Escolar Documentos
Profissional Documentos
Cultura Documentos
N (x; , 2 ) = p
e 2 (x)
1
(2 2 )
/ 2
= e2t .
To demonstate this result, the exponential terms may be gathered and rearranged to give
(3)
= exp 12 (z t)2 exp 12 t2 .
Then
Mz (t) = e
(4)
1 2
2t
2
1
1
e 2 (zt) dz
2
1 2
= e2t ,
where the final equality follows from the fact that the expression under the
integral is the N (z; = t, 2 = 1) probability density function which integrates
to unity.
Now consider the moment generating function of the Normal N (x; , 2 )
distribution when and 2 have arbitrary values. This is given by
Z
2
2
1
1
xt
(5)
Mx (t) = E(e ) = ext p
e 2 (x) / dx
(2 2 )
Define
(6)
z=
x
,
which implies
1
x = z + .
zt
Mx (t) = e
(7)
12 z 2
e
(2 2 )
Z
1 2
1
t
=e
ezt e 2 z dz
2
1
= et e 2
2 2
dx
dz
dz
Here, to establish the first equality, we have used dx/dz = . The final equality
follows in view of the final equality of equation (2) above where the dummy
variable t can be replace by t. The conclusion is that
(8)
Let x N (x , x2 ) and y N (y , y2 ) be two independently distributed normal variables. Then their sum is also a normally distributed random variable: x + y = z N (x + y , x2 + y2 ).
To prove this we need only invoke the result that, in the case of independence, the moment generating function of the sum is the product of the moment
generating functions of its elements. This enables us to write
(10)