Skip to Main content Skip to Navigation
Theses

Statistique bayésienne appliquée en sciences humaines et sociales.

Abstract : This work focuses on two issues: the first concerns mediation analysis and the second concerns dating in archaeology in the presence of outliers. Concerning the mediation analysis, I have developed a non-parametric approach to test the existence of direct effect in binary response causal mediation. Second, prior distributions are compared in Bayesian inference for causal mediation with binary re- sponse. Third, the B-priors are adapted to me- diation models from psychological research and a moderation test based on the Bayes factor is proposed. Concerning dating in archaeology, a methodology is developed to estimate ages in the presence of outliers. This is based on an existing Bayesian model (Event Model) from which an outlier detection test is developed. This methodology is applied in the combination of measurements and in the estimation of an OSL age (Optically Stimulated Luminescence).
Document type :
Theses
Complete list of metadatas

Cited literature [109 references]  Display  Hide  Download

http://hal.univ-nantes.fr/tel-02431662
Contributor : Jean-Michel Galharret <>
Submitted on : Wednesday, January 8, 2020 - 9:25:22 AM
Last modification on : Monday, October 19, 2020 - 10:59:30 AM
Long-term archiving on: : Thursday, April 9, 2020 - 1:19:05 PM

File

these JM GALHARRET.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : tel-02431662, version 1

Collections

Citation

Jean-Michel Galharret. Statistique bayésienne appliquée en sciences humaines et sociales.. Statistiques [math.ST]. Université de Nantes Faculté des sciences et des techniques, 2019. Français. ⟨tel-02431662⟩

Share