Long-term travel demand forecasting models considering parameter changes over time
Project/Area Number |
25380564
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Commerce
|
Research Institution | Kobe University |
Principal Investigator |
SANKO Nobuhiro 神戸大学, 経営学研究科, 准教授 (00403220)
|
Project Period (FY) |
2013-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2015: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2014: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2013: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
Keywords | 消費者行動 / 交通行動 / 交通手段選択 / 需要予測 / 移転可能性 / 断面調査 / サンプル数 / モデル更新 / 調査 / データの新しさ / モデルの更新 / 国内総生産 |
Outline of Final Research Achievements |
When cross-sectional data from multiple time points are available for modelling, models estimated with data from multiple time points, where parameters are expressed as functions of constant gross domestic product per capita, produced better forecasting performance than conventional models estimated with data from only the most recent time point. When data are available from two points in time with ten year interval, a use of older data in addition to more recent data contributes little to improve forecasting performance. Models estimated with several hundred observations from the more recent time point produced statistically significantly better forecasts than models estimated with 10000 observations from the older time point. Model updating methods, which utilise data from both the older and more recent time points, never produced statistically significantly better forecasts than models utilising data from only the more recent time point.
|
Report
(4 results)
Research Products
(8 results)