Filters








9,642 Hits in 8.5 sec

Truncation point estimation using multiple replications in parallel

F. Bause, M. Eickhoff
Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693)  
In steady-state simulation the output data of the transient phase often causes a bias in the estimation of the steadystate results. A common advice is to cut off this transient phase.  ...  Finding an appropriate truncation point is a wellknown problem and is still not completely solved. In this paper we consider two algorithms for the determination of the truncation point.  ...  MULTIPLE REPLICATIONS IN PARALLEL LetF j (x|S(0)) denote the empirical CDF of the k values from the independent replications.F j (x|S (0) ) is an estimation of F j (x|S(0)) and, of course, the accuracy  ... 
doi:10.1109/wsc.2003.1261451 dblp:conf/wsc/BauseE03 fatcat:leduam3dh5ectn4aj4z65kj5yy

AutoSimOA: a framework for automated analysis of simulation output

K Hoad, S Robinson, R Davies
2011 Journal of Simulation  
There are two key issues in assuring the accuracy of estimates of performance obtained from a simulation model.  ...  Our Automated Simulation Output Analyser identifies the warm-up period, estimates the number of replications, and/or analyses output from a single run, with the aim of providing the user with accurate  ...  Acknowledgements-This work was part of the Automating Simulation Output Analysis (AutoSimOA) project (http://www.wbs.ac.uk/ go/autosimoa, accessed March 2009) that was funded by the UK Engineering and  ... 
doi:10.1057/jos.2010.22 fatcat:q7ee3f7vynhwvfl5jnqctdmjki

Model-independent comparison of simulation output

Nuno Fachada, Vitor V. Lopes, Rui C. Martins, Agostinho C. Rosa
2017 Simulation modelling practice and theory  
In this paper, we present a model comparison technique, which uses principal component analysis to convert simulation output into a set of linearly uncorrelated statistical measures, analyzable in a consistent  ...  properties of simulation output; and, c) it simplifies the modelers' work, as it can be used directly on simulation outputs.  ...  First, in Section 2, we review commonly used methods for comparing the output of simulation models, as well as previous work on model replication using these methods.  ... 
doi:10.1016/j.simpat.2016.12.013 fatcat:ccsam7gjrzed3k2cjba7muqzqm

Calculation of forensic likelihood ratios: Use of Monte Carlo simulations to compare the output of score-based approaches with true likelihood-ratio values [article]

Geoffrey Stewart Morrison
2016 arXiv   pre-print
Monte Carlo simulations are used to compare the output of these approaches to true likelihood-ratio values calculated on the basis of the distribution specified for a simulated population.  ...  In order for a score-based approach to produce a forensically interpretable likelihood ratio, however, in addition to accounting for the similarity of the questioned sample with respect to the known sample  ...  Note that the output of this procedure has also replicated the asymmetric nature of the true likelihood-ratio values, and on average has resulted in estimates of likelihood-ratio values which are close  ... 
arXiv:1612.08165v1 fatcat:yahnnr7wnrcinkotsjjtmc23mm

Analysis of initial transient deletion for replicated steady-state simulations

Peter W. Glynn, Philip Heidelberger
1991 Operations Research Letters  
The applicability of these results to simultaneously running multiple replications on a highly parallel computer is discussed. simulation; steady-state; initial transient 0167-6377/91/$03.50  ...  To produce intervals with good convergence characteristics, the relative growth rates of the number of replications, the length of each replication, and the deletion period must be controlled.  ...  The resulting estimator then corresponds to a multiple replicate estimator.  ... 
doi:10.1016/0167-6377(91)90020-p fatcat:uc6chiycqndqdksveyi2l4udya

ARD: An automated replication-deletion method for simulation analysis

Emily K. Lada, Anup C. Mokashi, James R. Wilson
2013 2013 Winter Simulations Conference (WSC)  
ARD is an automated replication-deletion procedure for computing point and confidence interval (CI) estimators for the steady-state mean of a simulation-generated output process.  ...  To compensate for skewness in the truncated sample mean for each replication, the CI incorporates a skewness adjustment.  ...  point are used to compute a truncated sample mean X i = (n i − w i ) −1 ∑ n i j=w i +1 X i, j for that replication.  ... 
doi:10.1109/wsc.2013.6721472 dblp:conf/wsc/LadaMW13 fatcat:2p6tqnejfvaavoxayidltrwi54

Pre-processing for approximate Bayesian computation in image analysis

Matthew T. Moores, Christopher C. Drovandi, Kerrie Mengersen, Christian P. Robert
2014 Statistics and computing  
However, the computational cost of these simulations can be prohibitive for high dimensional data. An important example is the Potts model, which is commonly used in image analysis.  ...  Images encountered in real world applications can have millions of pixels, therefore scalability is a major concern.  ...  In particular, we are grateful to D. P. Simpson, A. Mira  ... 
doi:10.1007/s11222-014-9525-6 fatcat:xuvxgpnkjbaslmo6bt4vofdwhy

Output data analysis for simulations

C. Alexopoulos, Seong-Hee Kim
Proceedings of the Winter Simulation Conference  
This paper reviews statistical methods for analyzing output data from computer simulations. First, it focuses on the estimation of steady-state system parameters.  ...  The estimation techniques include the replication/deletion approach, the regenerative method, the batch means method, and the standardized time series method.  ...  For output analysis, there are two types of simulations: Finite-horizon simulations. In this case the simulation starts in a specific state and runs until a terminating event occurs.  ... 
doi:10.1109/wsc.2002.1172872 dblp:conf/wsc/AlexopoulosK02 fatcat:3iu5wxdoezdrjiu5reyvkw5zhi

