324,752 Hits in 8.3 sec

Two-part test of vaccine effect

Zonghui Hu, Michael Proschan
2015 Statistics in Medicine  
The weighted twopart test is a combination of two statistics, one on disease incidence and one on disease severity.  ...  Though motivated by vaccine studies, the proposed tests apply to any trials that involve both a binary and a continuous outcome for evaluating treatment effect.  ...  The two-tailed p-values for Fisher's exact test, Lachenbruch's test, and the optimal weighted combination test are 0.48, 0.72, and 0.87, respectively.  ... 
doi:10.1002/sim.6412 pmid:25630496 pmcid:PMC4393783 fatcat:qk5h25s6cnbxbf3kuqtoyok77q

Combining density forecasts

Stephen G. Hall, James Mitchell
2007 International Journal of Forecasting  
It proposes a simple data-driven approach to direct combination of density forecasts using "optimal" weights. JEL Classification: C53; E37  ...  This paper brings together two important but hitherto largely unrelated areas of the forecasting literature, density forecasting and forecast combination.  ...  Then define the "optimal" combination weight vector, w, where w = (w 1 , .., w N ), as that w that minimizes the test statistic s(z t ): w = arg min w s(z t ). (2) Minimizing the test statistic over w  ... 
doi:10.1016/j.ijforecast.2006.08.001 fatcat:dtjt7tt2xvgkdorfcl25jwdqky

Optimally weighted Z-test is a powerful method for combining probabilities in meta-analysis

2011 Journal of Evolutionary Biology  
Whitlock demonstrated that a weighted version of the inverse normal method, or "weighted Z-test" is superior to Fisher's method for combining P-values for one-sided T-tests.  ...  Although there is no single approach that is the best in every situation, the weighted Z-test enjoys certain properties that make it an appealing choice as a combination method for meta analysis.  ...  Acknowledgments This research was supported by the Intramural Research Program of the NIH, National Institute of Environmental Health Sciences.  ... 
doi:10.1111/j.1420-9101.2011.02297.x pmid:21605215 pmcid:PMC3135688 fatcat:on2lswir4rfyfp5utr4fce6ygu

Articulating user preferences in many-objective problems by sampling the weighted hypervolume

Anne Auger, Johannes Bader, Dimo Brockhoff, Eckart Zitzler
2009 Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09  
In two previous studies, we addressed both issues independently: a study proposed the weighted hypervolume indicator with which user-defined preferences can be articulated; other studies exist that propose  ...  Here, we combine these two approaches for the first time and extend them, i.e., we present an approach of sampling the weighted hypervolume to incorporate user-defined preferences into the search for problems  ...  To this end, we recall the definition of the weighted hypervolume indicator I w H (A) for a solution set A ⊆ X from [23] : I w H (A) = r l w( z) · αA( z)d z (1) where αA( z) = 1 if f (A) { z} 0 else is  ... 
doi:10.1145/1569901.1569979 dblp:conf/gecco/AugerBBZ09 fatcat:3zxmcisq2fehjhneymazfjukue

Is the weighted z-test the best method for combining probabilities from independent tests?

2011 Journal of Evolutionary Biology  
Through simulation, Whitlock showed that when all the alternatives have the same effect size, the weighted z-test is superior to both unweighted z-test and Fisher's method when combining P-values from  ...  independent studies.  ...  Acknowledgments The author appreciates the comments from Professor Mike Whitlock and Professor Allen Moore. I am also grateful to Professor Mohammad H.  ... 
doi:10.1111/j.1420-9101.2010.02226.x pmid:21401770 fatcat:fiwlk6634jgflnh76tepcloham

DAAS: Differentiable Architecture and Augmentation Policy Search [article]

Xiaoxing Wang, Xiangxiang Chu, Junchi Yan, Xiaokang Yang
2022 arXiv   pre-print
Specifically, 1) for the NAS task, we adopt a single-path based differentiable method with Gumbel-softmax reparameterization strategy due to its memory efficiency; 2) for the auto-augmentation task, we  ...  The searched architecture is evaluated by training on datasets with fixed data augmentation policies.  ...  θ, z (i) ; D val ) • ∇ a z (i) Training for Supernet Weights θ Weights for candidate architecture z are directly obtained from the supernet, so we should train supernet weights θ to adapt various architectures  ... 
arXiv:2109.15273v2 fatcat:qvet6o3mqjgr7dtgfjakero3iu

A comparison of missing data methods for hypothesis tests of the treatment effect in substance abuse clinical trials: a Monte-Carlo simulation study

Sarra L Hedden, Robert F Woolson, Robert J Malcolm
2008 Substance Abuse Treatment, Prevention, and Policy  
In this article, we describe several methods of combining data that may be used for testing hypotheses of the treatment effect.  ...  Specifically, power was greatest for the weighted, compared to un-weighted methods, especially for greater missing data percentages.  ...  Acknowledgements The authors would like to acknowledge NIDA 1 R01 DA016368 & NCRR RR01070.  ... 
doi:10.1186/1747-597x-3-13 pmid:18522752 pmcid:PMC2441613 fatcat:a6js7llsmbakzejqirahrbtsm4

