اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدXorshift1024*, Xorshift1024+, Xorshift128+ and Xoroshiro128+ Fail Statistical Tests for Linearity
44
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
LEcuyer & Simards Big Crush statistical test suite has revealed statistical flaws in many popular random number generators including Marsaglias Xorshift generators. Vigna recently proposed some 64-bit variations on the Xorshift scheme that are further scrambled (i.e., Xorshift1024*, Xorshift1024+, Xorshift128+, Xoroshiro128+). Unlike their unscrambled counterparts, they pass Big Crush when interleaving blocks of 32 bits for each 64-bit word (most significant, least significant, most significant, least significant, etc.). We report that these scrambled generators systematically fail Big Crush---specifically the linear-complexity and matrix-rank tests that detect linearity---when taking the 32 lowest-order bits in reverse order from each 64-bit word.
قيم البحث
اقرأ أيضاً
We apply several statistical estimators to high-resolution N-body simulations of two currently viable cosmological models: a mixed dark matter model, having $Omega_ u=0.2$ contributed by two massive neutrinos (C+2 uDM), and a Cold Dark Matter model w
ith Cosmological Constant (LambdaCDM) with $Omega_0=0.3$ and h=0.7. Our aim is to compare simulated galaxy samples with the Perseus-Pisces redshift survey (PPS). We consider the n-point correlation functions (n=2-4), the N-count probability functions P_N, including the void probability function P_0, and the underdensity probability function U_epsilon (where epsilon fixes the underdensity threshold in percentage of the average). We find that P_0 (for which PPS and CfA2 data agree) and P_1 distinguish efficiently between the models, while U_epsilon is only marginally discriminatory. On the contrary, the reduced skewness and kurtosis are, respectively, S_3simeq 2.2 and S_4simeq 6-7 in all cases, quite independent of the scale, in agreement with hierarchical scaling predictions and estimates based on redshift surveys. Among our results, we emphasize the remarkable agreement between PPS data and C+2 uDM in all the tests performed. In contrast, the above LambdaCDM model has serious difficulties in reproducing observational data if galaxies and matter overdensities are related in a simple way.
We derive general equations for non-linearity corrections and statistical uncertainty (variance) estimates for data acquired with near-infrared detectors employing correlated double sampling, multiple correlated double sampling (Fowler sampling) and
uniformly-spaced continuous readout techniques. We compare our equation for the variance on each pixel associated with Fowler sampling with measurements obtained from data taken with the array installed in the near-infrared cross-dispersed spectrograph (SpeX) at the NASA Infrared Telescope Facility and find that it provides an accurate representation of the empirical results. This comparison also reveals that the read noise associated with a single readout of the SpeX array increases with the number of non-destructive reads, n_r, as n_r^0.16. This implies that the {effective} read noise of a stored image decreases as n_r^-0.34, shallower than the expected rate of n_r^-0.5. The cause of this read noise behavior is uncertain, but may be due to heating of the array as a result of the multiple read outs. Such behavior may be generic to arrays that employ correlated or multiple correlated double sampling readouts.
Bland and Altman plot method is a graphical plot approach that compares related data sets, supporting the eventual replacement of a measurement method for another one. Perhaps due to its graphical easy output it had been widely applied, however often
misinterpreted. We provide three nested tests: accuracy, precision and agreement, as a means to reach statistical support for the equivalence of measurements. These were based on structural regressions added to the method converting it on inferential statistical criteria, verifying mean equality (accuracy), homoscedasticity (precision), and concordance with a bisector line (agreement). A graphical output illustrating these three tests were added to follow Bland and Altmans principles. Five pairs of data sets from previously published articles that applied the Bland and Altmans principles illustrate this statistical approach. In one case it was demonstrated strict equivalence, three cases showed partial equivalence, and there was one case without equivalence. Here we show a statistical approach added to the graphical outputs that turns the Bland-Altman otherwise graphical subjective interpretation into a clear and objective result and with significance value for a reliable and better communicable decision.
A new statistical procedure, based on a modified spline basis, is proposed to identify the linear components in the panel data model with fixed effects. Under some mild assumptions, the proposed procedure is shown to consistently estimate the underly
ing regression function, correctly select the linear components, and effectively conduct the statistical inference. When compared to existing methods for detection of linearity in the panel model, our approach is demonstrated to be theoretically justified as well as practically convenient. We provide a computational algorithm that implements the proposed procedure along with a path-based solution method for linearity detection, which avoids the burden of selecting the tuning parameter for the penalty term. Monte Carlo simulations are conducted to examine the finite sample performance of our proposed procedure with detailed findings that confirm our theoretical results in the paper. Applications to Aggregate Production and Environmental Kuznets Curve data also illustrate the necessity for detecting linearity in the partially linear panel model.
Nonparametric statistical tests are useful procedures that can be applied in a wide range of situations, such as testing randomness or goodness of fit, one-sample, two-sample and multiple-sample analysis, association between bivariate samples or coun
t data analysis. Their use is often preferred to parametric tests due to the fact that they require less restrictive assumptions about the population sampled. In this work, JavaNPST, an open source Java library implementing 40 nonparametric statistical tests, is presented. It can be helpful for programmers and practitioners interested in performing nonparametric statistical analyses, providing a quick and easy way of running these tests directly within any Java code. Some examples of use are also shown, highlighting some of the more remarkable capabilities of the library.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
