Re: Stationary processes...an easy way?

backformystuff wrote:

Hello again everyone,

I have a homework dealing with stationary processes. I'm hoping
someone can give me some hints to be at least able to detect what is
and what isn't a stationary process upon inspection of an equation,
given the parameters:

{Zsubt} = sequence of normal random variables with mean 0 and variance
sigma^2;
a,b,c = constants

Xsubt = Zsub1 cos(ct) + Zsub2 sin(ct).

My answer is that this *is* stationary because the cos & sin & (ct)
cancel eachother out? Is that an acceptable way of approaching this?


No. What do you know about linear combinations of jointly normal random variables?

And, is there an easy way of finding out the mean and autocovariance
functions?


Use basic facts (linearity and bilinearity, respectively) of expectation and covariance.


--
Stephen J. Herschkorn sjherschko@xxxxxxxxxxxx
Math Tutor on the Internet and in Central New Jersey and Manhattan

.