A NEAREST-NEIGHBOR MODEL FOR FORECASTING MARKET RESPONSE

Researchers in marketing often are interested in modeling time series and causal relationships simultaneous. The prevailing approach to doin g so is a transfer function model that combines a Box-Jenkins model wi th regression analysis. The Box-Jenkins component assumes that a stati onary, stochastic process generates each data point in the time series . We introduce a multivariate methodology that uses a nearest neighbor technique to represent time series behavior that is complex and nonst ationary. This methodology represents a deterministic approach to mode ling a time series as a discrete dynamic system. In this paper we desc ribe how a time series may exhibit chaotic behavior, and present a mul tivariate nearest neighbor method capable of representing such behavio r. We provide an empirical demonstration using store scanner data for a consumer packaged good.