Related papers: Local Two-Sample Testing: A New Tool for Analysing…
Two-sample testing is a fundamental problem in statistics. Despite its long history, there has been renewed interest in this problem with the advent of high-dimensional and complex data. Specifically, in the machine learning literature,…
Rejecting the null hypothesis in two-sample testing is a fundamental tool for scientific discovery. Yet, aside from concluding that two samples do not come from the same probability distribution, it is often of interest to characterize how…
We present a simple method for assessing the predictive performance of high-dimensional models directly in data space when only samples are available. Our approach is to compare the quantiles of observables predicted by a model to those of…
The problem of identifying regions of spatially interesting, different or adversarial behavior is inherent to many practical applications involving distributed multisensor systems. In this work, we develop a general framework stemming from…
This article concerns tests for the two-sample location problem when the dimension is larger than the sample size. The traditional multivariate-rank-based procedures cannot be used in high dimensional settings because the sample scatter…
We revisit the performance and biases of the two-dimensional approach to galaxy-galaxy lensing. This method exploits the information for the actual positions and ellipticities of source galaxies, rather than using only the ensemble…
Hypothesis testing in high dimensional data is a notoriously difficult problem without direct access to competing models' likelihood functions. This paper argues that statistical divergences can be used to quantify the difference between…
To develop galaxy-targeting approaches, the gravitational-wave community built a catalog of stellar mass in the local universe based on the 2MASS spectroscopic and photometric redshift surveys. By cleaning and supplementing this catalog,…
We introduce a new 2-D hexagon technique to probe the topological structure of the universe, in which we map regions of the sky with high and low galaxy densities onto a 2-D lattice of hexagon unit cells, We define filled cells as…
The two-sample hypothesis testing problem is studied for the challenging scenario of high dimensional data sets with small sample sizes. We show that the two-sample hypothesis testing problem can be posed as a one-class set classification…
We are carrying out a comprehensive multi-wavelength study of dwarf galaxies in the Local Volume (< 5 Mpc). After our all-sky survey more than doubled the dwarf census we are now measuring structural parameters, integrated properties, and…
We study the problem of conditional two-sample testing, which aims to determine whether two populations have the same distribution after accounting for confounding factors. This problem commonly arises in various applications, such as…
We consider the hypothesis testing problem of detecting a shift between the means of two multivariate normal distributions in the high-dimensional setting, allowing for the data dimension p to exceed the sample size n. Specifically, we…
We present new evidence for a large deficiency in the local galaxy distribution situated in the 4000 sq.deg. APM survey area. We use models guided by the 2dF Galaxy Redshift Survey (2dFGRS) n(z) as a probe of the underlying LSS. We first…
Using the bright galaxy counts from the 2 Micron All Sky Survey (2MASS) second incremental release, two techniques for probing large-scale structure at distances of ~150 h-1 Mpc are investigated. First, we study the counts from two sets of…
We investigate the large-scale structure of the local galaxy distribution using the recently completed 2 Micron All Sky Survey (2MASS). First, we determine the K-band number counts over the 4000 sq.deg. APM survey area where evidence for a…
We present a new non-parametric method to quantify morphologies of galaxies based on a particular family of learning machines called support vector machines. The method, that can be seen as a generalization of the classical CAS…
We consider testing for two-sample means of high dimensional populations by thresholding. Two tests are investigated, which are designed for better power performance when the two population mean vectors differ only in sparsely populated…
We quantify the effects of \emph{morphological k-correction} at $1<z<2$ by comparing morphologies measured in the K and I-bands in the COSMOS area. Ks-band data have indeed the advantage of probing old stellar populations for $z<2$,…
The rise of generative models for scientific research calls for the development of new methods to evaluate their fidelity. A natural framework for addressing this problem is two-sample hypothesis testing, namely the task of determining…