Modeling and Forecasting CPC Prices

Abstract

This paper deals with modeling and forecasting coke petroleum calcination (CPC) prices. We first consider some empirical techniques (polynomial regression, Holt and Winters smoothing) and compare them with the more general Box and Jenkins method. We also use nonparametric predictors. The case study is accessible to readers with an intermediate level of statistics. Prior exposure to Box-Jenkins techniques is useful but not strict-ly necessary.