The Combination Forecasting Of Bayesian Model Averaging Base On The Maximum Likelihood And Using It In Coal Demand Forecasting

Coal is China's most important energy , it play crucial roles in the national economic life. Overproduction of coal will affect national stability and development; coal surplus will affect the healthy development of the coal sector itself.Meeting the requirements for coal production and development of market economy is our ultimate pursuit. Therefore, Scientific and effective coal demand forecast is conducive to speed up the scientific development of China's coal industry, it also help to adjust our energy structure. It has significant meaning to our social economic of sustainable development. Coal demand forecast is from the existing coal, economic, social, starting the big systems integration, analysis of historical data used to explore the demand for coal and its influencing factors to predict future demand for coal.Coal demand forecasts can be roughly divided into two categories: using the single model, using a combination of the models. Demand for coal and the complexity of the nonlinear systems, a single model can't forecast very well, so it is necessary to use a combination of forecasting methods. The combination forecasting combines various individual methods to take full advantage of useful information. So that it can improve the prediction accuracy. The key to the combination forecasting is to determine the weight of each individual forecasting model and it can be divided into fixed weight combination forecasting and changeable weight combination forecasting, judging from its time-defined changeability. We have do a lot research on the fixed weight combination forecasting, and we have already has many mature methods on it. However, the fixed weight combination forecasting is difficult to reflect the changeable behavior of individual models. On the contrary, the changeable weight combination forecasting can do it so as to improve the model prediction accuracy and enhance the practicality of the forecasting model. But it is hard to find a way to determine its weight because its weight is a function of the time.The Bayesian method can clearly show the information update process, it can also combine the subjective information and data with various kinds of interventions. Therefore, the Bayesian combination forecasting methods has great significance in adaptability to update the combining weights. Bayesian Model Averaging Combination Prediction uses posterior probability as the weight to calculate the weighted average for all the possible single prediction models. Having considered all the possible single prediction models and set posterior probability as the standard to estimate the models. It has overcome the shortcomings of the existent methods of calculating combination weight and tackled the problem of models'uncertainty.The key point to carry on combination forecast with BMA is the posterior probability. We have extended the standard approach to Bayesian forecast combination by forming the weights for the forecast combinations form the maximum likelihood rather than the standard marginal likelihood. The new approach overcome the marginal likelihood is over-reliance on the prior information and have sample properties by split the sample to two parts. Finally, we use the new approach to predict the coal demand forecast. The result show that the model that performance well would get more weight, the weight and the model selection is asymptotic. The new methods show the best performance.