CONDITIONS WHEN MARKET SHARE MODELS ARE USEFUL FOR FORECASTING - FURTHER EMPIRICAL RESULTS

The increased availability of data ard access to computers has meant t hat econometric methods are readily available to model and forecast ma rket share. However, controversy exists over their usefulness. For exa mple R. Brodie and C.A. de Kluyver's (International Journal of Forecas ting, 1987, 3, 423-437) review of empirical studies revealed that the predictive accuracy of causal market share models was not consistently better than that of a naive model. In contrast, V. Kumar and T.B. Hea th (International Journal of Forecasting, 1990, 6, 163-174) found that causal models consistently outperformed the naive model when using ag gregated weekly scanner data which allowed for more observations. This paper reports the results of a replication and extension study which confirms Kumar and Heath's findings. However, the increased accuracy f rom using the causal model is diminished considerably when the more re alistic situation of forecasting competitive action is included. The p aper concludes by outlining a research agenda aimed at further clarify ing the conditions when market share models are useful for forecasting .