Causal inference to formalize responsibility analyses in road safety epidemiology

Résumé : The last few decades have seen the Structural Causal Model framework provide valuable tools to assess causal effects from observational data. In this article, we briefly review recent results regarding the recoverability of causal effects from selection biased data, and apply them to the case of responsibility analyses in road safety epidemiology. Our objective is to formally determine whether causal effects can be unbiasedly estimated through this type of analyses, when available data are restricted to severe accidents, as it is commonly the case in practice. However, because speed has a direct effect on the severity of the accident, we show that the causal odds-ratio of exposures that influence speed, such as alcohol, is not estimable. We present numerical results to illustrate our arguments, the magnitude of the bias and to discuss some recent results from real data.
Keywords : STATISTICS METHODOLOGY
Document type :
Conference papers
Complete list of metadatas

Cited literature [52 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02354511
Contributor : Ifsttar Cadic <>
Submitted on : Thursday, November 7, 2019 - 5:38:17 PM
Last modification on : Saturday, November 9, 2019 - 1:42:26 AM

File

ris00001390.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02354511, version 1

Collections

Citation

Marine Dufournet, Emilie Lanoy, Jean-Louis Martin, Vivian Viallon. Causal inference to formalize responsibility analyses in road safety epidemiology. Journées GDR/SFB, Oct 2017, BORDEAUX, France. 1 p. ⟨hal-02354511⟩

Share

Metrics

Record views

5

Files downloads

1