Transit Ridership Models at the Stop Level

Abstract

This report documents the development of a ridership model at the stop level for Transit Level of Service (TLOS), a software package of the Florida Department of Transportation (FDOT) for measuring transit availability and mobility. This report is in two separate parts. This first part discusses issues in formulating a ridership model on several aspects, including literature review, the study area, analytical framework, data needs, and model-formulation issues. For each issue, the discussion focuses on the alternative approaches to dealing with the issue, any resolution, and CUTR's recommendation, if different from the resolution. The second part discusses the data made available by Kittelson and Associates, Inc. under a separate contract with the FDOT, the data used for model estimation, and the selection of a final model. The final model relates average weekday boarding at a TLOS stop with six categories of factors: 1) socio-demographics in a catchment area; 2) TLOS value; 3) the street environment for pedestrians; 4) accessibility to population and employment; 5) interaction with other modes; and 6) competition with other TLOS stops. Despite some data limitations, the model fits the data well and behaves as expected.

Transit ridership forecasting at station level: an approach based on distance-decay weighted regression

“…Some of these models (Parsons Brinckerhoff, 1996;Kuby et al, 2004) fit data from several cities and include city-wide variables, such as heating and cooling degree days or primary metropolitan statistical area populations. Others consider only data of a particular study area (Walters and Cervero, 2003;Chu, 2004) and, logically, do not use city-wide variables.…”

“…Direct models lack the regional perspective of four-step models, but they are directly responsive to land-use characteristics within the station catchment areas (Cervero, 2006). Chu (2004) argues that the traditional four-step process is ineffective for assessing the impacts of changes to the network or service levels on transit patronage. The reasons for this have to do with accuracy and relevancy.…”

“…Direct models based on multiple regression analysis are a complementary approach to estimating ridership as a function of station environment and transit services features Chu, 2004;Cervero, 2006). Such models are a quick-response and less expensive alternative to the four-step travel forecasting models.…”

“…To date, very few studies have used GIS and multiple regression analysis for transit forecasting (some exceptions are Parsons Brinckerhoff, 1996;Walters and Cervero, 2003;Kuby et al, 2004;Chu, 2004). Proposed models use standard distance thresholds for delimiting service areas and do not take into account that the greater the distance to stops and stations within the catchment area, the less public transport tends to be used.…”

The demand for reliable transit service: New evidence using stop level data from the Los Angeles Metro bus system

“…in addition to reliability). Chu (2004) proposed an average weekday stop-level boarding model for the Florida Department of Transportation that consists of six factors -catchment area sociodemographics, transit level of service, pedestrian environment, population and employment accessibility, interaction with other modes, and completion with other stops. The model is practical, and a very good starting point.…”