Time series, normal distribution?

MaxManus
Messages
268
Reaction score
1

Homework Statement



If I have a time series model

x_1 = my + epsilon_1
x_i = my + a(x_{i-1} - my) + epsilon_i

epsilon_i are iid standard normal.

Can I then say that
y = a_1 x_1+a_2 x_2 + ... a_n x_n

is multi normal?



The Attempt at a Solution



All the x-es are normal since they are built up of previous epsilons thich are independent and normal.

But the x-es are not independent so can I then say that a linear combination of them is normal
 
Physics news on Phys.org
absolutely, any linear combinations of joint Gaussian plus whatever constant is still joint Gaussian (in your case, iid Gaussian is a special joint Gaussian)
 
Thanks for the help.
 
There are two things I don't understand about this problem. First, when finding the nth root of a number, there should in theory be n solutions. However, the formula produces n+1 roots. Here is how. The first root is simply ##\left(r\right)^{\left(\frac{1}{n}\right)}##. Then you multiply this first root by n additional expressions given by the formula, as you go through k=0,1,...n-1. So you end up with n+1 roots, which cannot be correct. Let me illustrate what I mean. For this...
Back
Top