Seasonality and the Order of Integration for Consumption.

This paper investigates the univariate orders of integration for the variables in a consumption function, emphasizing the role of seasonality in integration testing. Using seasonally-unadjusted quarterly data, the authors find that nondurable consumer expenditure appears to require two levels of differencing, whereas each of its explanatory variables needs to be differenced only once. Consumption is, however, highly seasonal and conventional one-quarter or annual differencing may not be appropriate in such a case. Generalizing the time series process to allow seasonally-varying parameters, only one level of generalized first differencing is needed for this variable. This is consistent with a seasonally-varying form for the consumption function. Coauthors are A. P. L. Chui, Jeremy P. Smith, and C. R. Birchenhall. Copyright 1988 by Blackwell Publishing Ltd