Bayesian vs frequentist: comparing Bayesian model selection with a frequentist approach using the iterative smoothing method

We have developed a frequentist approach for model selection which determines the consistency between any cosmological and data using distribution of likelihoods from iterative smoothing method. Using this approach, we shown how confidently can conclude whether support given without comparison to different one. In current work, compare our with conventional Bayesian based on estimation evidence nested sampling. use simulated future Roman (formerly WFIRST)-like type Ia supernovae in analysis. discuss limits show proposed perform better falsification individual models. Namely, if true is among candidates being tested that select correct model. If all options are false, then will merely least incorrect Our designed such case models false.