Estimating Mode of Transport in Daily Mobility during the COVID-19 Pandemic Using a Multinomial Logistic Regression Model

Int J Environ Res Public Health. 2023 Mar 5;20(5):4600. doi: 10.3390/ijerph20054600.

Abstract

At the beginning of 2020 there was a spinning point in the travel behavior of people around the world because of the pandemic and its consequences. This paper analyzes the specific behavior of travelers commuting to work or school during the COVID-19 pandemic based on a sample of 2000 respondents from two countries. We obtained data from an online survey, applying multinomial regression analysis. The results demonstrate the multinomial model with an accuracy of almost 70% that estimates the most used modes of transport (walking, public transport, car) based on independent variables. The respondents preferred the car as the most frequently used means of transport. However, commuters without car prefer public transport to walking. This prediction model could be a tool for planning and creating transport policy, especially in exceptional cases such as the limitation of public transport activities. Therefore, predicting travel behavior is essential for policymaking based on people's travel needs.

Keywords: COVID-19; mobility; multinomial regression model; transport.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Bicycling
  • COVID-19*
  • Humans
  • Logistic Models
  • Pandemics*
  • Transportation

Grants and funding

This publication was created thanks to support under the Operational Program for Integrated Infrastructure for the project “Identification and possibilities of implementation of new technological measures in transport to achieve safe mobility during a pandemic caused by COVID-19” (ITMS code: 313011AUX5), co-financed by the European Regional Development Fund.