Advantages of variance reduction techniques in establishing confidence intervals for quantiles

Over the past two decades, U.S. nuclear power plant regulation has increasingly depended on best-estimate plus uncertainty safety analyses. As a result of the shift to best-estimate analyses, the distribution of the output metric must be compared against a regulatory goal, rather than a single, conservative value. This comparison has historically been conducted using a 95% one-sided confidence interval for the 0.95-quantile of the output distribution, which is usually found following the technique of simple random sampling using order statistics (SRS-OS). While SRS-OS has certain statistical advantages, there are drawbacks related to the available sampling schemes and the accuracy and precision of the resulting value. Recent work has shown that it is possible to establish asymptotically valid confidence intervals for a quantile of the output of a model simulated using variance reduction techniques (VRTs). These VRTs can provide more informative results than SRS-OS. This work compares SRS-OS and the VRTs of antithetic variates and Latin hypercube sampling through several experiments, designed to replicate conditions found in nuclear safety analyses. This work is designed as an initial investigation into the use of VRTs as a tool to satisfy nuclear regulatory requirements, with hope of expanded analyses of VRTs in the future.

[1]  A. Winsor.  Sampling techniques. , 2000, Nursing times.

[2]  Marvin K. Nakayama.  Asymptotically Valid Confidence Intervals for Quantiles and Values-at-Risk When Applying Latin Hypercube Sampling , 2011 .

[3]  D. M. Rasmuson,et al.  Use of 3/sup n/ parallel flats fractional factorial designs in computer code uncertainty analysis , 1979 .

[4]  Michael Falk,et al.  On the estimation of the quantile density function , 1986 .

[5]  K NakayamaMarvin,et al.  Confidence intervals for quantiles when applying variance-reduction techniques , 2012 .

[6]  M. Stein.  Large sample properties of simulations using latin hypercube sampling , 1987 .

[7]  Eve Bofingeb,et al.  ESTIMATION OF A DENSITY FUNCTION USING ORDER STATISTICS1 , 1975 .

[8]  Attila Guba,et al.  Statistical aspects of best estimate method - I , 2003, Reliab. Eng. Syst. Saf..

[9]  Marvin K. Nakayama.  Asymptotic properties of kernel density estimators when applying importance sampling , 2011, Proceedings of the 2011 Winter Simulation Conference (WSC).

[10]  Luis A. Reyes,et al.  SUBJECT: RISK-INFORMING 10 CFR 50.46, "ACCEPTANCE CRITERIA FOR EMERGENCY CORE COOLING SYSTEMS FOR LIGHT-WATER NUCLEAR POWER REACTORS" , 2004 .

[11]  James R. Wilson,et al.  Correlation-Induction Techniques for Estimating Quantiles in Simulation Experiments , 1998, Oper. Res..

[12]  G. Box,et al.  On the Experimental Attainment of Optimum Conditions , 1951 .

[13]  P. Hall,et al.  On the Distribution of a Studentized Quantile , 1988 .

[14]  Peter W. Glynn,et al.  Stochastic Simulation: Algorithms and Analysis , 2007 .

[15]  A. Saltelli,et al.  Reliability Engineering and System Safety , 2008 .

[16]  R. P. Martin,et al.  AREVA's realistic large break LOCA analysis methodology , 2005 .

[17]  Marvin K. Nakayama,et al.  Confidence intervals for quantiles when applying variance-reduction techniques , 2012, TOMC.

[18]  J. L. Jaech.  On the Use of Tolerance Intervals in Acceptance Sampling by Attributes , 1972 .

[19]  J. Ghosh.  A New Proof of the Bahadur Representation of Quantiles and an Application , 1971 .

[20]  Emanuel Parzen,et al.  Density quantile estimation approach to statistical data modelling , 1979 .

[21]  Joseph L. Gastwirth,et al.  On a Simple Estimate of the Reciprocal of the Density Function , 1968 .

[22]  Abraham Wald,et al.  An Extension of Wilks' Method for Setting Tolerance Limits , 1943 .

[23]  Ing Rj Ser.  Approximation Theorems of Mathematical Statistics , 1980 .

[24]  Jon C. Helton,et al.  Latin Hypercube Sampling and the Propagation of Uncertainty in Analyses of Complex Systems , 2002 .

[25]  M Marconi,et al.  Distribution of Quantiles in Samples from a Bivariate Population , 2010 .

[26]  Cesare Frepoli,et al.  An Overview of Westinghouse Realistic Large Break LOCA Evaluation Model , 2008 .

[27]  Herbert A. David,et al.  Order Statistics , 2011, International Encyclopedia of Statistical Science.

[28]  R. R. Bahadur.  A Note on Quantiles in Large Samples , 1966 .

[29]  Max Henrion,et al.  Uncertainty: A Guide to Dealing with Uncertainty in Quantitative Risk and Policy Analysis , 1990 .

[30]  M. D. McKay,et al.  A comparison of three methods for selecting values of input variables in the analysis of output from a computer code , 2000 .

[31]  M. Makai,et al.  Remarks on statistical aspects of safety analysis of complex systems , 2003, physics/0308086.

[32]  Paul Glasserman,et al.  Monte Carlo Methods in Financial Engineering , 2003 .

[33]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .

[34]  Graham B. Wallis,et al.  Evaluation of nuclear safety from the outputs of computer codes in the presence of uncertainties , 2004, Reliab. Eng. Syst. Saf..

[35]  J. Tukey.  WHICH PART OF THE SAMPLE CONTAINS THE INFORMATION? , 1965, Proceedings of the National Academy of Sciences of the United States of America.