Transportation Research Part B: Methodological, 2016
Discrete choice modeling is widely applied in transportation studies. However, the need to consid... more Discrete choice modeling is widely applied in transportation studies. However, the need to consider correlation between observations creates a challenge. In spatial econometrics, a spatial lag term with a pre-defined weight matrix is often used to capture such a correlation. In most previous studies, the weight matrix is assumed to be exogenous. However, this assumption is invalid in many cases, leading to biased and inconsistent parameter estimates. Although some attempts have been made to address the endogenous weight matrix issue, none has focused on discrete choice modeling. This paper fills an existing gap by developing a Spatial Autoregressive Binary Probit Model with Endogenous Weight Matrix (SARBP-EWM). The SARBP-EWM model explicitly considers the endogeneity by using two equations whose error terms are correlated. Markov Chain Monte Carlo (MCMC) method is used to estimate the model. Model validation with simulated data shows that the model parameters can converge to their true values and the endogenous weight matrix can be reliably recovered. The model is then applied to a simplified firm relocation choice problem, assuming that similar size firms influence one another. The model quantifies the peer effect, and takes into consideration other independent variables including industry type and population density. The estimation results suggest that peer influence among firms indeed affect their relocation choices. The application results offer important insights into business location choice and can inform future policy making. The sample size for applying the model is currently limited to hundreds of observations. This paper contributes to the existing literature on discrete choice modeling and spatial econometrics. It provides a new tool to discover spatial correlations that are hidden in a wide range of transportation issues, such as land development, location choice, and various travel behavior. Those hidden spatial correlations are otherwise difficult to identify and estimation results may be biased. Establishing a new model that explicitly considers endogenous weight matrix and applying the model to a real life transportation issue represent a significant contribution to the body of literature.
Transportation Research Part C: Emerging Technologies, 2015
As a result of the rapid growth of online shopping, more goods and services are delivered directl... more As a result of the rapid growth of online shopping, more goods and services are delivered directly to residential units. The door-to-door deliveries improve residents' accessibility to retail sector, and at the same time create truck delivery trips. However, partially due to the data limitation, most existing freight research focuses on freight trips generated by business establishments. Little is known about freight trips generated by residential units. As a growing number of urban areas are pushing for dense and mixed development, it is necessary to understand the pattern of truck freight trips directly generated by residential units. This paper uses the U.S. National Household Travel Survey (NHTS) data to investigate the freight trips generated by residential units. The 2009 NHTS provides accurate, comprehensive and timely information on trips, land use, household characteristics and social economic factors. It is the first time that the NHTS data is used to estimate freight trips. A binary choice model and a right-censored negative binomial model are used to identify the impacts of person-related, household-related, and regional-specific variables on home delivery frequency. A case study for the New York State Capital District is then presented. The estimated freight trips generated by residential units are also compared to the freight trips generated by business establishments. Results, although still preliminary and subject to uncertainty, indicate that freight trips generated by residential units have comparable magnitude as the freight trips generated by businesses. Such a study will supplement city logistics studies that traditionally focus on business behavior, helping reconstruct a complete picture of the freight activities in urban areas.
The rapid growth of ecommerce brings great changes to the transportation system. However, most ex... more The rapid growth of ecommerce brings great changes to the transportation system. However, most existing studies focus on the impact of ecommerce on freight system. Its impact on personal trips is relatively less studied. It is reasonable to argue that online shopping reduces the need of shopping trips by making goods accessible via door-to-door deliveries. On the other hand, online shopping may also create more shopping trips as online shoppers travel to stores to experience, compare or pick up the goods. Understanding the connections between online shopping and shopping trips is critical for transportation planners to prepare for changes that information technology will continue to bring to this nation in the future. Using the 2009 National Household Travel Survey (NHTS) data and a structural equation model (SEM), this paper disentangles the bidirectional connections between online shopping and shopping trips. Results show that online shopping encourages shopping trips while shopping trips tend to suppress the online shopping propensity. Besides, both online shopping and shopping trips are influenced by exogenous factors such as shoppers' demographic features, regional specific factors and household attributes. A closer examination at the state level further confirms model validity while disclosing spatial variation in their relationship.
