Docsity
Docsity

Prepare for your exams
Prepare for your exams

Study with the several resources on Docsity


Earn points to download
Earn points to download

Earn points by helping other students or get them with a premium plan


Guidelines and tips
Guidelines and tips

Math 281A Homework 2: Statistical Inference and Hypothesis Testing, Assignments of Mathematical logic

probability and statistical inference

Typology: Assignments

2021/2022

Uploaded on 01/21/2023

Shashi123
Shashi123 🇮🇳

5 documents

1 / 1

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Math 281A Homework 2
Due: Oct 17, in class
1. Let X1,...,Xnbe i.i.d. from N(0,1), show that ¯
Xand (X1¯
X,...,Xn¯
X)are independent.
2. Suppose that random vector (X, Y )has probability density function
1
πex2+y2
2I(xy >0).
Does (X, Y )possess a multivariate normal distribution? Find the marginal distributions.
3. Suppose Tnand Snare sequences of estimators such that
n(Tnθ)d
Ð Nk(0,Σ),and Sn
P
Ð Σ,
for a certain vector θand a nonsingular matrix Σ. Show that
(a) Snis nonsingular with probability tending to one;
(b) {θn(Tnθ)S1
n(Tnθ)χ2
k,α}is a confidence ellipsoid of asymptotic confidence level 1 α.
4. Suppose that XmBinomial(m, p1), YnBinomial(n, p2)and they are independent. To test H0p1=
p2=a, we consider the test statistic
C2
m,n =(Xmma)2
ma(1a)+(Ynna)2
na(1a).
(a) Find the limit distribution of C2
m,n as m, n ;
(b) How would you modify the test statistic if awere unknown? What’s the limit distribution after
modification? You don’t need to rigorously prove this question.

Partial preview of the text

Download Math 281A Homework 2: Statistical Inference and Hypothesis Testing and more Assignments Mathematical logic in PDF only on Docsity!

Math 281A Homework 2

Due: Oct 17, in class

  1. Let X 1 ,... , Xn be i.i.d. from N ( 0 , 1 ), show that

X and (X 1 −

X,... , Xn −

X) are independent.

  1. Suppose that random vector (X, Y ) has probability density function

π

e

x

2 +y

2

2 I(xy > 0 ).

Does (X, Y ) possess a multivariate normal distribution? Find the marginal distributions.

  1. Suppose T n

and S n

are sequences of estimators such that

n(T n

− θ)

d

Ð→ N k

( 0 , Σ), and S n

P

Ð→ Σ,

for a certain vector θ and a nonsingular matrix Σ. Show that

(a) S n

is nonsingular with probability tending to one;

(b) {θ ∶ n(T n

− θ)

⊺ S

− 1

n

(T

n

− θ) ≤ χ

2

k,α

} is a confidence ellipsoid of asymptotic confidence level 1 − α.

  1. Suppose that X m

∼ Binomial(m, p 1

), Y

n

∼ Binomial(n, p 2

) and they are independent. To test H 0

∶ p 1

p 2

= a, we consider the test statistic

C

2

m,n

(X

m

− ma)

2

ma( 1 − a)

(Y

n

− na)

2

na( 1 − a)

(a) Find the limit distribution of C

2

m,n

as m, n → ∞;

(b) How would you modify the test statistic if a were unknown? What’s the limit distribution after

modification? You don’t need to rigorously prove this question.