Journal of Economic Dynamics and Control 15 (April 1991) 275-284. Running a battery of unit root/cointegration tests and then imposing the answers on subsequent analysis is a bad idea. Alas, there is no substitute for plotting the data and thinking about what makes sense.
A Critique of The Application of Unit Root Tests
Previous
Previous
“Volatility Tests and Efficient Markets: A Review Essay”
Next
Next