The growth of app-based taxi services has disrupted the urban taxi market. It has seen significant demand shift between the traditional and emerging app-based taxi services. This study explores the influencing factors for determining the ridership distribution of taxi services. Considering the spatial, temporal, and modal heterogeneity, we propose a mixture modeling structure of spatial lag and simultaneous equation model. A case study is designed with 6-month trip records of two traditional taxi services and one app-based taxi service in New York City. The case study provides insights on not only the influencing factors for taxi daily ridership but also the appropriate settings for model estimation. In specific, the hypothesis testing demonstrates a method for determining the spatial weight matrix, estimation strategies for heterogeneous spatial and temporal units, and the minimum sample size required for reliable parameter estimates. Moreover, the study identifies that daily ridership is mainly influenced by number of employees, vehicle ownership, density of developed area, density of transit stations, density of parking space, bike-rack density, day of the week, and gasoline price. The empirical analyses are expected to be useful not only for researchers while developing and estimating models of taxi ridership but also for policy makers while understanding interactions between the traditional and emerging app-based taxi services.

中文翻译：

---

传统和基于应用程序的出租车系统乘客人数的影响因素和异质性

基于应用程序的出租车服务的增长扰乱了城市出租车市场。传统和新兴的基于应用程序的出租车服务之间的需求发生了显着变化。本研究探讨了决定出租车服务客流量分布的影响因素。考虑到空间、时间和模态的异质性，我们提出了空间滞后和联立方程模型的混合建模结构。案例研究设计了纽约市两项传统出租车服务和一项基于应用程序的出租车服务的 6 个月行程记录。该案例研究不仅提供了关于出租车每日乘客量的影响因素的见解，还提供了模型估计的适当设置。具体来说，假设检验展示了一种确定空间权重矩阵的方法，异构空间和时间单位的估计策略，以及可靠参数估计所需的最小样本量。此外，该研究发现，每日乘客量主要受员工人数、车辆拥有量、发达地区密度、中转站密度、停车位密度、自行车架密度、星期几和汽油价格的影响。预计实证分析不仅对研究人员在开发和估计出租车乘客量模型时有用，而且对决策者也有用，同时了解传统和新兴的基于应用程序的出租车服务之间的相互作用。发达地区的密度、中转站的密度、停车位的密度、自行车架的密度、星期几和汽油价格。预计实证分析不仅对研究人员在开发和估计出租车乘客量模型时有用，而且对决策者也有用，同时了解传统和新兴的基于应用程序的出租车服务之间的相互作用。发达地区的密度、中转站的密度、停车位的密度、自行车架的密度、星期几和汽油价格。预计实证分析不仅对研究人员在开发和估计出租车乘客量模型时有用，而且对决策者也有用，同时了解传统和新兴的基于应用程序的出租车服务之间的相互作用。