\texttt{GooStats} is a software framework that provides a flexible environment and common tools to implement multi-variate statistical analysis. The framework is based on C++11, CERN ROOT, MINUIT, and \texttt{GooFit}, a popular minimization engine that can run on general purpose graphics processing units. Running a multi-variate analysis in parallel on graphics processing units yields a huge...

Parameter estimation in high-energy neutrino/HEP experiments often involves Monte-Carlo simulations to evaluate likelihood functions, a typical use case being forward-folding Poisson likelihood analyses. Limited Monte Carlo samples induce statistical uncertainty into this problem. This is sometimes solved by the classical Ansatz of Barlow/Beeston (1993) - an approach that can be thought of as...

The Borexino detector, located at the Laboratori Nazionali del Gran Sasso in Italy, is a liquid scintillator detector with a primary goal to measure solar neutrinos. The spectral fit of the energy spectrum has been performed for the first time in the whole energy range from 0.19 up to 2.93 MeV. This approach made it possible to obtain the fluxes of 7Be, pp, and pep solar neutrinos...

A typical experiment in high energy physics is considered. The result of the experiment is assumed to be a histogram consisting of bins or channels with numbers of corresponding registered events. The expected background and expected signal shape or acceptance are measured in separate auxiliary experiments, or calculated by the Monte Carlo method with finite sample size, and hence with finite...

Neutrinos are tiny sub-atomic particles that carry no electrical charge and interact with matter only through the weak nuclear force, which makes them extremely hard to detect. There are three distinct types of neutrinos, called "flavors": ($\nu_e$, $\nu_\mu$, $\nu_\tau$), each of which can "oscillate" into the other with a detectable probability. Many experiments have been set-up to measure...

Statistical data analysis of modern experiments deals with large-scale models with hundreds of nuisance parameters. Direct application on statistical methods such as likelihood profiling, Bayesian methods and especially Feldman-Cousins procedure can lead to extensive numerical computations.

In order to facilitate the growing need for flexible and high-performance analysis tools to deal...

The look-elsewhere effect is a familiar issue to collider experiments, and occurs, for example, when a search is performed for a new resonance that is not predicted under the null hypothesis. Many searches for sterile neutrinos employ a similar strategy: looking for evidence of oscillation between two active flavours at an unknown mass-squared splitting. As with collider searches, this ...

Optimization problems in HEP often involve maximizing a measure of the sensitivity of the analysis to an hypothesis with respect to another; the latter is referred to as null hypothesis and in a frequentist framework is tested against the former, which is referred to as alternative hypothesis.

In most cases, it is desirable to fully compute the expected frequentist significance, accounting...

The canonical way to make experimental neutrino-cross-section data available for comparison with different theories and other experiments is to unfold it.

The aim of this is to remove the detector effects and efficiencies from the data to release distributions of variables of interest in "truth space".

Depending on the available data, the detector properties, and the variables of interest, it...

We are in an era of precision measurements at the Large Hadron Collider. The precision that can be achieved on some of the measurements is limited however due to large systematic uncertainties. This paper introduces a new technique to reduce the systematic uncertainty by quantifying the systematic impact of single events and correlating it with event observables to identify parts of the phase...

Linear algebra has been widely used in physics analysis of high-energy experiments. In this talk, I am going to review some of its recent usage in detector signal processing, noise filtering, event reconstruction, and data unfolding. In particular, its connections to various numerical and analytical techniques including the Fast Fourier Transformation, the Compressed Sensing, and the...

The determination of the neutrino Mass Hierarchy (MH) is one of the main goals of the major current and future neutrino experiments. The analysis usually proceeds from the $\Delta\chi^2$ estimator. This estimator may show several draw-backs and concerns, together with a debatable strategy.

The author will discuss the needs for a clear strategy as well as the related sensitivity evaluation.

The...

The statistical issues related to the search for sterile neutrinos are reviewed with focus on short-baseline appearance and disappearance experiments. The sensitivities for limit setting and signal discovery are discussed along with their dependency on the experimental parameters, including the signal rate and the spectral shape. Our baseline analysis is built on a profile-likelihood test...

In a statistical analysis in Particle Physics, nuisance parameters can be introduced to take into account various types of systematic uncertainties. The best estimate of such a parameter is often modeled as a Gaussian distributed variable with a given standard deviation (the corresponding "systematic error"). Although the assigned systematic errors are usually treated as constants, in...

Low-background experiments typically perform radioassay on detector construction materials, and use the resulting radioimpurity estimates to project experiment sensitivity. However, as the radiopurity of the materials improves and approaches the detection limit of the radioassay techniques, the radioimpurity concentration of the materials cannot be conclusively determined. Instead, only an...

I report the results of a search for $\bar{\nu}_{\mu} \rightarrow \bar{\nu}_{e}$ oscillations at the T2K experiment in a 3-flavour framework. An exposure of $1.49 \times 10^{21}$ Protons On Target (POT) is used in $\nu$ mode and $1.63 \times 10^{21}$ POT in $\bar{\nu}$ mode; an increase of $46\%$ in the $\bar{\nu}$ exposure compared to results reported in June 2018.

Results are reported for a...