Accelerated expansion from ghost-free bigravity: a statistical analysis with improved generality

TL;DR

This paper performs a comprehensive statistical analysis of ghost-free bigravity cosmology, showing it can mimic Lambda-CDM and fit observational data well, but with parameter degeneracies and no clear statistical preference.

Contribution

It provides the first extensive Bayesian and frequentist analysis of bigravity models against cosmological data, assessing their viability as alternatives to Lambda-CDM.

Findings

Bigravity models can produce late-time acceleration similar to Lambda-CDM.

The models fit observational data well at the background level.

Parameters of the bigravity model are highly degenerate, requiring further analysis.

Abstract

We study the background cosmology of the ghost-free, bimetric theory of gravity. We perform an extensive statistical analysis of the model using both frequentist and Bayesian frameworks and employ the constraints on the expansion history of the Universe from the observations of supernovae, the cosmic microwave background and the large scale structure to estimate the model's parameters and test the goodness of the fits. We explore the parameter space of the model with nested sampling to find the best-fit chi-square, obtain the Bayesian evidence, and compute the marginalized posteriors and mean likelihoods. We mainly focus on a class of sub-models with no explicit cosmological constant (or vacuum energy) term to assess the ability of the theory to dynamically cause a late-time accelerated expansion. The model behaves as standard gravity without a cosmological constant at early times, with an emergent extra contribution to the energy density that converges to a cosmological constant in the far future. The model can in most cases yield very good fits and is in perfect agreement with the data. This is because many points in the parameter space of the model exist that give rise to time-evolution equations that are effectively very similar to those of the $\Lambda$CDM. This similarity makes the model compatible with observations as in the $\Lambda$CDM case, at least at the background level. Even though our results indicate a slightly better fit for the $\Lambda$CDM concordance model in terms of the $p$-value and evidence, none of the models is statistically preferred to the other. However, the parameters of the bigravity model are in general degenerate. A similar but perturbative analysis of the model as well as more data will be required to break the degeneracies and constrain the parameters, in case the model will still be viable compared to the $\Lambda$CDM.