Local Sensitivity Analysis of Forecast Uncertainty in a Random-Utility-Based Multiregional Input-Output Model

Abstract

Transportation systems are critical to regional economies and quality of life. The Random-Utility-Based Multiregional Input-Output Model (RUBMRIO) for trade and travel choices is used here to appreciate the distributed nature of commodity flow patterns across the United States’ 3,109 contiguous counties and 12 industry sectors, for rail and truck operations. This paper demonstrates the model’s sensitivity to various inputs using the method of local sensitivity analysis with interactions (LSAI). This work simulates both individual effects as well as interaction effects of model inputs on outputs by providing sensitivity indices of model outputs to variations of inputs under two scenarios. Model outputs include predictions of domestic and export trade flows, value of goods produced, labor expenditures, and household and industry consumption levels across the counties in the United States. The LSAI technique allows transportation system operators to appreciate the roles of any model input and the associated uncertainty of outputs.

Three Methods for Anticipating and Understanding Uncertainty of Outputs from Transportation and Land Use Models

“…Then, Borgonovo et al ( 21 ) used the G-LUM by Kockelman ( 15 ) to illustrate LSAI techniques and found that the outputs respond almost additively to variations in model inputs over the given scenarios. Wang and Kockelman ( 22 ) applied LSAI to evaluate random–utility-based multiregional input-output models by producing FCSI for the variation of inputs under different scenarios.…”