2012
DOI: 10.1016/j.aap.2011.12.008
|View full text |Cite
|
Sign up to set email alerts
|

Examining the effects of site selection criteria for evaluating the effectiveness of traffic safety countermeasures

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
18
0
1

Year Published

2013
2013
2022
2022

Publication Types

Select...
4
3

Relationship

1
6

Authors

Journals

citations
Cited by 38 publications
(20 citation statements)
references
References 23 publications
1
18
0
1
Order By: Relevance
“…We should be careful when using the survival analysis method if treated sites are highly ranked hotspots in the before period, due to the RTM and site selection effects. However, it should be noted that according to the simulation study in Section 3.4, the consequence of the RTM and site selection effects gets smaller as the effect of site‐specific unobserved heterogeneity increases, which is consistent with the finding in Lord and Kuo (). On the other hand, temporal changes of unobserved factors could lead to the fluctuation of crash observations over time.…”
Section: Discussionsupporting
confidence: 85%
See 3 more Smart Citations
“…We should be careful when using the survival analysis method if treated sites are highly ranked hotspots in the before period, due to the RTM and site selection effects. However, it should be noted that according to the simulation study in Section 3.4, the consequence of the RTM and site selection effects gets smaller as the effect of site‐specific unobserved heterogeneity increases, which is consistent with the finding in Lord and Kuo (). On the other hand, temporal changes of unobserved factors could lead to the fluctuation of crash observations over time.…”
Section: Discussionsupporting
confidence: 85%
“…When the dispersion κ=0.6, the true CRRs are within 1 SD of the means estimated by the SARE model. Lord and Kuo () also found that the reduction in bias was associated with the increase in the dispersion parameter. The survival analysis can be an acceptable method even for treated sites top ranked in crash frequency when the dispersion of crash distribution is high and the unobserved heterogeneity effect dominates.…”
Section: Validation Of Survival Analysismentioning
confidence: 87%
See 2 more Smart Citations
“…One widely applied approach to help performing both tasks is the popular empirical Bayesian (EB) method. This method can correct for the regression-to-the mean bias (if the site selection bias is not present, see (14)), refines the predicted mean of an entity, and is relative simple to manipulate compared to the fully Bayesian approach (1). As discussed by Hauer (15,16) and Cheng and Washington (17), the EB method rests on two assumptions: (1) at a given location, crash occurrence obeys the Poisson probability law with mean  ; (2) the probability distribution of the  's of the population of sites is gamma distributed.…”
Section: Introductionmentioning
confidence: 99%