Results 1 to 2 of 2

Thread: Statistical estimation (classical) question

  1. #1
    Nov 2009

    Statistical estimation (classical) question

    Each worker's productivity Xi(where i=1,2,3,4....n) is distributed uniformly and independently on the interval (0,L), where L is an unknown upper limit, which we want to estimate
    Notice: L(Tilda) is an estimator of L
    a) The probability function density function in terms of L?
    b) Find E(xi) in terms of L?
    c) Find var(xi) in terms of L?
    d) Estimated L using L(tilda)= 2X(bar), where X(bar) is based on X1, X2,...Xn
    Find the bias of L(tilda)?
    e) Find the MSE of L(tilda)? is L(tilda) a consistent estimator of L?
    f) On inspecting the actual values X1, X2, Xn, we discards the estimator L(tilda), muttering curses on classical estimation theory, and estimates L another way. Can you see why we have might done so? The reason is good, by the way it's not a bayesian; and not all samples of X1, X2, Xn would cause him to react this way

    Have worked through some of the sub-questions, but far from sure about the correctness of the answers!

    Best regards
    Follow Math Help Forum on Facebook and Google+

  2. #2
    MHF Contributor matheagle's Avatar
    Feb 2009
    post what you have
    this point estimator is just the method of moments estimator from a U(0,L) distribution.
    A better estimator is the MLE, which is

    $\displaystyle {n+1\over n} X_{(n)}$

    where that rv is the largest order stat.

    Interstingly using my weird strong laws I'm runing simulations on a new estimator from this very distribution.
    It's a resampling idea I thought of this past summer, that seems to work.
    Follow Math Help Forum on Facebook and Google+

Similar Math Help Forum Discussions

  1. question about Remainder Estimation Theorem
    Posted in the Calculus Forum
    Replies: 0
    Last Post: Feb 5th 2011, 02:25 PM
  2. Statistical Hypothesis Question
    Posted in the Statistics Forum
    Replies: 0
    Last Post: Mar 3rd 2010, 08:15 AM
  3. Statistical Question (I believe...)
    Posted in the Statistics Forum
    Replies: 1
    Last Post: Feb 19th 2010, 01:31 PM
  4. Challenging Estimation Question - Help needed
    Posted in the Advanced Statistics Forum
    Replies: 3
    Last Post: Nov 3rd 2008, 09:00 PM
  5. Statistical Modelling question
    Posted in the Advanced Statistics Forum
    Replies: 0
    Last Post: Jan 19th 2008, 02:15 AM

Search Tags

/mathhelpforum @mathhelpforum