Related papers: Robust model comparison tests of DAMA/LIBRA annual…

In statistical learning, models are classified as regular or singular depending on whether the mapping from parameters to probability distributions is injective. Most models with hierarchical structures or latent variables are singular, for…

Typical Bayesian methods for models with latent variables (or random effects) involve directly sampling the latent variables along with the model parameters. In high-level software code for model definitions (using, e.g., BUGS, JAGS, Stan),…

We have recently proposed a new information-based approach to model selection, the Frequentist Information Criterion (FIC), that reconciles information-based and frequentist inference. The purpose of this current paper is to provide a…

Data collected during three years with a germanium spectrometer at the Sierra Grande underground laboratory have been analyzed for distinctive features of annual modulation of the signal induced by WIMP dark matter candidates. The main…

In many hypothesis testing applications, we have mixed priors, with well-motivated informative priors for some parameters but not for others. The Bayesian methodology uses the Bayes factor and is helpful for the informative priors, as it…

Comparison of appropriate models to describe observational data is a fundamental task of science. The Bayesian model evidence, or marginal likelihood, is a computationally challenging, yet crucial, quantity to estimate to perform Bayesian…

Experimental observations and theoretical arguments point out that Dark Matter (DM) particles are one of the most prominent component of the Universe. This motivated the pioneer DAMA experiment to investigate the presence of these particles…

We analyze the annual-modulation effect, measured by the DAMA Collaboration with the new implementation of a further two-years running, in the context of a possible interpretation in terms of relic neutralinos. We impose over the set of…

If dark matter is composed of weakly interacting particles, Earth's orbital motion may induce a small annual variation in the rate at which these particles interact in a terrestrial detector. The DAMA collaboration has identified at a…

We assess the tension between DAMA/LIBRA and the latest dark matter annual modulation results from the ANAIS-112 and COSINE-100 NaI experiments, under a range of hypotheses ranging from physical to general parameterisations. We find that,…

Claims by the DAMA (DArk MAtter) collaboration to have detected an annually varying signal consistent with models of dark matter appear to be at variance with results from other dark-matter searches. To further understand the DAMA results,…

The Akaike information criterion (AIC) has been used as a statistical criterion to compare the appropriateness of different dark energy candidate models underlying a particular data set. Under suitable conditions, the AIC is an indirect…

The DAMA/NaI and DAMA/LIBRA annual modulation data, which may be interpreted as a signal for the existence of weakly interacting dark matter (WIMPs) in our galactic halo, are examined in light of null results from other experiments. We use…

For linear models with a diverging number of parameters, it has recently been shown that modified versions of Bayesian information criterion (BIC) can identify the true model consistently. However, in many cases there is little…

COSINE-100 is a direct detection dark matter experiment that aims to test DAMA/LIBRA's claim of dark matter discovery by searching for a dark matter-induced annual modulation signal with NaI(Tl) detectors. We present new constraints on the…

This paper proposes the asymmetric linear double autoregression, which jointly models the conditional mean and conditional heteroscedasticity characterized by asymmetric effects. A sufficient condition is established for the existence of a…

The DAMA/Libra experiment has recently confirmed the annual modulation signal obtained in the earlier DAMA/NaI experiment, providing strong evidence that they have actually detected dark matter. We examine the implications of this…

One aim of representation learning is to recover the original latent code that generated the data, a task which requires additional information or inductive biases. A recently proposed approach termed Independent Mechanism Analysis (IMA)…

We review some aspects of Bayesian and frequentist interval estimation, focusing first on their relative strengths and weaknesses when used in "clean" or "textbook" contexts. We then turn attention to observational-data situations which are…

The present DAMA/LIBRA experiment and the former DAMA/NaI have cumulatively released so far the results obtained with the data collected over 13 annual cycles (total exposure: 1.17 ton $\times$ yr). They give a model independent evidence of…