Comment on "Bayesian evidence: can we beat MultiNest using traditional MCMC methods", by Rutger van Haasteren (arXiv:0911.2150)
arXiv:1001.0719
Abstract
In arXiv:0911.2150, Rutger van Haasteren seeks to criticize the nested sampling algorithm for Bayesian data analysis in general and its MultiNest implementation in particular. He introduces a new method for evidence evaluation based on the idea of Voronoi tessellation and requiring samples from the posterior distribution obtained through MCMC based methods. He compares its accuracy and efficiency with MultiNest, concluding that it outperforms MultiNest in several cases. This comparison is completely unfair since the proposed method can not perform the complete Bayesian data analysis including posterior exploration and evidence evaluation on its own while MultiNest allows one to perform Bayesian data analysis end to end. Furthermore, their criticism of nested sampling (and in turn MultiNest) is based on a few conceptual misunderstandings of the algorithm. Here we seek to set the record straight.
5 pages, 1 figure, added arXiv numbers to the references
References in corpus (13)
- Detection of a Dark Substructure through Gravitational Imaging
- Bayesian Selection of sign(mu) within mSUGRA in Global Fits Including WMAP5 Results
- Selecting a Model of Supersymmetry Breaking Mediation
- Efficient reconstruction of CMSSM parameters from LHC data - A case study
- Cold Dark Matter Isocurvature Perturbations: Constraints and Model Selection
- Prospects for dark matter detection with IceCube in the context of the CMSSM
- A Bayesian Analysis of the Constrained NMSSM
- Neutrino mass from cosmology: Impact of high-accuracy measurement of the Hubble constant
- Cluster detection in weak lensing surveys
- Classifying LISA gravitational wave burst signals using Bayesian evidence
- Bayesian evidence: can we beat MultiNest using traditional MCMC methods?
- Constraining the MSSM with Dark Matter indirect detection data
- Are BR(b->s gamma) and (g-2)_muon consistent within the Constrained MSSM?