Multi-objective design optimization using cascade evolutionary computations

Nikos D. Lagaros, Vagelis Plevris, Manolis Papadrakakis
2005 Computer Methods in Applied Mechanics and Engineering  
The optimum design achieved based on a deterministic formulation is compared, in terms of the optimum weight, the probability of violation of the constraints and the probability of failure, with the optimum  ...  The stochastic finite element problem is solved using the Monte Carlo Simulation method, combined with the Latin Hypercube Sampling technique for improving its computational efficiency.  ...  For the test examples considered in this study, the probability of constraint violation of the DBO designs is computed two orders of magnitude greater than the corresponding probabilities for the RDO designs  ... 
doi:10.1016/j.cma.2004.12.029 fatcat:d7shj5xklfdubk3bgbbvsps6fq

Domain Adaptation Based on Mixture of Latent Words Language Models for Automatic Speech Recognition

Ryo MASUMURA, Taichi ASAMI, Takanobu OBA, Hirokazu MASATAKI, Sumitaka SAKAUCHI, Akinori ITO
2018 IEICE transactions on information and systems  
For the approaches, this paper also describes methods to optimize mixture weights using a validation data set.  ...  The latent variables in the LWLMs are represented as specific words selected from the observed word space, so LWLMs can share a common latent variable space.  ...  The other is LWLM cross-mixture models in which two elements in LWLMs are independently combined with mixture weights.  ... 
doi:10.1587/transinf.2017edp7210 fatcat:s4xkfm27bfaejpdxx64tu2p37a

Ancestral Causal Inference [article]

Sara Magliacane, Tom Claassen, Joris M. Mooij
2017 arXiv   pre-print
Constraint-based causal discovery from limited data is a notoriously difficult challenge due to the many borderline independence test decisions.  ...  Several approaches to improve the reliability of the predictions by exploiting redundancy in the independence information have been proposed recently.  ...  We also thank Sofia Triantafillou for her feedback, especially for pointing out the correct way to read ancestral relations from a PAG.  ... 
arXiv:1606.07035v3 fatcat:dnuf4u3zpnbghphyu5swmxtrtq

Combining Independent Modules to Solve Multiple-choice Synonym and Analogy Problems [article]

Peter D. Turney, Michael L. Littman, Jeffrey Bigham, Victor Shnayder
2003 arXiv   pre-print
This paper examines three merging rules for combining probability distributions: the well known mixture rule, the logarithmic rule, and a novel product rule.  ...  The differences among the three rules are not statistically significant, but it is suggestive that the popular mixture rule is not the best rule for either of the two problems.  ...  Acknowledgments The research was supported in part by a grant from NASA.  ... 
arXiv:cs/0309035v1 fatcat:vhptns225rg4bj56vhy6ky25fm

Inference and sample size calculation for clinical trials with incomplete observations of paired binary outcomes

Song Zhang, Jing Cao, Chul Ahn
2016 Statistics in Medicine  
We propose a hybrid estimator to appropriately account for the mixed nature of observed data: paired outcomes from those who contribute complete pairs of observations and unpaired outcomes from those who  ...  We investigate the estimation of intervention effect and sample size determination for experiments where subjects are supposed to contribute paired binary outcomes with some incomplete observations.  ...  Acknowledgement The work was supported in part by NIH grants 1UL1TR001105, AHRQ grant R24HS22418, CPRIT grants RP110562-C1 and RP120670-C1, and NSF grant IIS-1302497-03.  ... 
doi:10.1002/sim.7168 pmid:27862151 pmcid:PMC5217765 fatcat:honwfilc3jcihbzkkosvgsj2pq

De-anonymizing private data by matching statistics

Jayakrishnan Unnikrishnan, Farid Movahedi Naini
2013 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton)  
Modeling the users' data as i.i.d., we study the composite hypothesis testing problem of identifying the correct matching between the anonymized histograms from the first set and the user data from the  ...  We propose a Generalized Likelihood Ratio Test as a solution to this problem and show that the solution can be identified using a minimum weight matching algorithm on an K × K complete bipartite weighted  ...  ACKNOWLEDGMENTS The authors thank Richard Timsit and Yves Despond for providing us with the EPFL Wi-Fi connection logs, and Elio Abi Karam for his help in the experimental evaluation.  ... 
doi:10.1109/allerton.2013.6736722 dblp:conf/allerton/UnnikrishnanN13 fatcat:x6kurnmg2faddfzuwwb46fzpdq

Optimal Tests for Combining p-Values

Zhongxue Chen
2021 Applied Sciences  
Numeric results from simulation study and real data examples demonstrate that the proposed tests are robust and powerful under many conditions.  ...  An asymptotically and uniformly most powerful p-value combination test based on constrained likelihood ratio test is then studied.  ...  For instance, a larger weight can be assigned to a study with more subjects; hence, in the z test, a p-value from a larger study may receive a greater weight.  ... 
doi:10.3390/app12010322 fatcat:zvcity7f45h2nf2z3oawvugdzi

Linear Combining in Dependent α-Stable Interference

Ce Zheng, Malcolm Egan, Laurent Clavier, Troels Pedersen, Jean-Marie Gorce
2020 ICC 2020 - 2020 IEEE International Conference on Communications (ICC)  
Exploiting this characterization, we derive optimal linear combining weights and an analytical approximation for the bit error rate (BER), accurate for large transmit power.  ...  Under a policy where each interferer independently accesses each band with probability p, we provide an exact characterization of the interference random vector.  ...  The extreme case p → 0 corresponds to independent α-stable interference on each subband, for which optimal linear combining has been studied in [9] , [10] .  ... 
doi:10.1109/icc40277.2020.9148724 dblp:conf/icc/ZhengECPG20 fatcat:b4bnlg47iveqlesbak6hf4kdqy
« Previous Showing results 1 — 15 out of 324,752 results