Modelling volatility of growth rate in atmospheric carbon dioxide concentrations in a Bayesian approach

Atmospheric gases, such as carbon dioxide, ozone, methane, nitrous oxide, and etc., create a natural greenhouse effect and cause climate change. Therefore, modelling behavior of these gases could help policy makers to control greenhouse effects. In a Bayesian framework, we analyse and model conditional variance of growth rate in atmospheric carbon dioxide concentrations (ACDC) using monthly data from a subset of the well known Mauna Loa atmosphere carbon dioxide record. The conditional variance of ACDC monthly growth rate is modelled using the autoregressive conditional heteroscedasticity (ARCH), generalized ARCH model (GARCH) and a few variants of stochastic volatility (SV) models. Smooth transition ARCH and GARCH models are shown to be able to capture the dynamics in the conditional variance in ACDC level growth rate and to improve the forecast performance of ACDC growth rate.