Scribd
Upload
221 views2 pages

Exercises Point Estimation

1. The document lists 10 exercises involving point estimation techniques like the method of moments and maximum likelihood estimation. The exercises involve estimating parameters of distributions like Poisson, exponential, normal from sample data. 2. Several exercises ask to estimate distribution parameters like the mean and variance from sample statistics, and compute probabilities based on the estimates. 3. The goal of the exercises is to practice applying common point estimation methods to estimate characteristics of populations from random samples.

Uploaded by

laura
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
221 views2 pages

Exercises Point Estimation

1. The document lists 10 exercises involving point estimation techniques like the method of moments and maximum likelihood estimation. The exercises involve estimating parameters of distributions like Poisson, exponential, normal from sample data. 2. Several exercises ask to estimate distribution parameters like the mean and variance from sample statistics, and compute probabilities based on the estimates. 3. The goal of the exercises is to practice applying common point estimation methods to estimate characteristics of populations from random samples.

Uploaded by

laura
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/ 2

Statistics II - Management Degree

List of exercises

Point estimation

1. In a box there are θ balls, numbered from 1 to θ . A random sample of 3 balls was drawn with
replacement, having obtained (13, 5, 9). Compute an estimate for θ using the method of moments
and the maximum likelihood method, and compare them.

2. Consider a population with the following density:


f ( x∣θ )=2θ2 x−3 ( x>θ ) , para θ>0 ,
and a random sample of size five: (15, 8, 10, 5, 17).
Knowing that E(X)= 2θ , compute the estimate of θ by the method of moments.

3. Consider a Poisson random variable X describing the number of faults in a piece of fabric from the
production of a certain firm. The Poisson parameter θ=E ( X ) represents the average number of
faults per piece of fabric in the total production of the firm.
However, rather than in θ , we can be interested in another quantity, for instance the proportion of
faultless pieces of fabric from the total production. Find the expression of such proportion as a
function of θ .

4. The time it takes a student to answer an exam question (in minutes) follows an exponential
distribution with parameter λ . A random sample of 40 questions gave a total of 480 minutes.
a) Obtain the maximum likelihood estimate of λ .
b) Compute the maximum likelihood estimate for the proportion of questions that are answered in
less than 15 minutes.
c) Consider an exam with 8 questions. What is the probability of answering all questions, given
that the maximum time allowed for the exam is 2 hours?

5. The repair time (minutes) of a certain type of machine, say X, follows a Normal distribution with
unknown parameters. A random sample of 10 repair times gave:
∑i =1 xi = 846 and ∑i =1 xi2 = 71607
10 10

Estimate the probability of the repair time being less than 83 minutes.

6. Consider a random sample of size three from an exponential distribution, say ( X 1 , X 2 , X 3 ) . In


order to estimate the mean, the following statistics are proposed:
X1 + X 2 X + 2X2
T1 = X 1 , T2 = , T3 = 1 and T4 = X .
2 3
a) Prove that all the above estimators are unbiased estimators of the mean.
b) Compute the relative efficiency of the estimators.
7. Consider a population with probability function given by
f (x∣θ )=θ (1−θ) x ( x=0, 1, 2, 3,…) ,
with 0<θ<1 . It is known that E( X )=(1−θ )/θ . A random sample of size 1000 gave
Σ1000
i =1 xi = 980 .

a) Compute the method of moments estimate of θ .


b) Derive the maximum likelihood estimator of θ .
c) Compute the maximum likelihood estimate for the population mean. Justify.

8. Traffic between 8am and 9am at a certain place was measured counting the number of vehicles that
passed at that time. Suppose the counts follow a Poisson process. A random sample of 9
observations was collected, having observed the following number of vehicles:
(95, 100, 80, 70, 110, 98, 97, 90, 70).
a) Derive the maximum likelihood estimator for the average number of vehicles that pass by that
place between 8am and 9am, and compute the corresponding estimate using the above sample.
b) Show that the estimator you found is consistent and the most efficient.
c) Compute the maximum likelihood estimate for the probability that no vehicles pass during at
least two minutes.

9. Consider a random variable, say X, whose distribution depends on parameters α e θ , having


E( X )=α θ and Var ( X )=α θ2 . From random sample of size 320 that gave Σ320i =1 xi = 22.2 and

Σi =1 xi = 535.8 , compute an estimate of the unknown parameters. Justify.


320 2

10. The maximum height of the waves (meters) at a certain beach is represented by a random variable
with the following density function:
x
f (x∣θ )= exp −
θ { }
x2
2θ
( x > 0) .

a) Obtain the maximum likelihood estimator for θ from the random sample ( X 1 , X 2 , , X n ) .
b) Show that the Fisher information equals 1/θ2 . (Note: X 2 follows an exponential distribution
with mean equal to 2θ ).
c) Show that the above estimator is unbiased, and study its efficiency.
d) Suppose that in the last six years the following maximum heights were observed:
3.1, 2.4, 2.6, 2.2, 1.9, 2.8.
Compute an estimate for P( X >3 ) .

You might also like