Analyzing the Difference Between Operating Speed and Target Speed Using Mixed-Effect Ordered Logit Model

Abstract

Desired operating speed (target speed) plays an important role in enhancing traffic operations and providing safe mobility to road users. Understanding the difference between vehicles’ operating speed and target speed on arterial roads is important for achieving safer speed that is consistent with the activity generated in the context classified roadways. This paper proposes a mixed-effect ordered logit model to examine the significant exogenous factors that affect the difference between the two speeds. To the best of the authors’ knowledge, no existing research has adopted the concept of target speed. Three years of probe vehicle-based data (INRIX speed data) and exogenous variables including traffic and roadway characteristics, land use attributes, and sociodemographic information are utilized in the models. The data include information for around 1,600 roadway segments in Central Florida. The results conclude that 16 variables are significantly associated with the difference between target speed and operating speed including speed limit, volume exposure, shoulder width information, sidewalk and shared path proportions, block length, number of signals, pavement conditions, residential and mixed land use, population density, and percentage of poverty. The results also indicate the effect of different time periods on the response variable. Therefore, different posted speed limits are recommended based on the time of day. Further, the study suggests the roadway measures that should be followed to achieve the desired target speed.

Multilevel Ordinal Logit Models: A Proportional Odds Application Using Data from Brazilian Higher Education Institutions

“…As delineated by Mahmoud et al [35] and Palardy [36], estimations for nested data, alternatively known as hierarchical regression models, mixed regression models, nested data models, and random coefficient models, are categorized within the realm of Generalized Linear Latent and Mixed Models (GLLAMM). This approach enables the concurrent examination of both fixed and random effects associated with the observed phenomenon.…”

Modified Geometric Design Consistency Criteria for Two-Lane Rural Highways Based On Crash Severity

“…Liu et al ( 21 ) revealed that slope direction, the absolute value of the elevation difference, the standard deviation of elevation, curve radius, and transition curve ratio help define highway alignment characteristics. Mahmoud et al ( 22 ) found that speed limit, traffic volume, shoulder width, block length, number of signals, pavement conditions, land use type, and population density significantly affect the GDC. Theofilatos and Yannis ( 23 ) found that the traffic volume significantly affects the crash rate.…”