個體選擇模式被廣泛應用於消費者選擇行為之研究，較先期的研究多將價格視為外生解釋變數，然事實上其可能是內生的。內生性將造成解釋變數與誤差項間有相關存在，而違反模式的基本假設，使內生變數之參數估計值產生偏誤，導致不正確的研究結論，進而嚴重影響行銷決策。造成相關的原因主要是消費者所欲追求的產品屬性，透過市場機制反應在價格上，使得價格提高，而該屬性是研究者不易觀察到的。
本研究之主要目的係將價格內生性納入個體選擇模式構建之考量，以國道客運高雄至台北路線六家客運公司為研究對象，檢驗顯示性價格資料（票價）以及感受資料（票價感受）兩種價格變數是否存在內生性問題，及其對模式的影響程度，並以控制函數法修正內生性所產生之偏誤參數校估結果，以期更正確地解釋國道客運市場旅運者之選擇行為。此外，亦構建同時考慮價格內生性與個體偏好異質性之個體選擇模式，以瞭解旅運者對於國道客運各家公司之偏好情形。歸納本研究之研究結果如下：
價格內生性方面，(1)本研究所使用的「票價」因其他服務品質變數已反應大部分的運具屬性，遺漏運具屬性很少，故內生性很小，可忽略不計。(2)「票價感受」因反應了個體之偏好，故與效用函數誤差項中所包含的個體偏好部份有相關，考慮內生性時所得之係數均較未考慮時高出許多。(3)內生性愈嚴重，係數低估情形愈嚴重。個體異質性方面，(1)旅運者對於國道客運市場北高線各客運公司之評價存在異質性與相似性。(2)價格內生性會影響考慮個體偏好異質性模式之結構。(3)考慮價格內生性所得各種模式之解釋能力均優於未考慮之模式。(4)使用票價感受時，模式加以考慮個體偏好將可減輕內生性問題。

Discrete choice model have been widely applied in consumer choice behavior researches. In earlier researches, they treated price as an exogenous variable while it should be treated as endogenous, because price is correlated with the error term in the utilities. This correlation will violate the basic assumptions of model, resulting in biased coefficient of price, producing misleading results, and seriously affecting the outcome of marketing decisions. The correlation results from that the market mechanism will increase the prices of products to reflect desirable attributes that are observed by consumers but not measured by researchers.
This research aims to account for endogeneity in discrete choice model. In this thesis, we use cross-sectional data from six companies serving the Kaohsiung-Taipei route to examine if “price” or “price perception” suffered from the endogeneity problem and to what extents. By applying control function approach, we correct the biased estimate of price, and be able to interpret travelers’ choice behavior more correctly. Besides, we also construct discrete choice model considering endogeneity and individual heterogeneity simultaneously. The aim is to find out the preferences of travelers toward different companies. The empirical results are as follow:
In the aspect of price endogeneity, we find (1) Since other service variables have reflected most modal attributes, there are few omitted modal attributes. Hence the endogeneity of “price” data we use is not important. (2) Since “price perception” represent individual’s preferences, it is therefore correlated with the unobserved preferences part in error term. The coefficient of “price perception” increases substantially when accounting for endogeneity. (3) The more serious the endogeneity, the more biased the coefficients are. In the aspect of heterogeneity, we find (1) Travelers’ evaluations toward highway passenger transport companies are heterogeneous, and some of them are similar. (2) Endogeneity does affect the structures of models considering heterogeneity. (3) Models which account for endogeneity are better than those that don’t. (4) When using “price perception” data, accounting for heterogeneity may lighten the endogeneity problem.

