A note on Ritov's Bayes approach to the minimax property of the cusum procedure

This is the authors' abstract. We don't add key points for this paper.

We consider, in a Bayesian framework, the model Wₜ = Bₜ + θ (t - ν)⁺, where B is a standard Brownian motion, θ is arbitrary but known and ν is the unknown change-point. We transfer the construction of Ritov to this continuous time setup and show that the corresponding Bayes problems can be reduced to generalized parking problems.