Results 1 to 3 of 3

Math Help - Chi-Square Test With Good Mean & Variance Estimate

  1. #1
    Newbie
    Joined
    Feb 2009
    Posts
    2

    Chi-Square Test With Good Mean & Variance Estimate

    Hello,

    I have come across some computer code that is attempting (what looks like) a Pearson's Chi-Square Test for normality.

    The program has good knowledge of the mean and variance of the quantity being tested (it maintains it over time through some fancy converging filter), however, rather than performing the statistic using expectations, it simply substitutes the estimates and computes the value for each incoming measurement.

    That is, measurements are processed one by one, and if it doesn't match the good mean and variance estimate, then it chucks it away.

    The statistic is programmed as:

    Chi^2 = (Measurement - EstimatedMean)^2/EstimatedVariance

    And the significance test is performed using one degree of freedom.

    My question is, how is this derived from the basic Pearson's Chi-Square formula where expectations are defined? And is this a good test for normality?

    Thankyou.
    Last edited by Trido; February 2nd 2009 at 12:46 AM.
    Follow Math Help Forum on Facebook and Google+

  2. #2
    Member
    Joined
    May 2006
    Posts
    244
    Quote Originally Posted by Trido View Post
    Hello,

    I have come across some computer code that is attempting (what looks like) a Pearson's Chi-Square Test for normality.

    The program has good knowledge of the mean and variance of the quantity being tested (it maintains it over time through some fancy converging filter), however, rather than performing the statistic using expectations, it simply substitutes the estimates and computes the value for each incoming measurement.

    That is, measurements are processed one by one, and if it doesn't match the good mean and variance estimate, then it chucks it away.

    The statistic is programmed as:

    Chi^2 = (Measurement - EstimatedMean)^2/EstimatedVariance

    And the significance test is performed using one degree of freedom.

    My question is, how is this derived from the basic Pearson's Chi-Square formula where expectations are defined? And is this a good test for normality?

    Thankyou.
    X^2 = (Measurement - Mean)^2/Variance

    is the square of a standard normal RV and so has a \chi^2 distribution with 1 degree of freedom. So if the estimates are good:

    Y^2 = (Measurement - EstimatedMean)^2/EstimatedVariance

    is approximately distributed with a \chi^2 distribution with 1 degree of freedom.

    This is not derived from Pearson's Chi-Square as it is a more primitive result, which underlies Pearson's Chi-Square.

    (the sum of the squares of n independent standard normal RV's has a \chi^2 distribution with n degrees of freedom)

    .
    Follow Math Help Forum on Facebook and Google+

  3. #3
    Newbie
    Joined
    Feb 2009
    Posts
    2
    Thankyou Constatine11.
    Follow Math Help Forum on Facebook and Google+

Similar Math Help Forum Discussions

  1. Estimate for population variance lognormal
    Posted in the Advanced Statistics Forum
    Replies: 4
    Last Post: January 11th 2011, 10:54 AM
  2. To obtain an estimate for the variance of the population mean
    Posted in the Advanced Statistics Forum
    Replies: 3
    Last Post: April 20th 2010, 06:13 AM
  3. MSE of Normal Variance Estimate
    Posted in the Advanced Statistics Forum
    Replies: 2
    Last Post: January 28th 2009, 10:17 PM
  4. Replies: 1
    Last Post: December 13th 2008, 01:19 PM
  5. Variance...why square?
    Posted in the Advanced Statistics Forum
    Replies: 5
    Last Post: January 29th 2006, 06:20 PM

Search Tags


/mathhelpforum @mathhelpforum