Sunday, April 1, 2012

Unit Root Tests With Missing Observations

Whenever we test the stationarity of our time-series data we use a "complete" historical time-series. That's to say, there can't be any "gaps" in the series,arising perhaps due to data observations that were not recorded, are contaminated, or are such extreme outliers that they are unbelievable and have to be discarded.

If observations are missing, for whatever reason, then we can't apply standard tests such as the Augmented-Dickey-Fuller (ADF) test, or the Kwiatowski, Phillips, Schmidt and Shin (KPSS) test.

Or can we?

A Very Sad Day for Econometrics

It's with great sadness that we learned this morning that Hal White (UCSD) has passed away. An econometrician of enormous stature, he will be greatly missed.

James Hamilton had this to say.

© 2012, David E. Giles