38.9. INDEPENDENCE AND CONDITIONAL PROBABILITY 795

Therefore,M (t) =

∫Rmp

∫Rmp−1

· · ·∫Rm1

f1 (x1) f2 (x2)

· · · fp (xp)exp

(p

∑k=1

tk ·Xk

)dx1 · · ·dxp

=∫Rmp

∫Rmp−1

· · ·∫Rm1

f1 (x1) f2 (x2) · · · fp (xp)p

∏k=1

exp(tk ·xk)

=p

∏k=1

∫Rmk

fk (xk)exp(tk ·xk)dxk =p

∏k=1

M (0, · · ·0,tk,0, · · · ,0)

Conversely, suppose the other condition. Then

M (t) =p

∏k=1

M (0, · · ·0,tk,0, · · · ,0) =

p

∏k=1

∫Rmp

∫Rmp−1

· · ·∫Rm1

f (x)exp(tk ·xk)

by Fubini’s theorem,p

∏k=1

∫Rmk

exp(tk ·xk) · · ·∫Rm j· · ·∫Rm1

f (x)dx1 · · ·dx j · · ·dxk

≡p

∏k=1

∫Rmk

exp(tk ·xk) fk (xk)dxk (38.6)

where fk (xk) is called the marginal distribution and is obtained as

fk (xk)≡∫Rmp· · ·∫̂Rmk· · ·∫Rm1

f (x)dx1 · · · d̂xk · · ·dxmp

where the hat indicates the thing is being omitted. Thus,∫Rmp· · ·∫Rm1

p

∏k=1

fk (xk)dx1 · · ·dxp = 1

and with respect to the density ∏pk=1 fk (xk) , E (t ·X) yields 38.6. But, as noted above, if

two densities deliver the same moment generating function, then they are the same. Hencethe Xk are independent because the density is the product of functions fk of the xk. ■

Proposition 38.9.8 Suppose {Xk}rk=1 are independent and each n(0,1) , normal with 0

mean and variance 1. Then ∑rk=1 X2

k is X 2 (r).

Proof: It follows from Corollary 38.8.8 that X2k is X 2 (1) . Then using independence,

E

(exp

(t

r

∑k=1

X2k

))= E

(r

∏k=1

exp(tX2

k))

=r

∏k=1

E(tX2

k)

=r

∏k=1

1

(1−2t)1/2 =1

(1−2t)r/2

which is the moment generating function of X 2 (r). ■

38.9. INDEPENDENCE AND CONDITIONAL PROBABILITY 795t) -[,,, Don of fi (x1) f2 (@2)p-ipteew (Etexi] dx, ++-dXpk=]Therefore,P7 bo boy fig fi (#1) f2(@2)--- fp (2p) [Texp (te 2)=I om Sic (xk) EXP (ti + Bx) dxK = Thro ---0,t;,0,--+ ,0)Conversely, suppose the other condition. ThenM(t) = [[M(0,---0,,0,--- ,0) =TT [ony foop-a fon, F@exp Cte)by Fubini’s theorem,Pp .11 / exp (tian) |, fF x)dx,-- -dxj---daxxkel Rk RI fam fP=T] hon exp (ty: ax) fi (ax) dar (38.6)k=1where f; (a) is called the marginal distribution and is obtained asfix) = [ of we f (w) day ---day---d&m,R™p Rk R”1where the hat indicates the thing is being omitted. Thus,Doan’ ff TTA xy) dx -+-dx, =1RP Rl p=and with respect to the density []_, fx (ax), E(t: X) yields 38.6. But, as noted above, iftwo densities deliver the same moment generating function, then they are the same. Hencethe X,; are independent because the density is the product of functions f; of the x,.Proposition 38.9.8 Suppose {X;};_, are independent and each n(0,1), normal with 0mean and variance 1. Then Yi_, X7 is 2? (r).Proof: It follows from Corollary 38.8.8 that x? is 2° (1). Then using independence,e(eo(sear)) = # (fe (x) = Te (a2)which is the moment generating function of 2°? (r). i17 11 pe (1-21)