探討RP與SP數據整合之方案相似與狀態相依

Investigating the alternative similarity and state dependence in combining RP and SP data

詹仕偉(Shih-Wei Jhan)

指導教授 ： 楊志文

國立臺中科技大學/管理學群/流通管理系碩士班/碩士(2011年)

https://doi.org/10.6826/NUTC.2011.00040

摘要

本研究目的在於探討數據整合模式中方案相似與狀態相依之影響，以提出抑制私人運具與提倡大眾運具之有效策略。在過去運輸文獻中，Nested Logit架構雖能整合多重數據，但其架構未能考慮個體異質、不同運具之數據尺度與負向狀態相依之影響。因此，本研究首先運用Error Components Logit模式進行數據整合，除考量方案相似與尺度變異外，並考慮負向狀態相依的轉移效用，最後並針對系統異質與隨機異質進行探討。實證結果顯示，在都會運具選擇行為中，運用Error Components Logit模式可有效考量Nested Logit 架構不足之處。旅行時間與旅行成本具有顯著的系統異質與隨機異質。在政策模擬的測詴結果中，提高私人運具的停車與通行費用為抑制私人運具的有效策略，而降低大眾運輸的票價與改善轉車次數，亦可顯著提升大眾運具的搭乘率。

關鍵字

數據整合 ； 方案相似 ； 狀態相依 ； NL架構 ； ECL架構

並列摘要

This study aimed to investigate the influences of alternative similarity and state dependence in combining multiple data sets. It also proposed the effective strategies to promote the usage of public transport and restrain the growing of private transport. In previous literatures, the structure of nested logit is famous and convenient method to combine multiple data sets. However, it could treat the problems of individual heterogeneity, scale variation, and negative effect of state dependence completely. Hence, this study proposed using error component logit to combing multiple data sets. This model could consider alternative similarity, scale variation, negative state- dependence, and heterogeneity simultaneously. Empirical results reveal that error components logit could successfully resolve the defect of nested logit structure in data combination. The systematic and random heterogeneity exist significantly on the coefficients of travel time and travel cost. The scenario results indicate that implementing parking and toll costs could reduce the usage of private transport effectively. Meanwhile, promoting pricing and improving transfer performance also can raise the usage of public transport.

並列關鍵字

Data Combination ； Alternative Similarity ； State dependence ； Nested Logit ； Error Components Logit

參考文獻

1. Ben-Akiva, M. and Morikawa, T. (1990). Estimation of switching models from revealed preferences and stated intentions. Transportation Research Part A, 24, 485-495.

2. Bhat, C. R. (1995). A heteroscedastic extreme value model of intercity travel mode choice. Transportation Research Part B, 29, 471-483.

3. Bhat, C. R. and Casterlar, S. (2002). A unified mixed logit framework for modeling revealed and stated preferences: formulation and application to congestion pricing analysis in the San Francisco Bay area. Transportation Research Part B, 36, 593-616.

5. Bradley, M. A. and Daly, A. J. (1997) Estimation of logit choice models using mixed stated preference and revealed preference information. In: Stopher, P. R., Lee-Gosselin, M. (Eds.), Understanding Travel Behaviour in an Era of Change. Pergamon, Oxford.

6. Brownstone, D., Bunch, D. S., Golob, T. and Ren (1996). A transactions choice model for forecasting demand for alternative-fuel vehicles. Research in Transportation Economics, 4, 87-129.