Incorporating Information Complexity into Regression-Based Freight Generation Model Selection
Freight transportation is vital to the growth of national economy and advancement of the wellbeing of America. The transportation community has been engaging in comprehensive and inclusive transportation planning, design, and implementation.Freight demand modeling is an essential part of the overall transportation development strategy for the future.It enables officials, policy-makers, and transportation analysts to have a comprehensive understanding of current and future transportation needs. Consequently, alternatives that address national transportation demands can be generated, and freight development strategies can be formulated to guide future transportation investments.This paper presents a paradigm shifting freight-demand model formulation.Instead of using the same functional equation form and a similar set of independent variables for all industry sectors, this study generates different models, with different functional forms and various sets of available independent variables, for each industry sector. Data from three Commodity Flow Surveys, which consists of state-level origin-destination movements of goods for two-dozen industry sectors, are utilized to showcase the practice of constructing state-level industry-based freight demand models and selecting the best models using the Bozdogan’s index of information complexity approach.This paper suggests that freight models should be tailored to individual industry sectors, i.e., use different functional equation form with different independent variables for each given industry sector. The resulting freight demand models enable transportation professionals to: Disaggregate the model’s geographic resolution from state (or metropolitan) level to county level, Update annual provisional freight data for the intermediate years between CFS surveys, and Forecast long-term freight movements.
-
-
Supplemental Notes:
- This paper was sponsored by TRB committee AT015 Standing Committee on Freight Transportation Planning and Logistics.
-
Corporate Authors:
500 Fifth Street, NW
Washington, DC United States 20001 -
Authors:
- Lim, Hyeonsup
- Chin, Shih Miao
- Hwang, Ho-Ling
- Han, Lee D
-
Conference:
- Transportation Research Board 96th Annual Meeting
- Location: Washington DC, United States
- Date: 2017-1-8 to 2017-1-12
- Date: 2017
Language
- English
Media Info
- Media Type: Digital/other
- Features: Figures; References; Tables;
- Pagination: 19p
- Monograph Title: TRB 96th Annual Meeting Compendium of Papers
Subject/Index Terms
- TRT Terms: Freight traffic; Origin and destination; Regression analysis; Travel demand; Trip generation
- Uncontrolled Terms: Information complexity
- Subject Areas: Freight Transportation; Planning and Forecasting;
Filing Info
- Accession Number: 01630301
- Record Type: Publication
- Report/Paper Numbers: 17-06162
- Files: PRP, TRIS, TRB, ATRI
- Created Date: Mar 27 2017 9:34AM