Scribd
Upload
2 views3 pages

final_review

The document contains a series of statistical problems involving independent random samples from various distributions, including uniform, normal, and Laplace distributions. It covers topics such as finding probability density functions, constructing confidence intervals, hypothesis testing, and estimating parameters. Each question requires the application of statistical methods to analyze sample data and draw conclusions about population parameters.

Uploaded by

Chan Hufflepuff
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views3 pages

final_review

The document contains a series of statistical problems involving independent random samples from various distributions, including uniform, normal, and Laplace distributions. It covers topics such as finding probability density functions, constructing confidence intervals, hypothesis testing, and estimating parameters. Each question requires the application of statistical methods to analyze sample data and draw conclusions about population parameters.

Uploaded by

Chan Hufflepuff
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Final Review

Q1. LetX1 , X2 , · · · , Xn be an independent random sample from the uniform distribution

U (0, θ).

(a) Find the probability density function of X(n) .

(b) Construct a pivotal variable based on the sample maximum X(n) .

(c) Use the result in part (a) and (b), to construct a 1 − α confidence interval for θ.

Q2. Let X1 , X2 , · · · , Xn be an independent random sample from Uniform[θ, 0] for θ < 0.

Let X(1) be the smallest value of the sample {Xi }ni=1 .


X(1)
(a) Show that T = is a pivotal quantity.
θ
(b) Give a 1 − α equal-tailed confidence interval for θ.

Q3. Suppose that 9 persons are randomly selected, and their height (in cm) is measured in the

morning and evening. Let X to denote the height measured in the morning, and Y to denote the

height measures in the evening. The observed values for this sample are given in the following

table:
Number (i) 1 2 3 4 5 6 7 8 9

Height in the morning (xi ) 170 175 160 161 165 172 170 180 174

Height in the evening (yi ) 170 174 158 160 163 172 168 177 172
Suppose that X ∼ N(µx , σx2 ), Y ∼ N(µy , σy2 ). Assume the variance for the height in the

morning and evening are equal.

(a) Find a 95% confidence interval of µx .

(b) Find a 95% confidence interval of µx − µy .


2
(c) Is it reasonable to conclude that the height in the morning is higher than that in the evening

using 5% significance level?

Q4. Suppose 10 tires are randomly selected from Tire Factory A, and life times (unit: 104 km)

of this random sample are recorded as follows:

4.6, 5.0, 5.5, 4.2, 4.3, 4.7, 5.2, 4.1, 4.8, 5.3.

At the same time, 12 tires are randomly selected from Tire Factory B, and life times of this

random sample are recorded as follows:

4.5, 5.2, 5.3, 5.8, 5.3, 4.2, 4.2, 4.8, 5.5, 5.6, 5.6, 5.0.

Suppose that tire life times in the two factories follow some normal distributions with equal

variance. Answer the following questions at the significance level α = 0.1.

(a) Is it suitable for Factory A to claim that the average life time of tires it produces is not less

than 5 × 104 km? State the reason.

(b) Find a 90% confidence interval estimate for the variance of tire life times in Factory A,
2.
i.e., σA

(c) Find a 90% confidence interval estimate for the ratio of variance of tire life times in Factory
2 /σ 2 .
A and B, i.e., σA B

(d) Does Factory B produce higher quality tires than Factory A? State the reason.

Q5. Let X1 , X2 , · · · , Xn be an independent random sample from a Laplace(θ) distribution,

which has the density given by


 
1 |x|
f (x; θ) = exp − for − ∞ < x < ∞.
2θ θ

Here, θ > 0 is a parameter. Note that if X ∼ Laplace(θ), EX = 0, E|X| = θ and E(X 2 ) = 2θ2 .

(a) Find the MLE of θ on Ω1 = {θ : θ > 0}.

(b) Calculate the CRLB with respect to θ.


3
(c) Is the MLE in (ii) the UMVUE of θ?

(d) Find the rejection region of the most powerful test for hypotheses:

H0 : θ = 1 versus H1 : θ = 2.

Q6. Suppose that X1 , X2 , · · · , Xn is an independent random sample from a distribution with

the following density:



 e−(x−θ) , x ≥ θ,


f (x; θ) =

 0, otherwise.

Here, −∞ < θ < ∞ is a parameter.

(a) Find a (non-trivial) sufficient statistic for θ.

(b) Based on the sufficient statistic in (i), find an unbiased estimator of θ (denoted by T1 ).

(c) Is T1 a consistent estimator of θ?

(d) Based on the sample mean X, find another unbiased estimator of θ (denoted by T2 ).

(e) Is T2 a consistent estimator of θ?

(f) Compare the efficiency of T1 and T2 .

Q7. Let X1 , X2 , · · · , Xn be an independent random sample from N (µ, 1). Suppose that a test

for the hypotheses:

H0 : µ = 0 versus H1 : 1 ≤ µ ≤ 2
( n )
X
has the rejection region Xi ≥ c for some constant c.
i=1
(a) Determine the value of c such that this test has size 0.05.

(b) Based on the value of c in (i), find the maximum and minimum power of this test under

H1 .

You might also like