Yoriyasu Sugie

Dynamic Analysis and Modeling of Stated Preference for Travel Modes

Dynamic analysis of stated preference for a new light rail transit system established in 1994 in Hiroshima was carried out using panel data collected for work/school trips at three points in time; 1987, 1990 and 1993. It was first empirically demonstrated that the stated preference for the New Transit System is greatly affected by actual travel modes being used (car and bus) and that the temporal changes of stated preference which were caused by changes of actual travel modes do not support the Markovian assumptions which indicate the individuals responses to a change of travel environment over three years (1987–90). The importance of state dependence was also identified by building dynamic SP mode choice models of the multinomial logit type. This was done in two ways: one was to employ the difference of past choice probabilities in the utility function and the other was the number of the best modes in past SP experiments. Even though both models improved greatly model goodness-of-fit, the latter was proved to be superior to the former in model estimation based on 1993 data.

CORRECTING ATTRITION BIAS IN STATED PREFERENCE MODE CHOICE MODELS

ABST RACT This paper aims at examining the extent of attrition biases specifically included in Stated Preference data and also demonstrates the effectiveness of a correcting method which exclude them in model building. SP panel data for the New Light Rail Transit System in Hiroshima, measured at two different points in tine, was used for this purpose. As a result, the effect of attrition bias on mode choice model parameters based on SP data was empirically clarified. Attrition models which determine whether the respondents of the first wave participate in the second survey or not were developed using first wave data. In addition, a mode choice model was constructed based on the stayers (i.e. participants in the first wave who participated in the second wave) at the second wave. The attrition bias of this model was corrected by sequential steps on the assumption that the error in the mode choice model correlates with that of the attrition model. It was found that this type of correcting could effectively cancel out the biased share of each travel mode.

Correcting Attrition Bias in Stated Preference Mode Choice Models

This paper aims at examining the extent of attrition biases specifically included in Stated Preference data and also demonstrates the effectiveness of a correcting method which exclude them in model building. It was made by developing a mode choice model and an attrition model based on the panel data in Hiroshima.

Relationship between Traffic Accident and Sight Distance to Signal at Intersection close to Bridge with Downhill

This study aims at examining the relationship between traffic accidents and the probability that the sight distances to traffic signals are inadequate at signalized intersections with downhill. The signalized intersections with downhill are selected firstly as less effective sites of the road safety measures by a preliminary statistical analysis based on traffic accident data at 92 high-accident sites in Hiroshima. It is turned out that the probability strongly correlates with the traffic accidents.

Dynamic Travel Demand Models Incorporating Unobserved Heterogeneity and First-order Serial Correlation

Very little work using repeated cross-sectional data has been undertaken in transport research. This is especially true for travel data gathered at multiple points in time, especially data that is gathered every 5-10 years such as Urban Area Travel Survey Data and Road Traffic Census Data in Japan. Accordingly, travel demand modeling based on these types of data is not yet fully developed. This paper deals with methods for developing models which include time series factors for predicting travel demand using three time-points travel data gathered in Hiroshima. As a result, it was shown that model parameters based on cross-sectional data were not stable over time by using Covariance Analysis or T-Statistic. The existence of first-order serial correlation in residuals was confirmed by using Generalized Durbin-Watson Statistics, while unobserved heterogeneity was checked by using Breusch-Pagan Statistics. Fixed-effects models using these two factors were developed and it was shown that their predicting accuracy was improved in comparison to traditional cross-sectional models.

Dynamic Analysis of Stated Preference for Travel Modes Using Panel Data

Dynamic analysis of stated preference, for the New Transit System of Light Rail type which was opened in 1994 in Hiroshima, was carried out using the panel data collected for work and school trips at two points in time; 1987 and 90. It was first empirically demonstrated that the stated preference for the NTS is greatly affected by actual travel modes consisting of car and bus, and that the temporal changes of stated preference which were caused by the change of actual travel mode, do not support the Markovian assumptions which indicate the individuals responses to a change of travel environment over the three years. The importance of state dependence was also demonstrated by building dynamic SP mode choice models of Multinomial Logit type.