Date

2022-1

Author

Ekici, Üsame

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

415
views

367
downloads

Cite This

With the rapid development of railways in Turkey, the research of railway passenger demand forecasting has gained much importance in the recent years. Passenger demand forecasting for transport services is essential for better management and better resource planning. In this study, a time-series-model was established using Auto Regressive Integrated Moving Average (ARIMA) forecasting method and then a regression model was formed to forecast the intercity railway passenger flow in Turkey. The daily passenger flow data from 2011 to 2015 was used to establish a model and 2016 daily passenger flow was predicted by the established model. To test the estimation power of the model, forecasting horizon was extended up to 2019. Analyzing forecasts from 2016 to 2019, reliability of the model was evaluated. Additionally, a series of analyses was performed to understand the nature of Rail Passenger Survey (RPS) data, conducted at the train stations as a part of National Transport Master Plan (NTMP). The descriptive statistics based analyses included socio-demographic characteristics, geographical distribution, trip purposes, trip frequency, access/egress modes and rail passenger behavior difference between the High Speed Rail (HSR) and conventional services. A further attempt of modeling using binary logistic regression enabled the detection of the passenger profile of a business trip traveler.

Subject Keywords

Intercity rail travel,, Passenger demand forecasting, Travel behavior of rail passenger, Time series analysis of rail passenger flow

URI

https://hdl.handle.net/11511/95246

Collections

Graduate School of Natural and Applied Sciences, Thesis