Professional Documents
Culture Documents
Sampling Distributions: F e X I
Sampling Distributions: F e X I
Definition: The gamma distribution Gamma(–, ⁄) with shape parameter – > 0 and scale
parameter ⁄ > 0 has density
⁄– ≠⁄x –≠1
f (x; –, ⁄) = e x I(0,Œ) (x).
(–)
Properties:
• Gamma(1, ⁄) = Exp(⁄)
• X ≥ Gamma(–, ⁄) =∆ cX ≥ Gamma(–, ⁄c )
n
ÿ n
ÿ
• Xi ≥ Gamma(–i , ⁄) independent =∆ Xi ≥ Gamma( –i , ⁄)
i=1 i=1
iid qm 2
Definition: If Zi ≥ N (0, 1), the distribution of Wm := i=1 Zi is called the ‰2 -distribution
with m degrees of freedom. We write
Wm ≥ ‰2m .
1
Theorem: ‰2m = Gamma( m
2 , 2 ).
Consequences:
p
m .005 .01 .025 .05 .10 .20 .25 .30 .40
“Table of the X2 Distribution” adapted in part from “A new table of percentage points of the chi-square
distribution” by H. Leon Harter. From BIOMETRIKA, vol 51(1964), pp. 231–239.
“Table of the X2 Distribution” adapted in part from the BIOMETRIKA TABLES FOR STATISTI-
CIANS, Vol. 1, 3rd ed., Cambridge University Press, © 1966, edited by E.S. Pearson and H.O. Hartley.