An Examination of the Slutsky Effect in Interpreting Arima Models

SYNOPTIC ABSTRACT

This paper examines the effect of differencing and smoothing operations on time series. It is demonstrated that in some cases these operations induce parameters which are unrelated to the structure of the process generating the data. Detrending and frequency analysis are suggested as useful steps in developing and interpreting time series models. Two cases are discussed.

Key Words and Phrases:

• Detrending
• Induced Parameters