臺灣博碩士論文加值系統

由於近年台灣地區私人運具的持續成長，造成道路壅塞等交通問題。台中市已計畫興建大眾捷運系統。為鼓勵民眾搭乘大眾捷運，必須具備完善的接駁運輸系統。過去研究接駁運具選擇大多使用多項羅吉特與巢式羅吉特來校估，並得到方案彼此之間是否具有相似性，而無針對旅運者之感受做校估，因此本欲同時校估旅運者彼此之間的異質性與方案彼此之相似性將混合羅吉特模式與一般化巢式羅吉特結合與隨機參數羅吉特結合誤差組合羅吉特來同時校估，並比較各模式之間的校估結果。
本研究依據敘述性偏好資料建立捷運接駁運具選擇模式，找出影響接駁運具選擇之重要變數。使用混合一般化巢式羅吉特模式與隨機誤差組合羅吉特來同時校估方案相似性與旅運者彼此之異質性，並應用於捷運接駁運具選擇之探討。校估結果得知，模式解釋能力優於一般化巢式羅吉特模式，但混合一般化巢式羅吉特模式與隨機誤差組合羅吉特校估結果略有不同，因混合一般化巢式羅吉特會因受到混合機率以亂數求解的關係受到影響，導致旅行成本較為不顯著。但隨機誤差組合羅吉特則無此影響。而最終校估結果以隨機誤差組合羅吉特為最佳模式。
校估結果顯示，旅行成本與旅行時間與部分社會經濟特性為影響接駁運具選擇之重要變數。最後，本研究研擬捷運接駁運具的營運策略。

In recent years, the use of private modes in Taiwan has continuously increasing and led to traffic congestions. Taichung City has been approved to construct the mass rapid transit system. In order to enhance the utilization of the new rapid transit system, it is important to have good transportation systems to access transit stations. The discrete choice analysis is a widely used approach for identifying important variables affecting access mode choice. Recent studies use multinomial logit model and nested logit model to analyze access mode.
This paper applies two advanced choice models with stated preference data to analyze access mode choice. One is the mixed generalized nested logit model which accounts for flexible substitution patterns between alternatives and simultaneously allows for preference heterogeneity by accommodating random coefficients. The second one is the error components logit model combined with random parameters features with the presence of the correlation among alternatives as well as random tasted heterogeneity across decision makers.
The empirical data used for access mode choice analysis was a stated preference survey conducted in Taichiung City, Taiwan. The mixed generalized nested logit model and the error components model with random coefficients produce similar estimation results. The results also indicate that joint effects of flexible substitution patterns between alternatives and random taste heterogeneity, however, will decrease the significance of covariance and heterogeneous parameters. The error components model with random coefficients outperforms the mixed generalized nested logit model as indication of a superior approach to analyze access mode choice. The use of these models can improve our understanding of how Metro travelers select access modes and advance modeling of access mode choice analysis. Effective operational and marketing plans for improvements of access modes are also proposed.

