Reverted Mean and Asymptotic Stationary Distribution for Timber Price Using a Mean-Reverting Stochastic Model

Abstract

We use a mean-reverting stochastic model to demonstrate a procedure for calculating the reverted mean and asymptotic stationary distribution of sawlog price data. The data used for this study comes from a local auction market in the Fukuoka Prefecture, Japan where 4m long sugi (Cryptomeria japonica) and hinoki (Chamercypress obtusa) are commonly traded. Parameter estimation is completed using a quasi-maximum likelihood method based on a local linearization scheme. The stationary distribution for our stochastic model is numerically constructed using a generalized Pearson system.