Bayesian model selection without evidences: application to the dark energy equation-of-state

Abstract

A method is presented for Bayesian model selection without explicitly computing evidences, by using a combined likelihood and introducing an integer model selection parameter $n$ so that Bayes factors, or more generally posterior odds ratios, may be read off directly from the posterior of $n$. If the total number of models under consideration is specified a priori, the full joint parameter space $(\theta ,n)$ of the models is of fixed dimensionality and can be explored using standard Markov chain Monte Carlo (MCMC) or nested sampling methods, without the need for reversible jump MCMC techniques. The posterior on $n$ is then obtained by straightforward marginalisation. We demonstrate the efficacy of our approach by application to several toy models. We then apply it to constraining the dark energy equation-of-state using a free-form reconstruction technique. We show that $\Lambda$CDM is significantly favoured over all extensions, including the simple $w(z)=\mathrm{constant}$ model.

Published in MNRAS. Article is 13 pages long including 12 figures, 3 tables and 2 appendices

References in corpus (7)

• Bayes in the sky: Bayesian inference and model selection in cosmology
• PolyChord: nested sampling for cosmology
• Crossing the Phantom Divide with Parameterized Post-Friedmann Dark Energy
• Model selection applied to reconstruction of the Primordial Power Spectrum
• Reconstruction of the Dark Energy equation of state
• Fast Bayesian Inference for Exoplanet Discovery in Radial Velocity Data
• Bayesian Model Averaging in Astrophysics: A Review

Cited by in corpus (61)

• The NANOGrav 15-year Data Set: Evidence for a Gravitational-Wave Background
• The second data release from the European Pulsar Timing Array III. Search for gravitational wave signals
• The NANOGrav 15-year Data Set: Search for Signals from New Physics
• The NANOGrav 12.5-year Data Set: Search For An Isotropic Stochastic Gravitational-Wave Background
• The NANOGrav 11-year Data Set: Pulsar-timing Constraints On The Stochastic Gravitational-wave Background
• The International Pulsar Timing Array second data release: Search for an isotropic Gravitational Wave Background
• Dynamic nested sampling: an improved algorithm for parameter estimation and evidence calculation
• Common-red-signal analysis with 24-yr high-precision timing of the European Pulsar Timing Array: Inferences in the stochastic gravitational-wave background search
• Quantifying tensions in cosmological parameters: Interpreting the DES evidence ratio
• From Bright Binaries To Bumpy Backgrounds: Mapping Realistic Gravitational Wave Skies With Pulsar-Timing Arrays
• Quantifying dimensionality: Bayesian cosmological model complexities
• Cosmological discordances II: Hubble constant, Planck and large-scale-structure data sets
• Searching for continuous Gravitational Waves in the second data release of the International Pulsar Timing Array
• The second data release from the European Pulsar Timing Array V. Search for continuous gravitational wave signals
• fgivenx: A Python package for functional posterior plotting
• Search for the Gravitational-wave Background from Cosmic Strings with the Parkes Pulsar Timing Array Second Data Release
• The NANOGrav 12.5-year data set: Search for Non-Einsteinian Polarization Modes in theGravitational-Wave Background
• Noise analysis in the European Pulsar Timing Array data release 2 and its implications on the gravitational-wave background search
• Constraining the Polarization of Gravitational Waves with the Parkes Pulsar Timing Array Second Data Release
• Search for Stochastic Gravitational-Wave Background from Massive Gravity in the NANOGrav 12.5-Year Data Set
• Bayesian inflationary reconstructions from Planck 2018 data
• Bayesian Evidences for Dark Energy models in light of current obsevational data
• Constraining the dark energy equation of state using Bayes theorem and the Kullback-Leibler divergence
• Constraining ultralight vector dark matter with the Parkes Pulsar Timing Array second data release
• Reconstruction of the neutrino mass as a function of redshift
• Accurate characterization of the stochastic gravitational-wave background with pulsar timing arrays by likelihood reweighting
• Evaluating the prevalence of spurious correlations in pulsar timing array datasets
• Label Switching Problem in Bayesian Analysis for Gravitational Wave Astronomy
• Model Dependence of Bayesian Gravitational-Wave Background Statistics for Pulsar Timing Arrays
• Galaxy Kinematics and Mass Calibration in Massive SZE Selected Galaxy Clusters to z=1.3
• Bayesian Methods in Cosmology
• Towards a framework for testing general relativity with extreme-mass-ratio-inspiral observations
• Practical approaches to analyzing PTA data: Cosmic strings with six pulsars
• Search for Non-Tensorial Gravitational-Wave Backgrounds in the NANOGrav 15-Year Data Set
• Constraining the Graviton Mass with the NANOGrav 15-Year Data Set
• Is there a spectral turnover in the spin noise of millisecond pulsars?
• Revised bounds on local cosmic strings from NANOGrav observations
• Disentangling Multiple Stochastic Gravitational Wave Background Sources in PTA Datasets
• Reconstructing the redshift evolution of escaped ionizing flux from early galaxies with Planck and HST observations
• Nonparametric reconstructions of dynamical dark energy via flexknots
• Bayesian sparse reconstruction: a brute-force approach to astronomical imaging and machine learning
• Marginalised Normal Regression: Unbiased curve fitting in the presence of x-errors
• Cosmic expansion history from SNe Ia data via information field theory -- the charm code
• Free-form modelling of galaxy clusters: a Bayesian and data-driven approach
• Dark energy reconstruction analysis with artificial neural networks: Application on simulated Supernova Ia data from Rubin Observatory
• Separating deterministic and stochastic gravitational wave signals in realistic pulsar timing array datasets
• FlexKnot as a Generalised Model of the Sky-averaged 21-cm Signal at z ~ 6-30 in the Presence of Systematics
• Adaptive Kernel Density Estimation proposal in gravitational wave data analysis
• A Parsimonious Tour of Bayesian Model Uncertainty
• Compromise-free Bayesian neural networks
• A Detection of Red Noise in PSR J1824$-$2452A and Projections for PSR B1937+21 using NICER X-ray Timing Data
• Bayesian analysis of running holographic Ricci dark energy
• Knot reconstruction of the scalar primordial power spectrum with Planck, ACT, and SPT CMB data
• Accounting for Noise and Singularities in Bayesian Calibration Methods for Global 21-cm Cosmology Experiments
• Constraining inflation with nonminimal derivative coupling with the Parkes Pulsar Timing Array third data release
• Rapid Construction of Joint Pulsar Timing Array Datasets: The Lite Method
• Kernel-, mean- and noise-marginalised Gaussian processes for exoplanet transits and $H_0$ inference
• The NANOGrav 15 yr Data Set: Customized Chromatic Noise Models
• The impact of outliers on pulsar timing arrays
• Bayes Factors via Savage-Dickey Supermodels
• Resonances in reflective Hamiltonian Monte Carlo