Sanjana Hossain
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sanjana Hossain has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Kaili Wang
Department of Civil and Mineral Engineering, University of Toronto, Toronto, Canada
4 shared publications Khandker Nurul Habib
4 shared publications- Khandker Nurul Habib
University of Toronto
4 shared publications - Felita Ong
Department of Civil & Mineral Engineering, University of Toronto, Toronto, Ontario, Canada
3 shared publications - Patrick Loa
Institute of Transportation Studies, University of California, Davis
3 shared publications Alireza Dianat
University of Toronto
1 shared publication
Latest Publications
- 4 July 2024
- Published by Springer Nature in Transportation
- Vol. 53 (2) , 675-711
Who drops off web-based travel surveys? Investigating the impact of respondents dropping out of travel diaries during online travel surveys
- 4 July 2024
- Published by Springer Nature in Transportation
- Vol. 53 (2) , 675-711
Who drops off web-based travel surveys? Investigating the impact of respondents dropping out of travel diaries during online travel surveys
- Open Access
- 9 May 2024
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2678 (11) , 736-749
Fusing Repeated Cross-Sectional Revealed Preference Datasets based on Rational Inattention Theory: Accounting for Changing Modal Preferences
To address the methodological limitation of cross-sectional studies and the data constraints of longitudinal/panel studies, this paper presents a model-based method to fuse repeated cross-sectional travel survey data based on the theory of rational inattention (RI) in discrete choice modeling. In the proposed framework, older cross-sectional data are used to model the prior probability of choice alternatives, and more recent cross-sectional data are used to capture conditional heterogeneous choices. The fusion method is theoretically more robust and computationally less burdensome than existing data pooling techniques. The method is empirically tested using data from two cycles of a large-sample post-secondary student travel survey in the Greater Toronto and Hamilton Area to investigate the commuting mode choices of post-secondary students. Parameter estimates of the RI-based multinomial logit (MNL) model indicate that the proposed method can generate behaviorally consistent results. Validation of the estimated model using a holdout sample indicates its improved forecasting performance compared with the classical random utility maximizing MNL model. The fusion method can be extended to more than two cycles of repeated cross-sectional data by updating the prior probabilities whenever new cross-sectional data become available. Thus, the study presents a continuous framework for fusing information from multiple time points using repeated cross-sectional datasets to capture preference evolution better and enhance the forecasting robustness of discrete choice models.
- 9 May 2024
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2678 (11) , 736-749
Open AccessFusing Repeated Cross-Sectional Revealed Preference Datasets based on Rational Inattention Theory: Accounting for Changing Modal Preferences
To address the methodological limitation of cross-sectional studies and the data constraints of longitudinal/panel studies, this paper presents a model-based method to fuse repeated cross-sectional travel survey data based on the theory of rational inattention (RI) in discrete choice modeling. In the proposed framework, older cross-sectional data are used to model the prior probability of choice alternatives, and more recent cross-sectional data are used to capture conditional heterogeneous choices. The fusion method is theoretically more robust and computationally less burdensome than existing data pooling techniques. The method is empirically tested using data from two cycles of a large-sample post-secondary student travel survey in the Greater Toronto and Hamilton Area to investigate the commuting mode choices of post-secondary students. Parameter estimates of the RI-based multinomial logit (MNL) model indicate that the proposed method can generate behaviorally consistent results. Validation of the estimated model using a holdout sample indicates its improved forecasting performance compared with the classical random utility maximizing MNL model. The fusion method can be extended to more than two cycles of repeated cross-sectional data by updating the prior probabilities whenever new cross-sectional data become available. Thus, the study presents a continuous framework for fusing information from multiple time points using repeated cross-sectional datasets to capture preference evolution better and enhance the forecasting robustness of discrete choice models.
- Open Access
- 14 March 2023
- Published by Springer Nature in Transportation
- Vol. 51 (5) , 1575-1610
Exploring the spatiotemporal factors affecting bicycle-sharing demand during the COVID-19 pandemic
This study investigates the roles of the socio-economic, land use, built environment, and weather factors in shaping up the demand for bicycle-sharing trips during the COVID-19 pandemic in Toronto. It uses “Bike Share Toronto” ridership data of 2019 and 2020 and a two-stage methodology. First, multilevel modelling is used to analyze how the factors affect monthly station-level trip generation during the pandemic compared to pre-pandemic period. Then, a geographically weighted regression analysis is performed to better understand how the relationships vary by communities and regions. The study results indicate that the demand of the service for commuting decreased, and the demand for recreational and maintenance trips increased significantly during the pandemic. In addition, higher-income neighborhoods are found to generate fewer weekday trips, whereas neighbourhoods with more immigrants experienced an increase in bike-share ridership during the pandemic. Moreover, the pandemic trip generation rates are more sensitive to the availability of bicycle facilities within station buffers than pre-pandemic rates. The results also suggest significant spatial heterogeneity in terms of the level of influence of the explanatory factors on the demand for bicycle-sharing during the pandemic. Based on the findings, some neighbourhood-specific policy recommendations are made, which inform decisions regarding the locations and capacity of new stations and the management of existing stations so that equity concerns about the usage of the system are adequately accounted for.
