The Empirical Bayes Method for Before and After Analysis

Slides:



Advertisements
Similar presentations
FUTURE CMF RESEARCH AND CHALLENGES Traffic Records Forum October 27, 2014 Daniel Carter, UNC HSRC.
Advertisements

Spring Before-After Studies Recap: we need to define the notation that will be used for performing the two tasks at hand. Let: be the expected number.
Spring  Crash modification factors (CMFs) are becoming increasing popular: ◦ Simple multiplication factor ◦ Used for estimating safety improvement.
Department of Civil Engineering University of Washington Quantitative Safety Analysis for Intersections on Washington State Two-lane Rural Highways Master’s.
Investigation of Varied Time Intervals in Crash Hotspot Identification Authors: Wen Cheng, Ph.D., P.E., Fernando Gonzalez, EIT, & Xudong Jia; California.
Developing an Intelligent Decision Support System for the Proactive Implementation of Traffic Safety Strategies Hongyi Chen, Ph.D. Assistant Professor.
Spring Sampling Frame Sampling frame: the sampling frame is the list of the population (this is a general term) from which the sample is drawn.
Spring INTRODUCTION There exists a lot of methods used for identifying high risk locations or sites that experience more crashes than one would.
Empirical Bayes Estimate Spring Empirical Bayes Model For the EB method, a different weight is assigned to the prior distribution and standard estimate.
Need to know in order to do the normal dist problems How to calculate Z How to read a probability from the table, knowing Z **** how to convert table values.
1 Chapter 17: Introduction to Regression. 2 Introduction to Linear Regression The Pearson correlation measures the degree to which a set of data points.
Generalized Linear Models
Incorporating Temporal Effect into Crash Safety Performance Functions Wen Cheng, Ph.D., P.E., PTOE Civil Engineering Department Cal Poly Pomona.
The Empirical Bayes Method for Safety Estimation Doug Harwood MRIGlobal Kansas City, MO.
Network Screening 1 Module 3 Safety Analysis in a Data-limited, Local Agency Environment: July 22, Boise, Idaho.
1 Validation and Implication of Segmentation on Empirical Bayes for Highway Safety Studies Reginald R. Souleyrette, Robert P. Haas and T. H. Maze Iowa.
Evaluation of Alternative Methods for Identifying High Collision Concentration Locations Raghavan Srinivasan 1 Craig Lyon 2 Bhagwant Persaud 2 Carol Martell.
1 CEE 763 Fall 2011 Topic 1 – Fundamentals CEE 763.
Safety management software for state and local highway agencies: –Improves identification and programming of site- specific highway safety improvements.
Role of SPFs in SafetyAnalyst Ray Krammes Federal Highway Administration.
HSM: Another Tool for Safety Management in Wyoming 1 Excellence in Transportation.
SPF Development and Data Needs John Milton Ph.D., P.E., Washington State Department of Transportation National Safety Performance Function Summit July.
1 7. What to Optimize? In this session: 1.Can one do better by optimizing something else? 2.Likelihood, not LS? 3.Using a handful of likelihood functions.
Fall 2002Biostat Statistical Inference - Proportions One sample Confidence intervals Hypothesis tests Two Sample Confidence intervals Hypothesis.
CE 552 Week 9 Crash statistical approaches Identification of problem areas - High crash locations.
July 29 and 30, 2009 SPF Development in Illinois Yanfeng Ouyang Department of Civil & Environmental Engineering University of Illinois at Urbana-Champaign.
Calibrating Highway Safety Manual Equations for Application in Florida Dr. Siva Srinivasan, Phillip Haas, Nagendra Dhakar, and Ryan Hormel (UF) Doug Harwood.
Fall  Crashes are “independent” and “random” events (probabilistic events)  Estimate a relationship between crashes and covariates (or explanatory.
Sampling Design and Analysis MTH 494 Lecture-21 Ossam Chohan Assistant Professor CIIT Abbottabad.
Session 2 History How did SPF come into being and why is it here to stay? Geni Bahar, P.E. NAVIGATS Inc.
Role of Safety Performance Functions in the Highway Safety Manual July 29, 2009.
Evaluating the performance of three different network screening methods for detecting high collision concentration locations using empirical data Prepared.
2( ) 8x + 14y = 4 -12x – 14y = x = x = 4 8x + 14y = 4 8(4) + 14y = y = y = -28 ___ ___ y = -2 The solution is (4, -2)
1 The Highway Safety Manual Predictive Methods. 2 New Highway Safety Manual of 2010 ►Methodology is like that for assessing and assuring the adequacy.
Low Cost Safety Improvements Pooled Fund Study Analytical Basics Dr. Bhagwant Persaud.
LECTURE 15: PARTIAL LEAST SQUARES AND DEALING WITH HIGH DIMENSIONS March 23, 2016 SDS 293 Machine Learning.
HIGHWAY SAFETY MANUAL Copyright © 2016 STC, UK
SUR-2250 Error Theory.
Impact of Intersection Angle on Safety
Artificial Realistic Data (ARD)
HSM Applications to Multilane Rural Highways and Urban Suburban Streets Predicting Crash Frequency and CMFs for Rural Divided Multilane Highways - Session.
Statistical Data Analysis - Lecture /04/03
Physics 114: Exam 2 Review Weeks 7-9
Generalized Linear Models
Solve Systems of Linear Equations by Elimination
8.1 – 8.3 Solving Proportions, Geometric Mean, Scale Factor of Perimeter and Area Since these sections are all very short, we are combining them into one.
Physics 114: Exam 2 Review Material from Weeks 7-11
Estimating
Exploratory Analysis of Crash Data
26th CARSP Conference, Halifax, June 5-8, 2016
Transportation Engineering Basic safety methods April 8, 2011
Network Screening & Diagnosis
The Empirical Bayes Method for Before and After Analysis
Pencil, highlighter, red pen, GP NB, textbook, calculator, HW
Doug Harwood Midwest Research Institute
HSM Practitioner’s Guider for Two-Lane Rural Highways Workshop
KS3 Mathematics A5 Functions and graphs
Prediction and Accuracy
HW 7b: HSM Practitioner’s Guider for Two-Lane Rural Highways Workshop
Day 71 – Verifying dilations
If the question asks: “Find the probability if...”
Pull 2 samples of 10 pennies and record both averages (2 dots).
Solving Systems of Equations by the Substitution and Addition Methods
Solving Inequalities Solving inequalities follows the same procedures as solving equations. There are a few special things to consider with.
HSM Practitioner’s Guider for Two-Lane Rural Highways Workshop
Solving Equations Containing Rational Expressions § 6.5 Solving Equations Containing Rational Expressions.
Algebra 1 Section 4.6.
HSM Practitioner’s Guider for Two-Lane Rural Highways Workshop
OUTLINE Questions? Quiz Go over homework Next homework Forecasting.
CARSP Conference May 26-29, 2019 Calgary
Presentation transcript:

