What is the method of moment estimator for θ?

  • Thread starter Thread starter mathmathRW
  • Start date Start date
  • Tags Tags
    Method Moment
mathmathRW
Messages
8
Reaction score
0

Homework Statement


Let ##X_1, X_2, ..., X_n## be a random sample from ## f_θ=2x/θ^2## , ##0≤x≤θ##.
Find a maximum likelihood estimator for θ. Find the method of moment estimator for θ.


The Attempt at a Solution


I have already found that the MLE is max{##x_i##}. I just need to find the method of moments estimator. My professor hasn't given any examples on this and everything I have found online seems completely different. I would appreciate some guidance on this one!
 
Physics news on Phys.org
mathmathRW said:

Homework Statement


Let ##X_1, X_2, ..., X_n## be a random sample from ## f_θ=2x/θ^2## , ##0≤x≤θ##.
Find a maximum likelihood estimator for θ. Find the method of moment estimator for θ.


The Attempt at a Solution


I have already found that the MLE is max{##x_i##}. I just need to find the method of moments estimator. My professor hasn't given any examples on this and everything I have found online seems completely different. I would appreciate some guidance on this one!

What is ##EX_i## in terms of ##\theta##? What is ##E \sum_{i=1}^n X_i / n##? So, what function of ##\theta## is estimated by the mean sample value ##\sum_{i=1}^n x_i / n##?
 
Ray Vickson said:
What is ##EX_i## in terms of ##\theta##? What is ##E \sum_{i=1}^n X_i / n##? So, what function of ##\theta## is estimated by the mean sample value ##\sum_{i=1}^n x_i / n##?

I calculated ##E(X)=2θ/3## and ##E(X^2)=θ^2/2##. I am not sure how to find ##\sum_{i=1}^n x_i / n##.
 
Ok, I have been looking online some more. Should I find ##σ^2(X)## ? It looks like maybe ##∑X_i^2/n=σ^2+[E(X)]^2##. Is that the method of moments estimator?

I have found ##σ^2(X)=θ^2/18## and ##∑X_i^2/n=σ^2+[E(X)]^2=θ^2/(2n)##.

Am I on the right track?
 
mathmathRW said:
I calculated ##E(X)=2θ/3## and ##E(X^2)=θ^2/2##. I am not sure how to find ##\sum_{i=1}^n x_i / n##.

You find ##\sum_{i=1}^n x_i / n## by taking a sample of size n, measuring the resulting ##x_i## values and then computing the sum. On the other hand, the RANDOM VARIABLE ##\sum_{i=1}^n X_i /n## is a different animal completely. As a random variable, it has a certain mean and variance, etc. What are these values, expressed in terms of ##n## and ##\theta## ?
 
There are two things I don't understand about this problem. First, when finding the nth root of a number, there should in theory be n solutions. However, the formula produces n+1 roots. Here is how. The first root is simply ##\left(r\right)^{\left(\frac{1}{n}\right)}##. Then you multiply this first root by n additional expressions given by the formula, as you go through k=0,1,...n-1. So you end up with n+1 roots, which cannot be correct. Let me illustrate what I mean. For this...
Back
Top