Forecasting automobile petrol demand in Australia: An evaluation of empirical models
Forecasting automobile petrol demand in Australia: An evaluation of empirical models
复制标题
DOI：
10.1016/j.tra.2009.09.003
复制
发表时间：
2010-01-01
影响因子：
6.4
通讯作者：
Hensher, David A.
中科院分区：
文献类型：
--
作者：
Li, Zheng;Rose, John M.;Hensher, David A.
自1970年代初以来，运输燃料消耗及其决定因素受到了极大的关注。在文献中，不同类型的建模方法已被用来估计汽油需求，每一个方法的优点和缺点。本文的动机是不断需要审查的有效性的经验燃料需求预测模型，侧重于理论和实际考虑，在不同的模型形式的建模过程中。我们考虑线性趋势模型，二次趋势模型，指数趋势模型，单指数平滑模型，Holt的线性模型，Holt-Winters的模型，部分调整模型（PAM），和自回归综合移动平均（ARIMA）模型。更重要的是，这项研究确定了预测和实际观察到的汽油需求之间的差异，以确定预测的准确性。根据确定的最佳预测模型，澳大利亚2007年至2020年的汽车汽油需求是在“一切照旧”的情况下提出的。(C)2009爱思唯尔有限公司保留所有权利。
Transport fuel consumption and its determinants have received a great deal of attention since the early 1970s. In the literature, different types of modelling methods have been used to estimate petrol demand, each having methodological strengths and weaknesses. This paper is motivated by an ongoing need to review the effectiveness of empirical fuel demand forecasting models, with a focus on theoretical as well as practical considerations in the model-building processes of different model forms. We consider a linear trend model, a quadratic trend model, an exponential trend model, a single exponential smoothing model, Holt's linear model, Holt-Winters' model, a partial adjustment model (PAM), and an autoregressive integrated moving average (ARIMA) model. More importantly, the study identifies the difference between forecasts and actual observations of petrol demand in order to identify forecasting accuracy. Given the identified best-forecasting model, Australia's automobile petrol demand from 2007 through to 2020 is presented under the "business-as-usual" scenario. (C) 2009 Elsevier Ltd. All rights reserved.