Bootstrap-Tobit model for maritime accident economic loss considering underreporting issues

Abstract

The underreporting of maritime accident data is a major concern in maritime transportation safety analysis. In order to avoid biased effects caused by the underreporting issue, this study aims to propose a Bootstrap-Tobit regression model for the estimation of economic loss resulting from maritime accidents. The questionnaire survey method is employed to determine the possible underreporting rates of maritime accident data and their occurrence probabilities, while the bootstrap sampling method is adopted to supplement the underreported data by generating a number of bootstrap samples. With ten year's archived maritime accident data, a case study is created to calibrate the proposed model. The proposed Bootstrap-Tobit model has captured the impacts of underreporting issues on the marginal effects of the economic loss contributory factors. The proposed model could supplement sufficient underreported data so that the results are more reliable and convincible.

KEYWORDS:

• Maritime accident
• bootstrap sampling
• underreporting data
• reliability

Acknowledgments

The authors sincerely thank three anonymous referees for their helpful comments and valuable suggestions, which considerably improved the exposition of this work. This study is supported by the National Natural Science Foundation of China (grant number 52072237), also sponsored by the National Key Research and Development Project (grant number 2019YFB1600602). The views expressed in this study only reflect the opinion of the author and must not be considered as official opinions from any national or international maritime authorities.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by National Natural Science Foundation of China: [Grant Number 52072237]; National Key Research and Development Project: [Grant Number 2019YFB1600602].