在交通管理分析上，起迄旅次矩陣扮演著越來越重要的角色，因此也吸引了很多估計起迄旅次矩陣方面的研究。動態的起迄旅次矩陣估計相當地新。許多動態方法的應用和發展較靜態方法來的廣泛。在這篇論文中，我們提供了方法去估計起迄旅次矩陣。我們使用時間序列中的非高斯狀態空間模型去估計起迄旅次矩陣並考慮了旅次時間。而這些方法主要是建立了在Kalman過濾器與Gibbs取樣器上。這模型也將擴展到非高斯的觀察誤差。

As origin-destination trip matrices becoming more and more important for many dynamic traffic network control and management analysis, approaches to estimate such matrices from traffic counts have attracted much research interest over the past decade. The dynamic origin-destination estimation approaches are relatively new. Their current status of development and applications are far from being as well recognized as those of static models. In this thesis we provide methods for estimating origin-destination demand pattern in the time domain. For doing this we consider the state space model with travel times to estimate parameters. These techniques rely on Gibbs sampler and Kalman filter. The model will also be extended to include non-Gaussian observation errors.

Contents
1 Introdution 3
2 State space, Kalman filter, and Gibbs sampler 6
2.1 State-Space Representations 6
2.2 Kalman Filter 7
2.3 Gibbs sampler 10
3 Model, prior, and assumption 11
3.1 Gaussian state space model 12
3.1.1 Gaussian state space model and prior assumption 12
3.1.2 Sampling scheme 13
3.1.3 Updating pattern 16
3.1.4 Algorithm 17
3.2 Non-Gaussian State Space Model 19
3.2.1 Introduction and non-Gaussian state space model 19
3.2.2 Monte Carlo likelihood 20
3.2.3 Selection of approximating model 22
3.2.4 Updating pattern 23
3.2.5 Algorithm for non-Gaussian model 24
4 Empirical results 26
4.1 Data description 26
4.1.1 Gaussian state space model 26
4.1.2 Non-Gaussian state space model 29
4.2 The results 35
5 Conclusion 36

Ansley, C. F. and Kohn, R. (1985), “Estimation, filtering, and smoothing in state space models with incompletely specified initial conditions,” The Annals of Statistics, vol.13, No.4, pp.1286-1316.
Box, G. E. P., and Tiao, G.. C. (1992), Bayesian Inference in Statistical Analysis, John Wiley and Sons.
Cascetta, E. and S. Nguyen (1988), “A unified framework for estimating or updating origin/destination matrices from traffic counts,” Transpn. Res., 22B, 437-455.
Chang, G. L., and Tao, X. (1999), "An Integrated Model for Estimating Time-Varying Network Origin-Destination Distributions", Transp. Res. —A, 33A, pp. 381-399.
Dickey, J. M. (1967b), “Matric-variate Generalizations of the Multivariate t Distribution and the Inverted Multivariate t Distribution,”Ann. Math. Statist. 38, 511.
Durbin, J., and Koopman, S. J. (1997), “Monte Carlo maximum likelihood estimation for non-Gaussian state space models,” Biometrika, vol.84, No.3, pp.669-684.
-Schnatter, S. (1994), “Applied state space modeling of non-Gaussian time series using integration-based Kalman filter,” Statist. Comp., vol.4, pp.259-269.
Fahrmeir, L. (1992), “Posterior mode estimation by extended Kalman filter for multivariate dynamic generalised linear models,” Journal of the American Statistical Association, vol.87, pp.501-509.
Guttman, I., and , D. (1984), Robust Kalman Filtering and its Applications, Technical Report, Mathematices Research Center, University of Wisconsin-Madison.
Geman, S. and Geman, D. (1984), “Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images,” IEEE, Trans. Pat. Anal. Mach. Intel. 6, 721-741.
Gelfand, A. E., Hills, S. E., Racine-Poon, A., and Simth, A. F. M. (1990), “Illustration of Bayesian inference in normal data models using Gibbs sampling,” Journal of the American Statistical Association, vol.85, pp.972-985.
Kahirsagar, A. M. (1960), “Some Extensions of the Multivariate t-Distribution and Multivariate Generalization of the Distribution of the Regression Coefficients,” Proc. Camb. Phil. Soc. 57, 80.
Kitagawa, G. (1987), “Non-Gaussian state space modeling of nonstationary time series,” Journal of the American Statistical Association, vol.82, pp.1023-1063.
Kalman, R. E. (1960), “A new approach to linear filtering and prediction problems,” Transaction of ASME, Journal of Basic Engineering, vol.82D, pp.34-45.
Nguyen, S. (1984), “Estimating origin-destination matrices from observed flows,” Transportation Planning Methods (M. Florian, Ed.), North Holland, Amsterdam, 363-380.
Okutani, I. (1987), “The Kalman Filtering Approach in Some Transportation and Traffic Problems,” Transportation and Traffic Theory, N. H. Gartner and N. H. M. Wilson (eds), Elsevier, New York, pp. 397-416.
Shephard, N. and Pitt, M. K. (1997), “Likelihood analysis of non-Gaussian measurement time series,” Biometrika, vol.84, No.3, pp.653-667.
Willumsen, K. G. (1984), “Estimating time-dependent trip matrices from traffic counts,” Proceedings of the Ninth International Symposium on Transportation and traffic Theorey, VNU Science press, 397-411.
West, M., Harrison, P. J. and Migon, H. S. (1985), “Dynamic generalized linear models and Bayesian forecasting (with Discussion),” Journal of the American Statistical Association, vol.80, pp.73-97.
West, M., and Harrison, P. J. (1989), Bayesian Forecasting and Dynamic Models, Springer-Verlag, New York.
Wu, J., “A Real-Time Origin-Destination Matrix Updating Algorithm for On-Line Applications,” Transp. Res. -B, 31B, pp. 381-396, 1997.
Yeh, C. W. (2000), “Estimation of O-D Pattern by Gaussian State Space Model with Unknown Transition Matrix,” Institute of Statistics, National Chiao Tung University, Taiwan.