I'm working with quarterly inflation, usually a AR(4) and I want to obtain different measures of persistence, that are: 1. the sum of the AR coefficients Σα 2. First Order Correlation Coefficient, let's call it ρ

for estimating (1), I used the Dickey-Fuller test with 4 lags and then 1 - d since enter image description here

then I also performed a rolling estimate with a n window to check the stability of the results through time

For (2), I used the following approach: - I regressed the my time series on the variable "time" - then I used "predict r, resid" (on Stata) - finally I calculated the correlation between the time series and the lagged time series

I know a similar issues is already this post How to derive the first order autocorrelation coefficient of an AR(1) process?, but I still have doubts on my procedures because I cannot replicate the results of some reference paper. I'm stuck on these two dumb issues and I'm sure the solution is straightforward but I am not able to see it.

Thank you in advance


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.