Scribd
Upload
47 views1 page

Lecture 12

This document summarizes four problems regarding probability distributions and maximum likelihood estimation: 1) It defines a probability distribution with parameter θ and asks to find the feasible values of θ and the MLE of θ given a sample. 2) It defines a probability density function with parameter θ and asks to find the MLE based on a sample. 3) It describes a soldier estimating the probability p of hitting a target and asks to calculate probabilities, find the MLE of p given sample data, and update the MLE with additional data. 4) It defines two estimators for parameter α based on a normal distribution sample and asks which is unbiased, their variances, and if a lower variance unbiased

Uploaded by

Anonymous T02GVGzB
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
47 views1 page

Lecture 12

This document summarizes four problems regarding probability distributions and maximum likelihood estimation: 1) It defines a probability distribution with parameter θ and asks to find the feasible values of θ and the MLE of θ given a sample. 2) It defines a probability density function with parameter θ and asks to find the MLE based on a sample. 3) It describes a soldier estimating the probability p of hitting a target and asks to calculate probabilities, find the MLE of p given sample data, and update the MLE with additional data. 4) It defines two estimators for parameter α based on a normal distribution sample and asks which is unbiased, their variances, and if a lower variance unbiased

Uploaded by

Anonymous T02GVGzB
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/ 1

Lecture March, 8, 2012.

1. Let X be a random variable with the following probability distribution:


P (x)

2
10

2
10

10

6
10

(a) What are the feasible values of ?


(b) Consider a random sample of independent observations from this
distribution, whose values happen to be:
1, 3, 4, 4, 1, 2, 4, 4, 4, 4, 4, 4, 4
What is the MLE of ?
2. Let X be distributed with density function fX (x; ) = (1 + )x for
0 x 1 and > 1. Obtain the MLE based on a sample of n independent
observations.
3. A battery fires continuously shells on targets, all of them of the same size
and at the same distance. A bored soldier wants to estimate the probability
p that a shell hits its target. The following sequence of questions, that you
must answer in his place, suggests one way of doing it.
(a) What is the probability of hitting the target with the first shot? With
the second (we assume that the first missed the target)? With the
third? With the n-th shot?
(b) If a given target, repeatedly fired upon, is hit with the 13th shot,
what would be the maximum likelihood estimation of p?
(c) After the first target is hit, the soldier witnesses the destruction of
another two, of the same size and at the same distance, requiring
respectively 22 and 14 shots. What would be the new MLE of p
encompassing all information?
4. A random sample made of two independent observations from a N (, 1)
distribution is used to estimate . The following two estimators ares
considered:

2
X1 +
3
2
X1 +
5

1
X2
3
4
X2
5

(a) Which (if any) of those two estimators are unbiased?


(b) What are their respective variances?
(c) Can you obtain an unbiased estimator of whose variance is less
than that of ? If your answer is yes, provide an example; if your
answer is no, explain why not.

You might also like