Modelling  and Forecasting the Demand for Automobile Petrol in Australia, and its Policy Implications

Zheng Li

Petrol is the most important  transport fuel and accounts for the largest consumption share among various  road transport energies. This thesis presents different econometric modelling  systems to estimate the demand for petrol in the Australian road transport  sector, emphasizing the effects of national income and petrol price. Quarterly time series data for Australia  over the period 1977-2006 are employed to capture the adjustment process  associated with responses through time to changes in those factors. Seasonality  is also addressed due to the use of quarterly data. Eight modelling systems for petrol demand are  used to compare the forecasting performance of different approaches. Then, the  best-forecasting model is selected to predict  automobile petrol demand in Australia  from 2007 through to 2020. 

The prediction of a 14-year  forecasting horizon shows that Australian  automobile petrol consumption will continuously increase under the  "business-as-usual" scenario, and  increased greenhouse gas emission (primarily CO2) will be  produced and emitted into the environment.  Effective policy instruments need to be implemented to contain and then reduce  the emissions from automobiles. TRESIS, an integrated transport, land  use and environmental strategy impact simulation program, is used to estimate  the impacts on CO2 of several policy instruments. Given the findings  from the evaluation of different policy scenarios, the appropriate strategy  is suggested in order to  contribute to reducing greenhouse  gas emission in Australia.