I am trying to fit an ARIMA model on the time series of exchange rate. I have tried several kinds of ARIMA specifications (MA(1), MA(1,2), ...) and I am evaluating the particular setting according to the PACF and ACF functions, the Q-test for residuals, and finally I wanted to take a look at the information criteria AIC and BIC. However, if I run the Stata postestimation command
estat ic I always get the same result with undefined (.) value of the log-likelihood for the null model, which seems a bit suspicious.
So am I doing something wrong?