Observational Before—After Studies in Road Safety
Estimating the Effect of Highway and Traffic Engineering Measures on Road Safety
- 1st Edition - June 20, 1997
- Imprint: Pergamon
- Author: E. Hauer
- Language: English
- eBook ISBN:9 7 8 - 0 - 0 8 - 0 5 1 3 0 0 - 3
This three part monograph aims to enable road safety researchers and professionals to interpret correctly the results of one of the main sources of knowledge about the effect of… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteThis three part monograph aims to enable road safety researchers and professionals to interpret correctly the results of one of the main sources of knowledge about the effect of road safety engineering measures, the "observational Before-After study".
Part I, ESSENTIALS - contains information the author regards as essential for forming an opinion of results obtained by others, and for planning and analysing such a study. This is written to be accessible to all.
Part II, ADAPTATIONS OF CONVENTIONAL APPROACHES - explains how to avoid the errors and improve the results obtained from the predominant methods currently used. This Part employs algebra and statistical analysis.
Part III, ELEMENTS OF A NEW APPROACH - presents new approaches to improve future methods of observation and analysis.
For transportation researchers and professionals interested in road safety.
Section headings, chapter headings and papers: Preface. Glossary. Introduction. Essentials. What is the Question? Defining Safety. Underbrush. Safety as a property of an entity. Frequency or rate? Chapter summary. Counting Accidents. What is being counted. Target accidents. Chapter summary. Prediction and Estimation. Prediction of what safety would have been. Estimation of what safety was after the treatment. Chapter summary. Adaptions of Conventional Approaches. Basic Building Blocks. The four-step. Statistical differentials. Chapter summary. The Naive Before-After Study. Statistical anaylsis of the naive before-after study. Separating the wheat from the chaff. Study design considerations. Signal heads and intergreen times - on reading and learning. Chapter summary. Improving Prediction I: Factors Measured and Understood. Accounting for change in traffic. The traffic flow correction in the four-step. The estimation of rtf. Coefficients of variation for AADT estimates. Illustrations and discussion. Chapter summary. Improving Prediction II: Using a Comparison Group. Statistical analysis. Study design considerations for the 'C-G method'. Estimation of VAR {&ohgr;}. A case study: replacing STOP signs by YIELD signs. When different entities have different comparison ratios. The modified comparison ratio. Chapter summary. The Variability of Treatment Effect. The expanded 'four-step'. An illustration: raised pavement markers. Application to meta-analysis. Chapter summary.
Elements of a New Approach. Back to the Starting Point: The Empirical Bayes Approach. The shaky foundation and how to shore it up. The regression-to-the-mean phenomenon. Two clues to safety. The mathematics of mixing the two clues. How to estimate E {&kgr;} and VAR {&kgr;}. The proof of the pudding. Two case studies. Naive and C-G studies revisited. Additional applications. Chapter summary. A More Coherent Approach? Uses of multivariate models of accident counts. The model equation: meaning, form and assumptions. Likelihood function for parameter estimation. An illustration. How to estimate the &kgr;1, &kgr;2, &kgr;3, ..., &kgr;Y for some entity? How to predict the &kgr;i,Y+;1, ..., &kgr;i,Y+Z. The safety effect of road resurfacing in New York State. Chapter summary. Closure. References. Index.
Elements of a New Approach. Back to the Starting Point: The Empirical Bayes Approach. The shaky foundation and how to shore it up. The regression-to-the-mean phenomenon. Two clues to safety. The mathematics of mixing the two clues. How to estimate E {&kgr;} and VAR {&kgr;}. The proof of the pudding. Two case studies. Naive and C-G studies revisited. Additional applications. Chapter summary. A More Coherent Approach? Uses of multivariate models of accident counts. The model equation: meaning, form and assumptions. Likelihood function for parameter estimation. An illustration. How to estimate the &kgr;1, &kgr;2, &kgr;3, ..., &kgr;Y for some entity? How to predict the &kgr;i,Y+;1, ..., &kgr;i,Y+Z. The safety effect of road resurfacing in New York State. Chapter summary. Closure. References. Index.
- Edition: 1
- Published: June 20, 1997
- Imprint: Pergamon
- Language: English
- eBook ISBN: 9780080513003
EH
E. Hauer
Affiliations and expertise
Department of Civil Engineering, University of Toronto, Ontario, Canada