اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDetection of Periodicity Based on Independence Tests - III. Phase Distance Correlation Periodogram
84
0
0.0
(
0
)
تأليف
Shay Zucker
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
I present the Phase Distance Correlation (PDC) periodogram -- a new periodicity metric, based on the Distance Correlation concept of Gabor Szekely. For each trial period PDC calculates the distance correlation between the data samples and their phases. PDC requires adaptation of the Szekelys distance correlation to circular variables (phases). The resulting periodicity metric is best suited to sparse datasets, and it performs better than other methods for sawtooth-like periodicities. These include Cepheid and RR-Lyrae light curves, as well as radial velocity curves of eccentric spectroscopic binaries. The performance of the PDC periodogram in other contexts is almost as good as that of the Generalized Lomb-Scargle periodogram. The concept of phase distance correlation can be adapted also to astrometric data, and it has the potential to be suitable also for large evenly-spaced datasets, after some algorithmic perfection.
قيم البحث
اقرأ أيضاً
We introduce an improvement to a periodicity metric we have introduced in a previous paper.We improve on the Hoeffding-test periodicity metric, using the Blum-Kiefer-Rosenblatt (BKR) test. Besides a consistent improvement over the Hoeffding-test appr
oach, the BKR approach turns out to perform superbly when applied to very short time series of sawtoothlike shapes. The expected astronomical implications are much more detections of RR-Lyrae stars and Cepheids in sparse photometric databases, and of eccentric Keplerian radial-velocity (RV) curves, such as those of exoplanets in RV surveys.
We introduce and test several novel approaches for periodicity detection in unevenly-spaced sparse datasets. Specifically, we examine five different kinds of periodicity metrics, which are based on non-parametric measures of serial dependence of the
phase-folded data. We test the metrics through simulations in which we assess their performance in various situations, including various periodic signal shapes, different numbers of data points and different signal to noise ratios. One of the periodicity metrics we introduce seems to perform significantly better than the classical ones in some settings of interest to astronomers. We suggest that this periodicity metric - the Hoeffding-test periodicity metric - should be used in addition to the traditional methods, to increase periodicity detection probability.
We discuss methods currently in use for determining the significance of peaks in the periodograms of time series. We discuss some general methods for constructing significance tests, false alarm probability functions, and the role played in these by
independent random variables and by empirical and theoretical cumulative distribution functions. We also discuss the concept of independent frequencies in periodogram analysis. We propose a practical method for estimating the significance of periodogram peaks, applicable to all time series irrespective of the spacing of the data. This method, based on Monte Carlo simulations, produces significance tests that are tailor-made for any given astronomical time series.
We investigate the problem of testing whether $d$ random variables, which may or may not be continuous, are jointly (or mutually) independent. Our method builds on ideas of the two variable Hilbert-Schmidt independence criterion (HSIC) but allows for
an arbitrary number of variables. We embed the $d$-dimensional joint distribution and the product of the marginals into a reproducing kernel Hilbert space and define the $d$-variable Hilbert-Schmidt independence criterion (dHSIC) as the squared distance between the embeddings. In the population case, the value of dHSIC is zero if and only if the $d$ variables are jointly independent, as long as the kernel is characteristic. Based on an empirical estimate of dHSIC, we define three different non-parametric hypothesis tests: a permutation test, a bootstrap test and a test based on a Gamma approximation. We prove that the permutation test achieves the significance level and that the bootstrap test achieves pointwise asymptotic significance level as well as pointwise asymptotic consistency (i.e., it is able to detect any type of fixed dependence in the large sample limit). The Gamma approximation does not come with these guarantees; however, it is computationally very fast and for small $d$, it performs well in practice. Finally, we apply the test to a problem in causal discovery.
This paper introduces a new method named Distance-based Independence Screening for Canonical Analysis (DISCA) to reduce dimensions of two random vectors with arbitrary dimensions. The objective of our method is to identify the low dimensional linear
projections of two random vectors, such that any dimension reduction based on linear projection with lower dimensions will surely affect some dependent structure -- the removed components are not independent. The essence of DISCA is to use the distance correlation to eliminate the redundant dimensions until infeasible. Unlike the existing canonical analysis methods, DISCA does not require the dimensions of the reduced subspaces of the two random vectors to be equal, nor does it require certain distributional assumption on the random vectors. We show that under mild conditions, our approach does undercover the lowest possible linear dependency structures between two random vectors, and our conditions are weaker than some sufficient linear subspace-based methods. Numerically, DISCA is to solve a non-convex optimization problem. We formulate it as a difference-of-convex (DC) optimization problem, and then further adopt the alternating direction method of multipliers (ADMM) on the convex step of the DC algorithms to parallelize/accelerate the computation. Some sufficient linear subspace-based methods use potentially numerically-intensive bootstrap method to determine the dimensions of the reduced subspaces in advance; our method avoids this complexity. In simulations, we present cases that DISCA can solve effectively, while other methods cannot. In both the simulation studies and real data cases, when the other state-of-the-art dimension reduction methods are applicable, we observe that DISCA performs either comparably or better than most of them. Codes and an R package can be found in GitHub https://github.com/ChuanpingYu/DISCA.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
