In this paper, we utilize a mean reverting stochastic process to model the dynamic behaviour of natural gas consumption, where a Brownian motion drives the noise. We employ daily data on natural gas consumption from Istanbul, Turkey to estimate our model and evaluate the forecast performance by backtesting of the model at different forecast horizons using relative mean squared errors. We document that time-series observations on natural gas consumption exhibits stationarity, strong seasonality, mean reversion, and serial correlation. Based on our approach, the conditional distribution of natural gas consumption is derived, and it can be used for forecasting and pricing contingent claims on natural gas consumption.
ahmet goncu hasn't uploaded this paper.
Let ahmet know you want this paper to be uploaded.