The traffic fatalities in the U.S. had remained relatively stable between 40,716 and 43,510 from ... more The traffic fatalities in the U.S. had remained relatively stable between 40,716 and 43,510 from 1994 to 2005. However, according to the Fatality Analysis Reporting System (FARS), the traffic fatalities dropped dramatically from 43,510 in 2005 to 33,808 in 2009. This paper studies fatalities from social-economic perspective and uses an ARIMA model to perform a time-series analysis of fatalities from 1994 to 2009 by controlling unemployment rate, GDP, auto sales and other factors. The results indicate that ARIMA model is appropriate for the analysis and the number of auto sales is significantly related to fatality downturn. Findings from this study will enhance the understanding of traffic safety issues from a macro level and facilitate traffic safety policy design.
The concept of freight consolidation center (FCC) has emerged in recent years. Although several c... more The concept of freight consolidation center (FCC) has emerged in recent years. Although several case studies have indicated that FCCs are beneficial to the operation of urban transportation systems, the implementation of this concept has proven difficult because the construction and operation of a FCC involves the coordination of different, and conflicting, stakeholders. Unlike other traditional approaches, this paper investigates the FCC development issue using experimental economics. First, profit functions are defined for involved stakeholders; based on those profit functions, four players-carriers, operators, government, and residents-bid on rent, financial incentives, and wages to maximize their own profits. Eight scenarios are analyzed and compared to determine potential influential factors and appropriate conditions for FCC decision making. Results show that public-private partnership lowers rent and increases wages, which leads to higher carrier, operator, and resident profits. A central location lowers rent, wages, financial incentives, and all stakeholders' profits. A larger carrier size benefits all stakeholders. In conclusion, the appropriate conditions for FCC development are public-private partnerships in noncentral locations with large carrier sizes.
Transportation Research Part B: Methodological, 2016
Discrete choice modeling is widely applied in transportation studies. However, the need to consid... more Discrete choice modeling is widely applied in transportation studies. However, the need to consider correlation between observations creates a challenge. In spatial econometrics, a spatial lag term with a pre-defined weight matrix is often used to capture such a correlation. In most previous studies, the weight matrix is assumed to be exogenous. However, this assumption is invalid in many cases, leading to biased and inconsistent parameter estimates. Although some attempts have been made to address the endogenous weight matrix issue, none has focused on discrete choice modeling. This paper fills an existing gap by developing a Spatial Autoregressive Binary Probit Model with Endogenous Weight Matrix (SARBP-EWM). The SARBP-EWM model explicitly considers the endogeneity by using two equations whose error terms are correlated. Markov Chain Monte Carlo (MCMC) method is used to estimate the model. Model validation with simulated data shows that the model parameters can converge to their true values and the endogenous weight matrix can be reliably recovered. The model is then applied to a simplified firm relocation choice problem, assuming that similar size firms influence one another. The model quantifies the peer effect, and takes into consideration other independent variables including industry type and population density. The estimation results suggest that peer influence among firms indeed affect their relocation choices. The application results offer important insights into business location choice and can inform future policy making. The sample size for applying the model is currently limited to hundreds of observations. This paper contributes to the existing literature on discrete choice modeling and spatial econometrics. It provides a new tool to discover spatial correlations that are hidden in a wide range of transportation issues, such as land development, location choice, and various travel behavior. Those hidden spatial correlations are otherwise difficult to identify and estimation results may be biased. Establishing a new model that explicitly considers endogenous weight matrix and applying the model to a real life transportation issue represent a significant contribution to the body of literature.
