Multiple linear regression (MLR) is a commonly used statistical technique to predict future values. In this paper, we examine the situation in which a given time series dataset contains numerous observations of important predictor variables that can effectively be classified into groups based on their values. In such situations, cluster analysis is often employed to improve the MLR models predictive accuracy, usually by creating separate regressions for each cluster. We introduce a novel approach in which we use the clusters and cluster centroids as input data for the predictor variables to improve the predictive accuracy of the MLR model. We illustrate and test this approach with a real dataset on fleet maintenance.
Klimberg, R., Ratick, S. and Smith, H. (2017), "A Novel Approach to Forecasting Regression and Cluster Analysis", Advances in Business and Management Forecasting (Advances in Business and Management Forecasting, Vol. 12), Emerald Publishing Limited, pp. 87-101. https://doi.org/10.1108/S1477-407020170000012006Download as .RIS
Emerald Publishing Limited
Copyright © 2018 Emerald Publishing Limited