Simple and statistically sound recommendations for analysing physical theories.

Physical theories that depend on many parameters or are tested against data from many different experiments pose unique challenges to statistical inference. Many models in particle physics, astrophysics and cosmology fall into one or both of these categories. These issues are often sidestepped with statistically unsound ad hoc methods, involving intersection of parameter intervals estimated by multiple experiments, and random or grid sampling of model parameters. Whilst these methods are easy to apply, they exhibit pathologies even in low-dimensional parameter spaces, and quickly become problematic to use and interpret in higher dimensions. In this article we give clear guidance for going beyond these procedures, suggesting where possible simple methods for performing statistically sound inference, and recommendations of readily-available software tools and standards that can assist in doing so. Our aim is to provide any physicists lacking comprehensive statistical training with recommendations for reaching correct scientific conclusions, with only a modest increase in analysis burden. Our examples can be reproduced with the code publicly available at Zenodo.

Impact of a Higgs boson at a mass of 126 GeV on the standard model with three and four fermion generations.

We perform a comprehensive statistical analysis of the standard model (SM) with three and four generations using the latest Higgs search results from LHC and Tevatron, the electroweak precision observables measured at LEP and SLD, and the latest determinations of M(W), m(t), and α(s). For the three-generation case we analyze the tensions in the electroweak fit by removing individual observables from the fit and comparing their predicted values with the measured ones. In particular, we discuss the impact of the Higgs search results on the deviations of the electroweak precision observables from their best-fit values. Our indirect prediction of the top mass is m(t) =175.7(-2.2)(+3.0) GeV at 68.3% C.L., which is in good agreement with the direct measurement. We also plot the preferred area in the M(W)-m(t) plane. The best-fit Higgs boson mass is 126.0 GeV. For the case of the SM with a perturbative sequential fourth fermion generation (SM4) we discuss the deviations of the Higgs signal strengths from their best-fit values. The H → γγ signal strength now disagrees with its best-fit SM4 value at more than 4σ. We perform a likelihood-ratio test to compare the SM and SM4 and show that the SM4 is excluded at 5.3σ. Without the Tevatron data on H → bb the significance drops to 4.8σ.