CONTENTS
誌謝 2
摘要 3
ABSTRACT 4
Chapter 1 Introduction 9
1.1Research Background and Motivation 9
1.2 Research Problem and Objectives 11
1.3 Research Methodology 12
1.4 Flow Chart 13
1.5 Thesis Organization 14
Chapter 2 Literature Review 15
2.1 Access mode choice 15
2.2 Discrete Choice Model 18
2.3 Mixed Generalized Extreme Value Model 21
Chapter 3 Methodology 25
3.1 Multinomial Logit Model 25
3.2 Nested Logit Model 26
3.3 Generalized Nested Logit Model 28
3.4 Mixed logit Model 30
3.5 Mixed-GEV Model 32
Chapter 4 Data 35
4.1 Data Source 35
4.2 Statistical analysis of respondents’ characteristics 37
Chapter 5 Empirical Analyses 40
5.1 Model attributes 40
5.2 Results of MNL Models 42
5.3 Results of NL Models 46
5.4 Results of Generalized Nested Logit Models 48
5.5 Results of Random-Parameter Multinomial logit 51
5.6 Results of Random-Parameter Nested logit Models 54
5.7Results of Random-Parameter Generalized Nested Logit Models 57
5.8 Results of Error Component Logit Models 60
5.9 Random-Parameter and Error Component Logit Models 64
5.10 Summary of the estimation results 66
Chapter 6 Conclusions 69
References 72

LIST OF FIGURES
Figure 1. Flow chart 13
Figure 2. Multinomial Logit structure 25
Figure 3. Nested Logit correlation structure 26
Figure 4. Nested Logit correlation structure 27
Figure 5. Nested Logit correlation structure 27
Figure 6. Generalized Nested Logit correlation structure 29


LIST OF TABLES
Table1. Access mode of rapid transit attributes (short distance) 37
Table2. Access mode of rapid transit attributes (long distance) 37
Table3. The characteristic of respondents 39
Table4. The mode choice of respondents 40
Table5. Results of the MNL_1 model 45
Table7. Results of the NL models (1/2) 48
Table8. Results of the NL models (2/2) 49
Table9. Results of the GNL models (1/2) 51
Table10. Results of the GNL models (2/2) 52
Table11. Results of the RPMNL model 54
Table12. Results of the RPNL models (1/2) 57
Table13. Results of the RPNL models (2/2) 58
Table14. Results of the RPGNL model (1/2) 60
Table15. Results of the RPGNL model (2/2) 61
Table16. Results of the ECL models 63
Table17. Results of the ECL models 64
Table18. Results of the RPECL models 66
Table19. Summary of estimation result (1/2) 67
Table20. Summary of estimation result (2/2) 68

1.Alamdari, F.E., Black, I.G., (1992), “Passengers’ Choice of Airline under Competition: the Use of the Logit model,” Transport Reviews, Vol. 12, pp. 153-170.
2.Bajwa, S., Bekhor, S., Kuwahara, M., Chung, E., (2006), “Discrete Choice Modeling of Combined Mode and Departure Time,” Transportmetrica, Vol. 4:2, pp.155-177.
3.Ben-Akiva, M., Lerman, S., (1985), “Discrete Choice Analysis: Theory and Application to Travel Demand,” MIT Press, Cambridge, Massahusetts.
4.Ben-Akiva, M., Bolduc, N., (1991), “Multinomial probit with autoregressive error structure,” Cahier 9123, Department of Economics, University Laval, Quebec.
5.Bhat, C., (1998b), “An analysis of travel mode and departure time choice for urban shopping trips,” Transportation Research B 32, pp. 361–371.
6.Bhat, C., (2000), “Incorporating observed and unobserved heterogeneity in urban work mode choice modeling,” Transportation Science 34, 228-238
7.Bhat, C., (2002), “Recent methodological advances rele relevant to activity and travel behavior. In: Mahmassani, H.S.(Ed.), Perpetual Motion: Travel Behavior Research Opportunities and Application Challenges,” Elsevier Science, Oxford, UK, pp. 381–414.
8.Bhatnagar, A., Ghose, S., (2004a), “A latent class segmentation analysis of e-shoppers,” Journal of Business Research, Vol. 57, pp. 758-767
9.Bhatnagar, A., Ghose, S., (2004b), “Segmenting consumers based on the benefits and risks of Internet shopping,” Journal of Business Research, Vol. 57, pp. 1352-1360
10.Boyd, J., and Mellman, J., (1980), “The effect of fuel economy standards on the u.s. automotive market: a hedonic demand analysis,” Transportation Research A 14, 367–378.
11.Cardell, S., Dunbar, F., (1980), “Measuring the societal impacts of automobile downsizing,” Tranportation Research A 14, 423–434.
12.Carlson, R.G., Wang, J., Falck, R.S., Siegal, H.A., (2005), “Drug use practices among MDMA/ecstasy users in Ohio: a latent class analysis,” Deug and Alcohol Dependence, Vol. 79, pp. 167-179.