Uncertainty in the Design Stage of Two-Stage Bayesian Propensity Score Analysis [article]

Shirley Liao, Corwin Zigler
2019 arXiv   pre-print
on how the treatment effect is estimated in the analysis stage.  ...  , and doubly robust estimation) and investigate in a simulation study the impact of statistician choice in PS model and implementation on the degree of between- and within-design variability in the estimated  ...  Simulation data, a simulated set of power plant emission data and code to implement the simulation study and power plant analysis are available at: https://github.com/shirleyxliao/Uncertainty-in-the-Design-Stage-of-Two-Stage-Bayesian-Propensity-Score-Analysis  ... 
arXiv:1809.05038v2 fatcat:mjiiftzdjzgx7n6oaq66lvwygy

DETECTING THE DURATION OF INITIAL TRANSIENT IN STEADY STATE SIMULATION OF ARBITRARY PERFORMANCE MEASURES

Mirko Eickhoff, Don McNickle, Krzysztof Pawlikows
2007 Proceedings of the 2nd International ICST Conference on Performance Evaluation Methodologies and Tools  
However, practically all these methods can only be used in simulations aimed at estimation of mean values.  ...  Many methods have been proposed for deciding the duration of this phase of simulation, to determine a valid truncation point of the transient portion of output data.  ...  We can see that output data analysis based on multiple parallel replications has got properties that make analysis of probability distributions feasible.  ... 
doi:10.4108/valuetools.2007.1937 dblp:conf/valuetools/EickhoffMP07a fatcat:cdg3ddr6orhyholzhw4tl2rxde

Optimal design for correlated processes with input-dependent noise

A. Boukouvalas, D. Cornford, M. Stehlík
2014 Computational Statistics & Data Analysis  
In the case of stochastic simulators, which produce a random output for a given set of model inputs, repeated evaluations are useful, supporting the use of replicate observations in the experimental design  ...  In this 33 paper, we investigate design under ML estimation, with a focus on best learning 34 the model parameters. 35 By utilising asymptotic results of estimators, useful approximations to finite 36  ...  Some authors have suggested using a 20 stochastic algorithm like simulated annealing with multiple restarts to guaran-21 tee robustness [36] or random sampling where an information gain is estimated 22  ... 
doi:10.1016/j.csda.2013.09.024 fatcat:35tgfzkxffh7tptfkb6hjio52m

Minimax Quasi-Bayesian estimation in sparse canonical correlation analysis via a Rayleigh quotient function [article]

Qiuyun Zhu, Yves Atchade
2021 arXiv   pre-print
The estimation of sparse canonical correlation vectors has emerged in recent years as an important but challenging variation of the CCA problem, with widespread applications.  ...  Canonical correlation analysis (CCA) is a popular statistical technique for exploring the relationship between datasets.  ...  Introduction Canonical correlation analysis is a statistical technique -dating back at least to [1] -that is used to maximally correlate multiple datasets for joint analysis.  ... 
arXiv:2010.08627v2 fatcat:r42vna2ybfdkrlwexyb2rl3u2e

Power Analysis of Artificial Selection Experiments Using Efficient Whole Genome Simulation of Quantitative Traits

Darren Kessner, John Novembre
2015 Genetics  
This analysis uses a simulation framework that explicitly models whole genomes of individuals, quantitative traits, and selection based on individual trait values.  ...  Finally, we show that an increase in power is obtained by leveraging founder haplotype information to obtain allele frequency estimates.  ...  size used for haplotype frequency estimation (200 kb in this analysis).  ... 
doi:10.1534/genetics.115.175075 pmid:25672748 pmcid:PMC4391575 fatcat:hriwkvtoo5euzlu2vokozxensy

A Bayesian analysis of multiple-output production frontiers

Carmen Fernández, Gary Koop, Mark Steel
2000 Journal of Econometrics  
In this paper we develop Bayesian tools for estimating multi-output production frontiers in applications where only input and output data are available.  ...  erences from the existing literature, which either assumes a classical econometric perspective with restrictive functional form assumptions, or a non-stochastic approach which directly estimates the output  ...  We would also like to thank Robert Adams, Allen Berger and Robin Sickles for providing the banking data used in this paper.  ... 
doi:10.1016/s0304-4076(99)00074-3 fatcat:5gwm4vjpbzazzb5qlrk46xv5p4

GenoGAM: Genome-wide generalized additive models for ChIP-seq analysis [article]

Georg Stricker, Alexander Engelhardt, Daniel Schulz, Matthias Schmid, Achim Tresch, Julien Gagneur
2016 bioRxiv   pre-print
Here, we present GenoGAM (Genome-wide Generalized Additive Model), which brings the well-established and flexible generalized additive models framework to genomic applications using a data parallelism  ...  Smoothing parameters are objectively estimated from the data by cross-validation, eliminating ad-hoc binning and windowing needed by current approaches.  ...  Acknowledgements We thank Ulrike Gaul, Ulrich Unnerstall and Michael Lidschreiber for fruitful discussions on data analysis, Martin Morgan and Hervé Pagès for support during the implementation of the GenoGAM  ... 
doi:10.1101/047464 fatcat:zzn3ytgqejfs5bvrztdbqlrnyi
« Previous Showing results 1 — 15 out of 9,642 results