- Data, Statistics and AI for Well-Being of People and Organisations
- A cura di Luigi Fabbris, Alberto Franci, Pietro Renzi
Robust statistical modelling of the bridge overload risk caused by extreme traffic load hazard
- Mattia Cefis
- Maurizio Carpita
- © 2026 Author(s) |
- CC BY 4.0
- DOI: 10.36253/979-12-215-1062-1.26
In this research we adopt an advanced statistical approach for modeling bridge overload risk caused by extreme traffic. Starting from studies in transportation engineering, which identify the Frequency (F) and Severity (S) of bridge failure events as key components for risk assessment, we employ a Limited Dependent Variable Bivariate Probit Model to analyze these two potentially correlated dependent variables: a first “selection” equation for F and a second “outcome” equation for S conditional to F greater than a fixed threshold. With this statistical approach we take into account the potential correlation between the error terms of these two equations of the full bivariate model. A Stratified Bootstrap Procedure is used to test the model's stability and robustness. Preliminary results highlight a significant correlation between the residuals of the two equations within the Bivariate Probit framework. This study is developed as part of the Project Spoke N. 7 ”CCAM, Connected networks and Smart Infrastructures” of the ”Sustainable Mobility Center (MOST)”, 2022-2026, CUP D83C22000690001, funded by the European Union (EU) and the Italian Ministry for Universities and Research (MUR), National Recovery and Resilience Plan (NRRP).
- Keywords:
- Overload risk,
- Limited dependent variables,
- Bivariate Probit Model,
- Traffic overload,
- Risk assessment,
University of Brescia, Italy - ORCID: 0000-0003-1316-4605
University of Brescia, Italy - ORCID: 0000-0001-7998-5102
- Aldrich, J.H., Nelson, F.D. (1984). Linear Probability, Logit, and Probit models. Number 45. Sage. DOI: 10.4135/9781412984744
- Amemiya, T. (1981). Quantitative response models: a survey. Journal of Economic Literature, 19(4), pp. 1483-1536. DOI: 10.4337/9781035362707.00034
- Bishop, C.M., Nasrabadi, N.M. (2006). Pattern Recognition and Machine Learning, Volume 4. Springer. DOI: 10.1007/978-0-387-45528-0
- Chawla, N.V., Bowyer, KV., O’Hall, L., Kegelmeyer, W.P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, pp. 321-357. DOI: 10.1613/jair.953
- Chicco, D., Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21(1), pp. 1-13. DOI: 10.1186/s12864-019-6413-7
- Giudici, P. (2024). Safe machine learning. Statistics, 58(3), pp. 473-477. DOI: 10.1080/02331888.2024.2361481
- Menardi, G., Torelli, N. (2014). Training and assessing classification rules with imbalanced data. Data Mining and Knowledge Discovery, 28(1), pp. 92-122. DOI: 10.1007/s10618-012-0295-5
- Nasir, M., Dag, A., Simsek, S., Ivanov, A., Oztekin, A. (2022). Improving imbalanced machine learning with neighborhood-informed synthetic sample placement. Journal of Management Information Systems, 39(4), pp. 1116-1145. DOI: 10.1080/07421222.2022.2127453
- Ventura, R., Barabino, B., Maternini, G. (2024). Prediction of the severity of exceeding design traffic loads on highway bridges. Heliyon, 10(1), pp. 1-17. DOI: 10.1016/j.heliyon.2023.e23374
Informazioni sul capitolo
Titolo del capitolo
Robust statistical modelling of the bridge overload risk caused by extreme traffic load hazard
Autori
Mattia Cefis, Maurizio Carpita
Lingua
Inglese
DOI
10.36253/979-12-215-1062-1.26
Opera sottoposta a peer review
Anno di pubblicazione
2026
Copyright
© 2026 Author(s)
Licenza d'uso
Licenza dei metadati
Informazioni bibliografiche
Titolo del libro
Data, Statistics and AI for Well-Being of People and Organisations
Curatori
Luigi Fabbris, Alberto Franci, Pietro Renzi
Opera sottoposta a peer review
Numero di pagine
420
Anno di pubblicazione
2026
Copyright
© 2026 Author(s)
Licenza d'uso
Licenza dei metadati
Editore
Firenze University Press
DOI
10.36253/979-12-215-1062-1
ISBN Print
979-12-215-1061-4
eISBN (pdf)
979-12-215-1062-1
eISBN (xml)
979-12-215-1063-8
Collana
Applied Statistics Series