13.Cervero, R., (1995), “Rail Access Modes and Catchment Areas for the BART System,” University of California Transportation Center (UCTC), Berkeley, California, 1995.
14.Chu, C., (1981), “Structural Issues and Sources of Bias in Residential Location and Travel Choice Models,” PhD thesis, Northwestern University.
15.Daly, A.J., Zachary, S., (1978), “Improved multiple choice models,” In: Hensher, D.A., Dalvi, M.Q. (Eds.), Determinants of Travel Choice. Saxon House, Westmead.
16.Eran, F., (1994a), “The potential of rail as an environmental solution: Setting the agenda,” Transportation Research Part A: Policy and Practice, Volume 28, Issue 3, May 1994, Pages 209-221
17.Espino, R., Mart?瀋, J.C., Rom?鴨, C., (2008) “Analyzing the Effect of Preference Heterogeneity on Willingness to Pay for Improving Service Quality in an Airline Choice Context,” Transportation Research Part E, Vol. 44, pp. 593-606.
18.Fan, K., Eric, J., Daniel, B., (2000), “Modeling Rail Access Mode and Station Choice,” Transportation Research Record, No. 1413, pp. 49-59.
19.Greene, W.H., Hensher, D.A., (2003), “A latent class model for discrete choice analysis: contrasts with mixed logit,” Transportation Research Part B, Vol. 37, pp. 681-698
20.Hess, S., and Polak, J.W., (2006) “Cross-Nested Logit Modelling of the Combined Choice of Airport, Airline and Access-Mode,” Paper Presented at the 85th Annual Meeting of Transportation Research Board, Washington, D.C..
21.Hess, S., Bierlaire, M., Polak, J., (2004), “Development and Application of a Mixed Cross-Nested Logit model,” European Transport Conference, Strasbourg.
22.Hess, S., Adler, T., Polak, J.W., (2007) “Modelling Airport and Airline Choice Behaviour with the Use of Stated Preference Survey Data,” Transportation Research Part E, Vol. 43, pp. 221-233.
23.Hole, A.R. (2008) “Modelling heterogeneity in patients’ preferences for the attributes of a general practitioner appointment,” Journal of Health Economics, No. 1151.
24.Jong, D.G., Daly, A., Pieters, M., Vellay, C., Bradley, M., Hofman, F., (2003), “A model for time of day and mode choice using error components logit,” Transportation Research Part E, 2003, P.245-268.
25.Keijer, M.J.N., Rietveld, P., (2000), “How Do People Get to the Railway Station? The Dutch Experience,” Transportation Planning and Technology, Vol. 23, pp. 215-235.
26.Koppelman, F. and C. Wen (2000), “The paired combination logit model: Properties, estimation and application,” Transportation Research B 34, 75-89
27.Korf, J., Demetsky, M., (1981), “Analysis of Rapid Transit Access Mode Choice,” Transportation Research Record, No. 817, pp. 29-35.
28.Martijn B., Moshe G., Piet R., (2009), “Access to railway stations and its potential in increasing rail use,” Transportation Research Part A, Vol. 43, pp. 136-149.
29.Mason, K.J., Gray, R., (1995), “Short Haul Business Travel in the European Union: a Segmentation Profile,” Journal of Air Transport Management, Vol. 2, pp. 197-205.
30.McFadden, D., (1973), “Modeling the Choice of Residential Location,” Transportation Research Record, No. 672, pp. 72-77.
31.McFadden, D., (1978), “The General Linear Profit Function”, M. Fuss and D. McFadden eds., Production Economics: A Dual Approach to Theory and Applications,” Vol. 1, Armsterdam: North-Holland, pp. 409-453.
32.McFadden, D., and Train K., (2000), “Mixed MNL models of discrete response,” Journal of Applied Econometrics 15, 447–470.
33.Nuzzolo, A., Crisalli, U., Gangemi, F., (2000), “A Behavioral Choice Model for the Evaluation of Railway Supply and Pricing Policies,” Transportation Research Part A, Vol. 34, pp. 395-404.
