释义 |
Chi-Squared DistributionA distribution is a Gamma Distribution with and , where is thenumber of Degrees of Freedom. If have NormalIndependent distributions with Mean 0 and Variance 1, then
 | (1) |
is distributed as with Degrees of Freedom. If are independentlydistributed according to a distribution with , , ..., Degrees of Freedom, then
 | (2) |
is distributed according to with Degrees of Freedom.
 | (3) |
The cumulative distribution function is then
where is a Regularized Gamma Function. The Confidence Intervals can befound by finding the value of for which equals a given value. The Moment-Generating Function of the distribution is
so
The th Moment about zero for a distribution with Degrees of Freedom is
 | (13) |
and the moments about the Mean are
The th Cumulant is
 | (17) |
The Moment-Generating Function is
As ,
 | (19) |
so for large ,
 | (20) |
is approximately a Gaussian Distribution with Mean and Variance . Fishershowed that
 | (21) |
is an improved estimate for moderate . Wilson and Hilferty showed that
 | (22) |
is a nearly Gaussian Distribution with Mean and Variance .
In a Gaussian Distribution,
 | (23) |
let
 | (24) |
Then
 | (25) |
so
 | (26) |
But
 | (27) |
so
 | (28) |
This is a distribution with , since
 | (29) |
If are independent variates with a Normal Distribution having Means andVariances for , ..., , then
 | (30) |
is a Gamma Distribution variate with ,
 | (31) |
The noncentral chi-squared distribution is given by
 | (32) |
where
 | (33) |
is the Confluent Hypergeometric Limit Function and is the Gamma Function. The Mean,Variance, Skewness, and Kurtosis are
See also Chi Distribution, Snedecor's F-Distribution References
Abramowitz, M. and Stegun, C. A. (Eds.). Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables, 9th printing. New York: Dover, pp. 940-943, 1972.Beyer, W. H. CRC Standard Mathematical Tables, 28th ed. Boca Raton, FL: CRC Press, p. 535, 1987. Press, W. H.; Flannery, B. P.; Teukolsky, S. A.; and Vetterling, W. T. ``Incomplete Gamma Function, Error Function, Chi-Square Probability Function, Cumulative Poisson Function.'' §6.2 in Numerical Recipes in FORTRAN: The Art of Scientific Computing, 2nd ed. Cambridge, England: Cambridge University Press, pp. 209-214, 1992. Spiegel, M. R. Theory and Problems of Probability and Statistics. New York: McGraw-Hill, pp. 115-116, 1992.
|