Analytical methods in multivariate highway safety exposure data estimation

Details

• Creators:
  Mengert, Peter ; Roberts, Edwin
• Corporate Creators:
  John A. Volpe National Transportation Systems Center (U.S.)
• Subject/TRT Terms:
  • Information processing
  • Multivariate analysis
  • Highway safety
  • Traffic crashes
  • Mathematical models
  • Iterative Proportional Fitting
  • Log-Linear Modelling
  • Expectation Maximization
  • Accident Exposure
  • Data (Highway)
  More +
• Publication/ Report Number:
  DOT-HS806-494 ; DOT-TSC-NHTSA-83-5
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report; Oct. 1982-Nov. 1983
• Corporate Publisher:
  National Center for Statistics and Analysis (U.S.)
• Abstract:
  Three general analytical techniques which may be of use in ; extending, enhancing, and combining highway accident exposure data are ; discussed. The techniques are log-linear modelling, iterative propor ; tional fitting and the expectation maximization (EM) method. A general ; discussion identifies a number of frequently encountered exposure data ; deficiences and indicates how one or more of the three analytical tech ; niques may be of use in addressing each deficiency. The more ; mathematically-oriented sections provide a general introduction to each ; of the methods and discuss some of their properties of special interest ; in applications. A section illustrating applications to driving exposure data is included, together with computer program listings.
• Format:
  PDF
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/5834/dot_5834_DS1.pdf
• File Type:
  [PDF - 4.04 MB]
• Collection(s):
  Volpe Center
• Main Document Checksum:
  urn:sha-512:01729d4d762d447353102863f8cd6eecce79195fa56049e64af23cfc2e800cc33bd8891f54cfd095f48e434c8b04423c51f50b7eca1da362916493c2f251a1e0