Let $X$ be a single observation from the density $f(x) = (2θx + 1 − θ)I[0,1](x)$ with $−1≤ θ ≤ 1$. Find the most powerful test of size $α$ and its power
- Find a most powerful test of size $α$ of $H_0 : θ = 0$ versus $H_1 : θ = 1$.
- Find a uniformly most powerful test of size $α$ of $H_0 : θ = 0$ versus $H_1 : θ > 0$
- To test $H_0: θ ≤ 0$ versus $H_1: θ > 0$, the following procedure was used: Reject $H_0$ if $X$ exceeds $1/2$. Find the power and size of this test.
Answer
Answers can only be viewed under the following conditions:
- The questioner was satisfied with and accepted the answer, or
- The answer was evaluated as being 100% correct by the judge.
2 Attachments
3.7K
-
Hi, just checking on page 2, the derivative (h'(x)) should the second term be -2θb(2θax+1-2θa) instead of -2θ b(2θax+1-2θb)?
-
Yes, there was a typo in the solution. The final result does not change, though. Let me add a new version.
The answer is accepted.
Join Matchmaticians Affiliate Marketing
Program to earn up to a 50% commission on every question that your affiliated users ask or answer.
- answered
- 1095 views
- $25.00
Related Questions
- Ridge Regression for Panel Data Analysis
- standard deviation question (EASY)
- Probabilities/ states question
- Why is the t-test for two independent samples $\ t^* = \frac{(\bar{x}_1 - \bar{x}_2)}{\sqrt{\frac{S_1^2}{n_1} + \frac{S_2^2}{n_2}}}$?
- How to determine which predictor (in multiple linear regression) has the largest effect on the response? Should I be using any statistical test?
- Statistics Probability
- What is the normal probability distribution function?
- Quantitative reasoning
I feel the bounty is a little to low for this.
I second that.
Bounty has been increased
Is this for only one observation (n=1) or for a general random sample of n observations?
@Rage, this is a good question, yes the original question states let X be a single observation from the density. I will update the question to make this clear.
Without that hypothesis the problem was too difficult!