Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userChi-square versus median statistics in SNIa data analysis
341
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
In this paper we compare the performances of the chi-square and median likelihood analysis in the determination of cosmological constraints using type Ia supernovae data. We perform a statistical analysis using the 307 supernovae of the Union 2 compilation of the Supernova Cosmology Project and find that the chi-square statistical analysis yields tighter cosmological constraints than the median statistic if only supernovae data is taken into account. We also show that when additional measurements from the Cosmic Microwave Background and Baryonic Acoustic Oscillations are considered, the combined cosmological constraints are not strongly dependent on whether one applies the chi-square statistic or the median statistic to the supernovae data. This indicates that, when complementary information from other cosmological probes is taken into account, the performances of the chi-square and median statistics are very similar, demonstrating the robustness of the statistical analysis.
rate research
Read More
The median statistic has recently been discussed by Gott textit{et al.} as a more reliable alternative to the standard $chi^2$ likelihood analysis, in the sense of requiring fewer assumptions about the data and being almost as constraining. We apply this statistic to the currently available combined dataset of 92 distant type Ia supernovae, and also to a mock SNAP-class dataset. We find that the performances of the modified median and $chi^2$ statistics are comparable, particularly in the latter case. We further extend the work of Gott textit{et al.} by modifying the median statistic to account for the number and size of sequences of consecutive points above or below the median. We also comment on how the performance of the statistic depends on the choice of free parameters that one is estimating.
We use the Iocco et al. (2015) compilation of 2,780 circular velocity measurements to analyze the Milky Way rotation curve. We find that the error bars for individual measurements are non-gaussian, and hence instead derive median statistics binned central circular velocity values and error bars from these data. We use these median statistics central values and error bars to fit the data to simple, few parameter, rotation curve functions. These simple functions are unable to adequately capture the significant small scale spatial structure in these data and so provide poor fits. We introduce and use the Gaussian Processes (GP) method to capture this small scale structure and use it to derive Milky Way rotation curves from the binned median statistics circular velocity data. The GP method rotation curves have significant small-scale spatial structure superimposed on a broad rise to galactocentric radius $Rapprox7$ kpc and a decline at larger $R$. We use the GP method median statistics rotation curve to measure the Oort $A$ and $B$ constants and other characteristic rotation curve quantities. We study correlations in the residual circular velocities (relative to the GP method rotation curve). Along with other evidence for azimuthal asymmetry of the Milky Way circular rotation velocity field, we find that larger residual circular velocities seem to favor parts of spiral arms.
Unambiguous detection of signals superimposed on unknown trends is difficult for unevenly spaced data. Here, we formulate the Discrete Chi-square Method (DCM) that can determine the best model for many signals superimposed on arbitrary polynomial trends. DCM minimizes the Chi-square for the data in the multi-dimensional tested frequency space. The required number of tested frequency combinations remains manageable, because the method test statistic is symmetric in this tested frequency space. With our known tested constant frequency grid values, the non-linear DCM model becomes linear, and all results become unambiguous. We test DCM with simulated data containing different mixtures of signals and trends. DCM gives unambiguous results, if the signal frequencies are not too close to each other, and none of the signals is too weak. It relies on brute computational force, because all possible free parameter combinations for all reasonable linear models are tested. DCM works like winning a lottery by buying all lottery tickets. Anyone can reproduce all our results with the DCM computer code. All files, variables and other program code related items are printed in magenta colour. Our Appendix gives detailed instructions for using dcm.py. We also present one preliminary real use case, where DCM is applied to the observed (O) minus the computed (C) eclipse epochs of a binary star, XZ And. This DCM analysis reveals evidence for the possible presence of a third and a fourth body in this system. One recent study of a very large sample of binary stars indicated that the probability for detecting a fourth body from the O-C data of eclipsing binaries is only about 0.00005.
We report the results of an 87 square-degree point-source survey centered at R.A. 5h30m, decl. -55 deg. taken with the South Pole Telescope (SPT) at 1.4 and 2.0 mm wavelengths with arc-minute resolution and milli-Jansky depth. Based on the ratio of flux in the two bands, we separate the detected sources into two populations, one consistent with synchrotron emission from active galactic nuclei (AGN) and one consistent with thermal emission from dust. We present source counts for each population from 11 to 640 mJy at 1.4 mm and from 4.4 to 800 mJy at 2.0 mm. The 2.0 mm counts are dominated by synchrotron-dominated sources across our reported flux range; the 1.4 mm counts are dominated by synchroton-dominated sources above ~15 mJy and by dust-dominated sources below that flux level. We detect 141 synchrotron-dominated sources and 47 dust-dominated sources at S/N > 4.5 in at least one band. All of the most significantly detected members of the synchrotron-dominated population are associated with sources in previously published radio catalogs. Some of the dust-dominated sources are associated with nearby (z << 1) galaxies whose dust emission is also detected by the Infrared Astronomy Satellite (IRAS). However, most of the bright, dust-dominated sources have no counterparts in any existing catalogs. We argue that these sources represent the rarest and brightest members of the population commonly referred to as sub-millimeter galaxies (SMGs). Because these sources are selected at longer wavelengths than in typical SMG surveys, they are expected to have a higher mean redshift distribution and may provide a new window on galaxy formation in the early universe.
Distance correlation has gained much recent attention in the data science community: the sample statistic is straightforward to compute and asymptotically equals zero if and only if independence, making it an ideal choice to discover any type of dependency structure given sufficient sample size. One major bottleneck is the testing process: because the null distribution of distance correlation depends on the underlying random variables and metric choice, it typically requires a permutation test to estimate the null and compute the p-value, which is very costly for large amount of data. To overcome the difficulty, in this paper we propose a chi-square test for distance correlation. Method-wise, the chi-square test is non-parametric, extremely fast, and applicable to bias-corrected distance correlation using any strong negative type metric or characteristic kernel. The test exhibits a similar testing power as the standard permutation test, and can be utilized for K-sample and partial testing. Theory-wise, we show that the underlying chi-square distribution well approximates and dominates the limiting null distribution in upper tail, prove the chi-square test can be valid and universally consistent for testing independence, and establish a testing power inequality with respect to the permutation test.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
