝ e − x ,
for a random sample x1 , . . . ,xn with mean x = 5. Find the narrowest 95% posterior credible interval for θ .
[5 marks]