This action might not be possible to undo. Are you sure you want to continue?

**Spring 2006 – Professor Hartlaub
**

This exam contains two parts, a take home part and an in class part. The point values for each

problem are provided in parentheses. Good luck and have a great break!

Part 1 – Take Home Problems. Please remember the honor code that we discussed in class.

You may not discuss these problems with anyone else and you should report any violations of

the honor code that you observe.

1. Let

1 2

, , ,

n

Y Y Y K

be a random sample from a population with density function

2

3

3

, 0

( | )

0, .

y

y

f y

elsewhere

θ

θ

θ

¹

≤ ≤ ¹

·

'

¹

¹

We have previously showed that { }

( ) 1 2

max , , ,

n n

Y Y Y Y · K

is sufficient for . θ

a. Find the MLE for . θ (5)

b. Find a function of the MLE in part (a) that is a pivotal quantity. (10)

c. Use the pivotal quantity from part (b) to find a

100(1 )% α −

confidence interval for . θ

(10)

2. Suppose that

1 2

, , ,

n

Y Y Y K

constitute a random sample of size

n

from an exponential

distribution with mean . θ Find a

100(1 )% α −

confidence interval for ( )

2

. t θ θ ·

(15)

Part 2 – In Class Problems. Please show your work for all of the problems below.

3. Let

1 2

, , ,

n

Y Y Y K

be independent random variables such that each

i

Y

has a gamma distribution

with parameters

i

α

and

β

. Prove that

1

n

i

i

U Y

·

·

∑

has a gamma distribution and identify the

parameters. (15)

4. Let

1 2

, , ,

n

Y Y Y K

be a independent random variables, each with probability density function

2

3 , 0 1

( )

0, .

y y

f y

elsewhere

¹ ≤ ≤

·

'

¹

Show that

Y

converges in probability to some constant, and find the constant. (15)

5. Let

1 2 10

, , , Y Y Y K

denote a random sample of size ten from a normal distribution with mean 0

and variance

2

σ .

a. Identify the distribution of

10

Y

S ¸ _

÷

¸ ,

. (5)

b. Identify the distribution of

2

2

10Y

S

. (5)

c. Identify the distribution of

2

2

10

S

Y

. (5)

d. Use your answer from part (c) to find the number

c

such that

0.95.

S

P c c

Y

¸ _

− ≤ ≤ ·

÷

¸ ,

(5)

6. Let

1 2

, , ,

n

Y Y Y K

be independent and identically distributed uniform random variables on the

interval ( ) 0, 3θ

.

a. Derive the method of moments estimator for θ . (5)

b. Find the maximum likelihood estimator for θ . (5)

7. Suppose that

1 2

, , ,

n

Y Y Y K

denote a random sample from a population with probability density

function

2

1

, 0, 2

( )

2

0, .

y

e y

f y

elsewhere

β

β

β

¸ _

−

÷

+

¸ ,

¹

> > − ¹

·

' +

¹

¹

a. Find a sufficient statistic for

β

. (5)

b. Suggest a statistic to use as an unbiased estimator of

β

? (5)

c. Is the unbiased estimator you suggested in part (b) an MVUE for

β

? Explain why or

why not. (10)

d. Derive the MSE of your estimator in part (b). (5)

Sign up to vote on this title

UsefulNot usefulExam1 Spring2006

Exam1 Spring2006

- Estimation Theory
- ms2006
- Estimation Theory
- Estimation Theory Presentation
- AS_M2_A4
- Distrib Properties
- MVU
- Statistical Inference
- Estimation of Weibull Shape Parameter by Shrinkage Towards An Interval Under Failure Censored Sampling
- Maximum Likelihood Estimator
- Estimation Theory
- rtp0203
- GMM Ingles
- Unit 1
- Chapter 08
- Seminar
- 8. IMAMSS - Shrinkage - Hadeel Salim Alkutubi
- 07_lent_Topic 2 - Generalized Method of Moments, Part II - The Linear Model_mw217
- KNNL_AppA
- Week4Lect1
- Prasad Stat
- Unbiased Estimates of Weibull Parameters by the Linear Regression
- Mar 62002
- Right Censored Bayes Estimator for Lomax Model
- Aspects of Bayesian Inference
- Math Statistics
- Estimation_statistics
- Critica Variables Instrument Ales
- Back Matter
- ECE6540Fall09Midterm1
- Exam1 Spring2006

Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

We've moved you to where you read on your other device.

Get the full title to continue

Get the full title to continue reading from where you left off, or restart the preview.

scribd