中文部份
方菀萍，「個體選擇模式選擇集合之研究—以國道客運北高路線為例」，國立成功大學交通管理研究所碩士論文，民國91年。
石齊平，郭照榮，「當代計量經濟學」，三民書局，民國83年。
施鴻志、段良雄、凌瑞賢，「都市交通計畫—理論與實務」，茂昌圖書有限公司，民國73年。
段良雄、陳宥欽，「探討羅機模式的方案相似與方案異質問題」，中華民國運輸學會第17屆論文研討會論文集，頁105-114，民國91年。
許昭琮，「城際間個體選擇模式之研究」，國立成功大學交通管理研究所碩士論文，民國74年。
曾維琦，「國道客運公司市場定位之研究—以北高線為例」，國立成功大學交通管理研究所碩士論文，民國91年。
英文部份
Ben-Akiva, M. and Lerman, S. R. (1985), Discrete Choice Analysis: Thoery and Application to Travel Demand, MIT Press, Cambridge, MA.
Ben-Akiva, M., and Bolduc, D.(1996), “Multinomial Probit with a Logit Kernel and a General Parametric Specification of the Covariance Structure,” Working paper, MIT.
Ben-Akiva, M., and Bolduc, D., and Walker, J.(2002), “Specification, Identification & Estimation of the Logit Kernel (or Continuous Mixed Logit) Model,” Working paper, MIT.
Berry, S. T. (1994), “Estimating discrete-choice model of product differentiation,” RAND Journal of Economics, Vol. 25, No. 2, 242-262.
Berry, S. T., Levinsohn, J., and Pakes, A. (1995), “Automobile prices in market equilibrium,” Econometrica, Vol. 63, 841-890.
Besanko, D., Gupta, S., and Jain, D. (1998), “Logit Demand Estimation Under Competitive Pricing Behavior：An Equilibrium Framework,” Management Science, Vol. 44, No. 11, 1533-1547.
Bhat, C. R. (1998), “Incorporating Observed and Unobserved Heterogeneity in Urban Work Travel Mode Choice Modeling,” Transportation Science, Vol 34, No. 2, 228-238.
Browstone, D., and Train, K. (1996), “Forecasting new product penetration with flexible substitution patterns,” Working paper, Dept. of Economics, University of California, Irvine.
Bunch, D. S. (1991), “Estimability in the Multinomial Probit Model,” Transportation Research Part B, Vol.25B, No. 1, 1-12.
Chintagunta, P. K. (2001), “Endogeneity and Heterogeneity in a Probit Demand Model：Estimation Using Aggregate Data,” Management Science, Vol. 20, No. 4, 442-456.
Christ, C. F. (1966), Econometric Models and Methods. Wiley, New York.
Curtis, F. A. (1981), “Work Trip Travel Demand Modelling in Kingston Township, Ontario, Canada,” Transportation Planning and Technology, Vol. 7, pp.11-19.
Greene, W. H. (2000), Econometric Analysis. Prentice Hall, New Jersey.
Hausman, J. (1978), “Specification Tests in Econometrics,” Econometrica, Vol. 46, 1251-1272.
Heckman, J. (1978), “Dummy Endogenous Variables in a Simultaneous Equation System,” Econometrica, Vol. 46, 931-959.
Nakamura, A., and Nakamura, M. (1998), “Model Specification and Endogeneity,” Journal of Econometrics, Vol. 83, 213-237.
Petrin, A., and Train, K. (2003), “Omitted Product Attributes in Discrete Choice Models,” Working paper, NBER.
Rivers, D., and Vuong, Q. H. (1988), “Limited Information Estimator and Exogeneity Test for Simultaneous Probit Models,” Journal of Econometrics, Vol. 39, 347-366.
Smith, R. and Blundell, R. (1986), “An Exogeneity Test for a Simultaneous Equation Tobit Model with an Application to Labor Supply,” Econometrica, Vol. 54, 679-686.
Train, K. (2003). Discrete Choice Method with Simulation. Cambridge University Press.
Villas-Boas, J. M., and Winer, R. S. (1999), “Endogeneity in Brand Choice Models,” Management Science, Vol. 45, No. 10, 1324-1338.
Villas-Boas, J. M., and Kuksov, D. (2001), “Endogeneity and Individual Consumer Choice,” Working paper, University of California at Berkeley.
Walker, J. L. (2001),” Extended Discrete Choice Models：Integrated Framework，Flexible Error Structures，and Latent Variable,” Ph.D. Dissertation, Department of Civil and Environmental Engineering, MIT, USA.