Dr. Hackney STA Solutions pg 72

# Dr. Hackney STA Solutions pg 72 - 5-6 Solutions Manual for...

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 5-6 Solutions Manual for Statistical Inference Note that the pdf factors, showing that X and Y are independent, and we can read off the pdfs of each: X has the F distribution and Y is 2 . If we integrate out y to recover the p+q proper constant, we get the F pdf fX (x) = p 2 p+q 2 q 2 q p p/2 xp/2-1 1+ q px p+q 2 . b. Since Fp,q = 2 /p p 2 /q , q let U 2 , V 2 and U and V are independent. Then we have p q = = E U/p V /q p 1 qE p V = E U p E q V (by independence) (EU = p). EFp,q Then E 1 V = 0 1 v 1 1 q 2 v 2 -1 e- 2 dv = 2q/2 q-2 2 2(q-2)/2 = q v 1 q 2 2q/2 q-2 2 q-2 2 v 0 q-2 2 -1 e- 2 dv = 1 . q-2 v = Hence, EFp,q = q 2 2q/2 q q-2 , 2(q-2)/2 q-2 2 2q/2 p q p q-2 = if q > 2. To calculate the variance, first calculate U 2 q2 p2 V 2 = q2 E(U 2 )E p2 1 V2 . 2 E(Fp,q ) = E Now E(U 2 ) = Var(U ) + (EU )2 = 2p + p2 and E Therefore, 2 EFp,q = 1 V2 = 0 1 1 1 v (q/2)-1 e-v/2 dv = . 2 (q/2) 2q/2 v (q - 2)(q - 4) 1 q2 (p + 2) q2 p(2 + p) = , 2 p (q - 2)(q - 4) p (q - 2)(q - 4) and, hence Var(Fp,q ) = c. Write X = d. Let Y = U/p V /p q 2 (p + 2) q2 =2 - p(q - 2)(q - 4) (q - 2)2 1 X q q-2 2 q+p-2 p(q - 4) , q > 4. then = = V /q U/p Fq,p , since U 2 , V 2 and U and V are independent. p q qY p(1-Y ) (p/q)X 1+(p/q)X pX q+pX , so X = and p 2 dx dy q = p (1 - y)-2 . Thus, Y has pdf p-2 2 fY (y) = B p 2 q+p 2 p q , 2 2 q 2 -1 p q p qy p(1-y) q p+q 2 1+ p qy q p(1-y) q p(1 - y) 2 = y 2 -1 (1 - y) 2 -1 beta p q , . 2 2 ...
View Full Document

## This note was uploaded on 02/03/2012 for the course STA 1014 taught by Professor Dr.hackney during the Spring '12 term at UNF.

Ask a homework question - tutors are online