- 14 March 2023
- Published by Springer Nature in Transportation
- Vol. 51 (5) , 1575-1610
Open AccessExploring the spatiotemporal factors affecting bicycle-sharing demand during the COVID-19 pandemic
This study investigates the roles of the socio-economic, land use, built environment, and weather factors in shaping up the demand for bicycle-sharing trips during the COVID-19 pandemic in Toronto. It uses “Bike Share Toronto” ridership data of 2019 and 2020 and a two-stage methodology. First, multilevel modelling is used to analyze how the factors affect monthly station-level trip generation during the pandemic compared to pre-pandemic period. Then, a geographically weighted regression analysis is performed to better understand how the relationships vary by communities and regions. The study results indicate that the demand of the service for commuting decreased, and the demand for recreational and maintenance trips increased significantly during the pandemic. In addition, higher-income neighborhoods are found to generate fewer weekday trips, whereas neighbourhoods with more immigrants experienced an increase in bike-share ridership during the pandemic. Moreover, the pandemic trip generation rates are more sensitive to the availability of bicycle facilities within station buffers than pre-pandemic rates. The results also suggest significant spatial heterogeneity in terms of the level of influence of the explanatory factors on the demand for bicycle-sharing during the pandemic. Based on the findings, some neighbourhood-specific policy recommendations are made, which inform decisions regarding the locations and capacity of new stations and the management of existing stations so that equity concerns about the usage of the system are adequately accounted for.
- 2 November 2022
- Published by Elsevier in Transportation Research Part A: Policy and Practice
- Vol. 166, 164-185
The determinants of commute mode usage frequency of post-secondary students in the Greater Toronto and Hamilton Area
- 2 November 2022
- Published by Elsevier in Transportation Research Part A: Policy and Practice
- Vol. 166, 164-185
The determinants of commute mode usage frequency of post-secondary students in the Greater Toronto and Hamilton Area
- Open Access
- 23 August 2022
- Published by Springer Nature in Research Square
A Comprehensive Data Fusion to Evaluate the Impacts of COVID-19 on Passenger Travel Demands: Application of a Core-Satellite Data Collection Paradigm
The COVID-19 pandemic has altered travel patterns in cities across the world. Previous studies have found that travel choices during the pandemic are affected by attitudes and perceptions of risk in addition to transportation system level-of-service attributes. However, traditional travel demand models often rely on household travel survey data, which rarely include information on attitudinal factors. Conversely, specialized surveys are often lengthy, so they offer the ability to collect detailed attitudinal information but suffer from limited sample sizes. This study demonstrates the feasibility of fusing a “core” household travel survey with three specialized “satellite” surveys to evaluate the impacts of COVID-19 on passenger travel demand in the Greater Toronto Area (GTA). The study uses a non-parametric implicit data fusion method to generate multiple synthetic datasets that contain observed travel diaries and socioeconomic attributes of the trip-makers from the core survey, along with imputed attitudinal statements based on the satellite surveys. The results highlight the ability of the method to sufficiently reproduce the distribution of the attitudinal variables and the ability of the imputed variables to support the estimation of an advanced econometric model. The proposed method can reduce the risk of potential biases in the imputed data that can adversely impact subsequent data analysis. This method can be used to capitalize on the benefits of specialized surveys while still being able to utilize data from large-scale household travel surveys.
- 23 August 2022
- Published by Springer Nature in Research Square
Open AccessA Comprehensive Data Fusion to Evaluate the Impacts of COVID-19 on Passenger Travel Demands: Application of a Core-Satellite Data Collection Paradigm
The COVID-19 pandemic has altered travel patterns in cities across the world. Previous studies have found that travel choices during the pandemic are affected by attitudes and perceptions of risk in addition to transportation system level-of-service attributes. However, traditional travel demand models often rely on household travel survey data, which rarely include information on attitudinal factors. Conversely, specialized surveys are often lengthy, so they offer the ability to collect detailed attitudinal information but suffer from limited sample sizes. This study demonstrates the feasibility of fusing a “core” household travel survey with three specialized “satellite” surveys to evaluate the impacts of COVID-19 on passenger travel demand in the Greater Toronto Area (GTA). The study uses a non-parametric implicit data fusion method to generate multiple synthetic datasets that contain observed travel diaries and socioeconomic attributes of the trip-makers from the core survey, along with imputed attitudinal statements based on the satellite surveys. The results highlight the ability of the method to sufficiently reproduce the distribution of the attitudinal variables and the ability of the imputed variables to support the estimation of an advanced econometric model. The proposed method can reduce the risk of potential biases in the imputed data that can adversely impact subsequent data analysis. This method can be used to capitalize on the benefits of specialized surveys while still being able to utilize data from large-scale household travel surveys.
- 2 September 2021
- Published by Springer Nature in Transportation
- Vol. 49 (6) , 1801-1836
A hybrid data fusion methodology for household travel surveys to reduce proxy biases and under-representation of specific sub-group of population
- 2 September 2021
- Published by Springer Nature in Transportation
- Vol. 49 (6) , 1801-1836
A hybrid data fusion methodology for household travel surveys to reduce proxy biases and under-representation of specific sub-group of population
- 1 June 2021
- Published by Elsevier in Transport Policy
- Vol. 110, 71-85
Exploring the impacts of the COVID-19 pandemic on modality profiles for non-mandatory trips in the Greater Toronto Area
- 1 June 2021
- Published by Elsevier in Transport Policy
- Vol. 110, 71-85
Exploring the impacts of the COVID-19 pandemic on modality profiles for non-mandatory trips in the Greater Toronto Area