Regression models with crossed random effect errors can be very expensive to compute. The cost of both generalized least squares and Gibbs sampling easily grow as N3/2 (or worse) for N observations. Papaspiliopoulos, Roberts Zanella (Biometrika 107 (2020) 25–40) present a collapsed sampler that costs O(N), but under an extremely stringent model. We propose backfitting algorithm compute estimate...

The effects of possible explicit violation of the Peccei-Quinn symmetry responsible for the solution of the strong CP problem are studied in super-symmetric models. It is shown that automatic models with an abelian U (1) gauge symmetry are easy to construct both in the context of fundamental and composite models of axions. It is argued that it is preferable to use abelian rather that nonabelian...

Spatial phenomena are subject to scale effects, but there are rarely studies addressing such effects on spatially embedded contact networks. There are two types of structure in these networks, network structure and spatial structure. The network structure has been actively studied. The spatial structure of these networks has received attention only in recent years. Certainly little is known whe...

The hypothesis that non-perturbative gravitational effects lead to explicit breaking of global symmetries is considered in the context of Majoron models. We find that the nonvanishing Majoron mass generated by these effects can overclose the universe unless the massive Majoron is unstable. The cosmological mass density constraints can then be satisfied only if V BL < 10 TeV, where V BL is the s...

Background: Empirical evidence investigating heterogeneous impact of retirement on mental health depending on social backgrounds is lacking, especially among older adults. Methods: We examined the impact of changes in working status on changes in mental health using Japanese community-dwelling adults aged ≥65 years participating in the Japan Gerontological Evaluation Study between 2010 and 2013...