Examining Common Distributional Assumptions of Travel Characteristics for Data Simulation

Abstract

Issues about travel data limitation have been a growing concern for many urban areas. To address this problem, new research areas regarding the transferability of household travel survey data are emerging. It has been shown that local updating can significantly improve the quality of the transferred data. As part of a comprehensive research effort on the transferability of National Household Travel Survey (NHTS) data, this study attempts to fit 13 continuous distributions and 6 discrete distributions to various travel characteristics derived from the NHTS 2001 data sets. The best-fitted distributions are selected according to multiple criteria, including Anderson–Darling, chi-square, and Kolmogorov–Smirnov tests. The results of the analysis suggest that the assumption of normality does not hold for any of the travel characteristics in the sample. Instead, distributions such as gamma, Weibull, and exponential prove to dominate the best-fitted distributions for their respective applications. Despite the complexity of the best-fitted distributions, certain stable distributional patterns are shown to exist. This paper also summarizes the best distributional assumptions for various travel characteristics, followed by a brief introduction to their applications.

Get full access to this article

View all access options for this article.

References

Greaves

S. P.

, and Stopher

P. R.

Creating a Synthetic Household Travel and Activity Survey: Rationale and Feasibility Analysis. In Transportation Research Record: Journal of the Transportation Research Board, No. 1706, TRB, National Research Council, Washington, D.C., 2000, pp. 82–91.

Zhang

, and Mohammadian

Bayesian Updating of Transferred Household Travel Data. In Transportation Research Record: Journal of the Transportation Research Board, No. 2049, Transportation Research Board of the National Academies, Washington, D.C., 2008, pp. 111–118.

Hess

, Polak

J. W.

, and Axhausen

K. W.

Distributional Assumptions in Mixed Logit Models. Presented at 85th Annual Meeting of Transportation Research Board, Washington, D.C., 2006.

Mohammadian

, and Zhang

Investigating the Transferability of National Household Travel Survey Data. In Transportation Research Record: Journal of the Transportation Research Board, No. 1993, Transportation Research Board of the National Academies, Washington, D.C., 2007, pp. 67–79.

Giannopoulos

G. A.

An Analysis of Trip Length and Land Use Patterns in the Greater Athens Area.

Transportation, Vol. 6, No. 4, 1977, pp. 379–392.

Brown

P. J. B.

, and Masser

An Empirical Investigation of the Use of Broadbent's Rule in Spatial System Design. In Spatial Representation and Spatial Interaction ( Masser

, and Brown

P. J. B.

, eds.), Martinus Nijhoff, Leiden, Holland, 1978.

Lau

A Comparative Study of Distance Measures Using the Victorian Activity and Travel Survey (VATS) Data. Presented at 21st Conference of Australian Institutes of Transport Research (CAITR), 1999. mams.rmit.edu.au/y23zvueewjf5z.pdf. Accessed July 20, 2006.

SPSS 12 User's Manual: One-Sample Kolmogorov–Smirnov Test. SPSS Inc., 2003.

Hogg

R. V.

, and Ledolter

Applied Statistics for Engineers and Physical Scientists, 2nd ed. Prentice Hall, Upper Saddle River, N.J., 1992.

10.

Clark

D. R.

, and Thayer

C. A.

A Primer on the Exponential Family of Distributions, 2004. www.casact.org/pubs/dpp/dpp04/04dpp117.pdf. Accessed July 20, 2006.

11.

EDA Assumptions. NIST/SEMATECH e-Handbook of Statistical Methods. National Institute of Standards and Technology. www.itl.nist.gov/div898/handbook/. Accessed July 20, 2006.

12.

Park

H. M.

Testing Normality in SAS, STATA, and SPSS. http://pytheas.ucs.indiana.edu/∼statmath/stat/all/normality/Testing_Normality.pdf 2004. Accessed July 20, 2006.

13.

Crystal Ball Reference Manual in Crystal Ball 7: Distribution Fitting Methods. Decisioneering Inc., Denver, Colo., pp. 39–40.

14.

Guide to Using BestFit-Distribution Fitting for Windows, Version 4.5. Palisade Corporation, Newfield, N.Y., 2004, pp. 23–25.

15.

D'Agostino

, and Stephens

M. A.

Goodness-of-Fit Techniques. Marcel Dekker, Inc., New York, 1986, pp. 91–92.

16.

Huber

Fitting Distributions to Data—Practical Issues in the Use of Probabilistic Risk Assessment. 1999. www.quantdec.com/envstats/misc/Fitting%20data%20to%20distributions.pdf. Accessed July 20, 2006.

17.

National Household Travel Survey (NHTS), Version 4 Datasets. FHWA, U.S. Department of Transportation. http://nhts.ornl.gov/index.shtml. Accessed July 2005.

18.

Appendix O: Methods to Estimate Annual Miles Driven per Vehicle. In NHTS 2001 User's Manual. FHWA, U.S. Department of Transportation, 2004.

19.

Highway Statistics 2001. FHWA, U.S. Department of Transportation. www.fhwa.dot.gov/ohim/hs01/vm1.htm. Accessed July 20, 2006.