This is a problem from ISI MStat Examination,2018. It involves the construction of the most powerful test of size alpha using Neyman Pearson Lemma. The aim is to find its critical region in terms of quantiles of a standard distribution.
Let be an i.i.d sample from
, with
and
Based on the above sample,obtain the most powerful test for testing against
, at level
, with
.Find the critical region in terms of quantiles of a standard distribution.
2. Useful Transformations of Random Variables
3. Properties of standard probability distributions (e.g. Normal,Chi-squared etc)
All these topics are included in the regular coursework of undergraduate statistics students. If not, one may refer standard texts like Casella Berger.
As, is a random sample, they are independent by definition.
So, their joint pdf when is given by
, where
denotes the indicator function over the interval
.
Similarly, the joint pdf when is given by:
According to the Fundamental Neyman Pearson Lemma}, the most powerful size test for testing
vs
is given by the test function
as follows:
where k is such that .
So, our test criterion is
Plugging in the pdfs, we get the criterion as (say)
Our aim now is to find the value of from the given size
criterion,
Thus,
Now, we state a result: If ,then
distribution (Prove it yourself!)
As 's are independent, due to reproductive property of chi-squared distribution,
Hence , we simply need that value of such that the quantity
The obvious choice is , where
is the upper
point of
distribution.
So, we have implies
So, our critical region for this test is
In this problem , look at the supports of the two distributions under the null and alternative hypotheses.
See that both the supports are the same and hence the quantity is defined everywhere.
But suppose for a problem the two supports are not the same and they are not disjoint then try constructing a most powerful test using the Neyman Pearson Lemma.
For Example:
Let the family of distributions be
Find the most powerful test for testing against
Note that the supports under null and alternative hypotheses are not the same in this case.
Give it a try!
This is a problem from ISI MStat Examination,2018. It involves the construction of the most powerful test of size alpha using Neyman Pearson Lemma. The aim is to find its critical region in terms of quantiles of a standard distribution.
Let be an i.i.d sample from
, with
and
Based on the above sample,obtain the most powerful test for testing against
, at level
, with
.Find the critical region in terms of quantiles of a standard distribution.
2. Useful Transformations of Random Variables
3. Properties of standard probability distributions (e.g. Normal,Chi-squared etc)
All these topics are included in the regular coursework of undergraduate statistics students. If not, one may refer standard texts like Casella Berger.
As, is a random sample, they are independent by definition.
So, their joint pdf when is given by
, where
denotes the indicator function over the interval
.
Similarly, the joint pdf when is given by:
According to the Fundamental Neyman Pearson Lemma}, the most powerful size test for testing
vs
is given by the test function
as follows:
where k is such that .
So, our test criterion is
Plugging in the pdfs, we get the criterion as (say)
Our aim now is to find the value of from the given size
criterion,
Thus,
Now, we state a result: If ,then
distribution (Prove it yourself!)
As 's are independent, due to reproductive property of chi-squared distribution,
Hence , we simply need that value of such that the quantity
The obvious choice is , where
is the upper
point of
distribution.
So, we have implies
So, our critical region for this test is
In this problem , look at the supports of the two distributions under the null and alternative hypotheses.
See that both the supports are the same and hence the quantity is defined everywhere.
But suppose for a problem the two supports are not the same and they are not disjoint then try constructing a most powerful test using the Neyman Pearson Lemma.
For Example:
Let the family of distributions be
Find the most powerful test for testing against
Note that the supports under null and alternative hypotheses are not the same in this case.
Give it a try!