34.Pels, E., Nijkamp, P., Rietveld, P., (2003), “Access to and Competition between Airports: A Case Study for the San Francisco Bay Area,” Transportation Research Part A, Vol. 37, No. 1, pp. 71-83.
35.Provencher, B., Bishop, R.C., (2004), “Does accounting for preference heterogeneity improve the forecasting of a random utility model? A case study,” Journal of Environmental Economics and Management, Vol. 48, pp. 793-810.
36.Psaraki, V., and Abacoumkin, C., (2002), “Access Mode Choice for Relocated Airports: The New Athens International Airport,” Journal of Air Transport Management, Vol. 8, No. 2, pp. 89-98.
37.Rajat Rastog and K. V. Krishna Rao (2009), “Segmentation Analysis of Commuters Accessing Transit: Mumbai Study,” Journal of Transportation Engineering, pp. 506-515.
38.Rose, J.M., Hensher, D.A., Greene W.H., (2005), “Recovering Costs through Price and Service Differentiation: Accounting for Exogenous Information on Attribute Processing Strategies in Airline Choice. Journal of Air Transport Management,” Vol. 11, pp. 400-407.
39.Rubite, C., Muromachi, (2007), Y., “Modeling public transport chains in developing cities,” Jounal of the Eastern Asia Society for Transportation Studies, Vol. 7
40.Smith, D., (1956), “Product Differentiation and Market Segmentation as Alternative Marketing Strategies,” Journal of Marketing, Vol. 21, pp. 3-8.
41.Sobieniak, J., (1979), “Choice of Access Mode to Intercity Terminals,” Transportation Research Record, No. 728, pp. 47-53.
42.Sungjin, P., Junhee, K., (2008), “Factors That Influence Walking and Biking to the Station Modeling Commuter Rail Users’ Access mode choice,” TRB 2008
43.Sungyop, K., Gudmundur, F., Ulfarsson, J., Todd H., (2007), “Analysis of light rail rider travel behavior: Impacts of individual, built environment, and crime characteristics on transit access,” Transportation Research Part A, Vol. 41, pp. 511-522.
44.Swait, J., (2001), “Choice set generation within the generalized extreme value family of discrete choice models,” Transportation Research Part B, 35(7), 643-666.
45.Swait, J., Sweeney, J.C., (2000), “Perceived value and its impact on choice behaviour in a retail setting,” Journal of Business and Economics Statistics, Vol. 21, pp.80-87.
46.Train, K.E., (2003), Discrete Choice Methods with Simulation, UK: Cambridge University Press.
47.Tsamboulas, D., Golias, J., Vlahoyannis, M., (1992), “Model development for metro station access mode choice,” Transportation, Vol. 19, No. 3, pp. 231-244.
48.Vovsha, P., (1997), “The cross-nested logit model: Application to mode choice in the tel aviv metropolitan area,” Conference presentation, 76th Transportation Research Board Meetings, Washington, DC.
49.Walker, J.L., (2001), Extended Discrete Choice Models: Integrated Framework, Flexible Error Structures, and Latent Variables. PhD thesis, MIT, Cambridge, MA.
50.Warburg, V., Bhat, C., Adler, T., (2006), “Modeling Demographic and Unobserved Heterogeneity in Air passengers’ Sensitivity to Service Attributes in Itinerary choice,” In Transportation Research Record: Journal of the Transportation Research Board, No. 1951, pp. 13-20.
51.Wen, C.H., Koppelman, F.S., (2001), “The Generalized Nested Logit Model,” Transportation Research B, 35, PP.627-641.
52.Williams, H., (1977), “On the formation of travel demand models and economic evaluation measures of user benefits,” Environment and Planning A, Vol. 9, 285–344.
53.Park, D., Lee, S., Kim, C., Choi, C., Lee, C., (2010), “Access mode choice behaviors of water transportation: a case of Bangkok,” Journal of Advanced Transportation, Vol. 44, pp. 19-33.