True/False Statements, if false make them true:

1.The model Yt = Yt-1 + ut, where ut is a white noise process, is a process whose logarithm is stationary.

My idea: So the model itself is not stationary since its a random walk, but if i take the logarithm that should change right?

2. The model Yt = Yt-1+δ+ ut , where ut is a stationary ARMA(1,1) process with E(ut)=0, models a time series where the growth rates ∇Yt are uncorrelated

No idea if the second one is true.


1 Answer 1

  1. I assume you mean second order stationary. If $Y_t$ is not second order stationary, it is because the mean and/or variance change overtime. If that be the case, I see no way the mean and/or variance of $\log(Y_t)$ could remain the same.

  2. Growth rates as you define them are $\delta + u_t$. Take the particular case $\delta=0$ to make things simpler: that leaves you with $u_t$ which, being ARMA(1,1), is not an uncorrelated process.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.