The Empirical Bayes Method for Before and After Analysis

Key Reference Hauer, E., D.W. Harwood, F.M. Council, M.S. Griffith, “The Empirical Bayes method for estimating safety: A tutorial.” Transportation Research Record 1784, pp. 126-131. National Academies Press, Washington, D.C.. 2002 http://www.engr.uky.edu/~rsouley/CE%20635/docs/Bayes_tutor_hauer.pdf Open This Document and read through as you go along on PPT

EB Procedures Abridged Full Last 2-3 years data Traffic volume Can use more data Includes other factors

Empirical Bayes Weight should be based on sound logic and real data

The SPF – Safety Performance Function So what is the expected number of crashes for facilities of this type? Develop a (negative binomial) regression model to fit all the data – must have data to do this.* An example SPF: μ=average crashes/km-yr (or /yr for intersections) So, if ADT = 4000 Note: this SPF depends only on ADT … it needn’t * Can also use equations from HSM, but need “phi”

The overdispersion parameter The negative binomial is a generalized Poisson where the variance is larger than the mean (overdispersed) The “standard deviation-type” parameter of the negative binomial is the overdispersion parameter φ variance = η[1+η/(φL)] Where … μ=average crashes/km-yr (or /yr for intersections) η=μYL (or μY for intersections) = number of crashes/time φ=estimated by the regression (units must be complementary with L, for intersections, L is taken as one)

Example 1: How many crashes should we expect next year???

Example 1: road segment, 1 yr. of data

Example 1: computing the weight What happens when Y is large (compared to μ/φ)? When μ is small compared to φ?

Example 1 (cont): = 4.71 ± 1.19 accidents/km/year

Note effect of more data Example 2: 3 years of data: 12, 7, 8 4000 vpd Step 1: Step 2: Step 3: As before Note effect of more data = 7.97 ± 1.44 accidents/year for the section (compare to previous estimate and reliability) 1) 4.71 ± 1.19 2) 4.43 ± 0.80

Example 3: AMFs 1.2 meter shoulders (instead of 1.5) AMF (CMF) = 1.04 (4% increase in crashes) Step 1: Step 2: Step 3: Why is weight lower? 1) 4.71 ± 1.19 2) 4.43 ± 0.80 3) 4.47 ± 0.81

Example 4: subsections Total length = 1.5km, 11 crashes in 2 years

Large for fatals (helps you not to “chase” them Example 5: Severity 2.41 x 0.019 = 0.046 … 1.8 x 3 x 0.046 = 0.247 Note: φ stays same (mult dist. by constant); Large for fatals (helps you not to “chase” them Note: 20.357 ≠ 23.9 (from prob 2) … why? What is the suggested an ad hoc solution?

Example 6: intersection ADT=4520 SPF = 6.54×10-5 ×ADTmainline×ADTminor road ADT=230 AMF = 1.27 7 crashes in 3 years Step 1: Step 2: Step 3: So, what can you conclude about the site?

Example 7: group of intersections 11 crashes in 3 years Applies if you don’t know what crashes happened at what intersection Step 1: Step 2: (simplistic) However, not clear what to use

Example 7: (cont)

Example 7: (cont) Step 3: using w=0.088, Why so much confidence in the actual number? Is it because we have 3 yrs of data? Is it because 11 is smaller than 20.7? What would happen if 11 had been, say, 32?

Example 8 (The full procedure) 1.8 km, 9 yrs. Unchanged road ADT varies, AMF = 0.95, 74 total crashes μ =

Example 8, cont. (If all μ are equal) Why so small???

Example 9: Secular Trends Yearly multipliers can be used like AMFs to account for weather, technology changes (must be able to get them) Make much difference?

Example 10: Projections Projections can be made by using a simple ratio of ADTs (raised to the appropriate power) multiplied by the corresponding ratio of AMFs or yearly multipliers

Some thought questions Does EB eliminate RTM as stated? What happened if the SPF is not appropriate for your site What does appropriate mean?

Software for Homework You will need some software to develop the NB regression model for your SPF – that is the “R project” program. Investigate that now (see HW). http://www.r-project.org/ (info on “R”) Download R 2.15.0 for Windows (47 megabytes, 32/64 bit) Installation and other instructions New features in this version: Windows specific, all platforms.

Shouldn't THIS be the true safety effect?

Professor, May I be excused? My brain is full. Gary Larson, The Far Side, ©1986