Transportation Research Part C: Emerging Technologies, 2015
As a result of the rapid growth of online shopping, more goods and services are delivered directl... more As a result of the rapid growth of online shopping, more goods and services are delivered directly to residential units. The door-to-door deliveries improve residents' accessibility to retail sector, and at the same time create truck delivery trips. However, partially due to the data limitation, most existing freight research focuses on freight trips generated by business establishments. Little is known about freight trips generated by residential units. As a growing number of urban areas are pushing for dense and mixed development, it is necessary to understand the pattern of truck freight trips directly generated by residential units. This paper uses the U.S. National Household Travel Survey (NHTS) data to investigate the freight trips generated by residential units. The 2009 NHTS provides accurate, comprehensive and timely information on trips, land use, household characteristics and social economic factors. It is the first time that the NHTS data is used to estimate freight trips. A binary choice model and a right-censored negative binomial model are used to identify the impacts of person-related, household-related, and regional-specific variables on home delivery frequency. A case study for the New York State Capital District is then presented. The estimated freight trips generated by residential units are also compared to the freight trips generated by business establishments. Results, although still preliminary and subject to uncertainty, indicate that freight trips generated by residential units have comparable magnitude as the freight trips generated by businesses. Such a study will supplement city logistics studies that traditionally focus on business behavior, helping reconstruct a complete picture of the freight activities in urban areas.
The rapid growth of ecommerce brings great changes to the transportation system. However, most ex... more The rapid growth of ecommerce brings great changes to the transportation system. However, most existing studies focus on the impact of ecommerce on freight system. Its impact on personal trips is relatively less studied. It is reasonable to argue that online shopping reduces the need of shopping trips by making goods accessible via door-to-door deliveries. On the other hand, online shopping may also create more shopping trips as online shoppers travel to stores to experience, compare or pick up the goods. Understanding the connections between online shopping and shopping trips is critical for transportation planners to prepare for changes that information technology will continue to bring to this nation in the future. Using the 2009 National Household Travel Survey (NHTS) data and a structural equation model (SEM), this paper disentangles the bidirectional connections between online shopping and shopping trips. Results show that online shopping encourages shopping trips while shopping trips tend to suppress the online shopping propensity. Besides, both online shopping and shopping trips are influenced by exogenous factors such as shoppers' demographic features, regional specific factors and household attributes. A closer examination at the state level further confirms model validity while disclosing spatial variation in their relationship.
The traffic fatalities in the U.S. had remained relatively stable between 40,716 and 43,510 from ... more The traffic fatalities in the U.S. had remained relatively stable between 40,716 and 43,510 from 1994 to 2005. However, according to the Fatality Analysis Reporting System (FARS), the traffic fatalities dropped dramatically from 43,510 in 2005 to 33,808 in 2009. This paper studies fatalities from social-economic perspective and uses an ARIMA model to perform a time-series analysis of fatalities from 1994 to 2009 by controlling unemployment rate, GDP, auto sales and other factors. The results indicate that ARIMA model is appropriate for the analysis and the number of auto sales is significantly related to fatality downturn. Findings from this study will enhance the understanding of traffic safety issues from a macro level and facilitate traffic safety policy design.
The concept of freight consolidation center (FCC) has emerged in recent years. Although several c... more The concept of freight consolidation center (FCC) has emerged in recent years. Although several case studies have indicated that FCCs are beneficial to the operation of urban transportation systems, the implementation of this concept has proven difficult because the construction and operation of a FCC involves the coordination of different, and conflicting, stakeholders. Unlike other traditional approaches, this paper investigates the FCC development issue using experimental economics. First, profit functions are defined for involved stakeholders; based on those profit functions, four players-carriers, operators, government, and residents-bid on rent, financial incentives, and wages to maximize their own profits. Eight scenarios are analyzed and compared to determine potential influential factors and appropriate conditions for FCC decision making. Results show that public-private partnership lowers rent and increases wages, which leads to higher carrier, operator, and resident profits. A central location lowers rent, wages, financial incentives, and all stakeholders' profits. A larger carrier size benefits all stakeholders. In conclusion, the appropriate conditions for FCC development are public-private partnerships in noncentral locations with large carrier sizes.
Uploads
Papers by Yiwei Zhou