The sizes and powers of some stochastic dominance tests: A Monte Carlo study for correlated and heteroskedastic distributions

Testing for stochastic dominance among distributions is an important issue in the study of asset management, income inequality, and market efficiency. This paper conducts Monte Carlo simulations to examine the sizes and powers of several commonly used stochastic dominance tests when the underlying distributions are correlated or heteroskedastic. Our Monte Carlo study shows that the test developed by Davidson and Duclos [R. Davidson, J.Y. Duclos, Statistical inference for stochastic dominance and for the measurement of poverty and inequality, Econometrica 68 (6) (2000) 1435–1464] has better size and power performances than two alternative tests developed by Kaur et al. [A. Kaur, B.L.S.P. Rao, H. Singh, Testing for second order stochastic dominance of two distributions, Econ. Theory 10 (1994) 849–866] and Anderson [G. Anderson, Nonparametric tests of stochastic dominance in income distributions, Econometrica 64 (1996) 1183–1193]. In addition, we find that when the underlying distributions are heteroskedastic, both the size and power of the test developed by Davidson and Duclos [R. Davidson, J.Y. Duclos, Statistical inference for stochastic dominance and for the measurement of poverty and inequality, Econometrica 68 (6) (2000) 1435–1464] are superior to those of the two alternative tests.     

The role of “leads” in the dynamic OLS estimation of cointegrating regression models

In this paper, we consider the role of “leads” of the first difference of integrated variables in the dynamic OLS estimation of cointegrating regression models. Specifically, we investigate Stock and Watson’s [J.H. Stock, M.W. Watson’s, A simple estimator of cointegrating vectors in higher order integrated systems, Econometrica 61 (1993) 783–820] claim that the role of leads is related to the concept of Granger causality by a Monte Carlo simulation. From the simulation results, we find that the dynamic OLS estimator without leads substantially outperforms that with leads and lags; we therefore recommend testing for Granger non-causality before estimating models.     

Learning attribute-efficiently with corrupt oracles

We study learning in a modified EXACT model, where the oracles are corrupt and only few of the presented attributes are relevant. Both modifications were already studied in the literature [Dana Angluin, Mārti?š Krikis, Learning with malicious membership queries and exceptions (extended abstract), in: COLT ’94: Proceedings of the Seventh Annual Conference on Computational Learning Theory, ACM Press, 1994, pp. 56–57 [3]; Dana Angluin, Mārti?š Krikis, Robert H. Sloan, György Turán, Malicious omissions and errors in answers to membership queries, Machine Learning 28 (1997) 211–255; Laurence Bisht, Nader H. Bshouty, Lawrance Khoury, Learning with errors in answers to membership queries (extracted abstract), in: FOCS ’04: Proceedings of the 45th Annual IEEE Symposium on Foundations of Computer Science, FOCS’04, IEEE Computer Society, 2004, pp. 611–620; Nader H. Bshouty, Lisa Hellerstein, Attribute-efficient learning in query and mistake-bound models, J. Comput. System Sci. 56 (3) (1998) 310–319 [12]; Nick Littlestone, Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm, Machine Learning 2 (4) (1988) 285–318; Robert H. Sloan, Gyorgy Turan, Learning with queries but incomplete information (extended abstract), in: COLT ’94: Proceedings of the Seventh Annual Conference on Computational Learning Theory, ACM Press, 1994, pp. 237–245 [5]], and efficient solutions were found to most of their variants. Nonetheless, their reasonable combination is yet to be studied, and integrating the existing solutions either fails or works with a complexity that can be significantly improved. In this paper we prove the equivalence of EXACT learning attribute-efficiently with and without corrupt oracles. For each of the possible scenarios we describe a generic scheme that enables learning in these cases using modifications of the standard learning algorithms. We also generalize and improve previous non-attribute-efficient algorithms for learning with corrupt oracles.     

DPEMC: A Monte Carlo for double diffraction

We extend the POMWIG Monte Carlo generator developed by B. Cox and J. Forshaw, to include new models of central production through inclusive and exclusive double Pomeron exchange in proton-proton collisions. Double photon exchange processes are described as well, both in proton-proton and heavy-ion collisions. In all contexts, various models have been implemented, allowing for comparisons and uncertainty evaluation and enabling detailed experimental simulations.

Program summary

Title of the program:DPEMC, version 2.4Catalogue identifier: ADVFProgram summary URL:http://cpc.cs.qub.ac.uk/summaries/ADVFProgram obtainable from: CPC Program Library, Queen's University of Belfast, N. IrelandComputer: any computer with the FORTRAN 77 compiler under the UNIX or Linux operating systemsOperating system: UNIX; LinuxProgramming language used: FORTRAN 77High speed storage required:<25 MBNo. of lines in distributed program, including test data, etc.: 71 399No. of bytes in distributed program, including test data, etc.: 639 950Distribution format: tar.gzNature of the physical problem: Proton diffraction at hadron colliders can manifest itself in many forms, and a variety of models exist that attempt to describe it [A. Bialas, P.V. Landshoff, Phys. Lett. B 256 (1991) 540; A. Bialas, W. Szeremeta, Phys. Lett. B 296 (1992) 191; A. Bialas, R.A. Janik, Z. Phys. C 62 (1994) 487; M. Boonekamp, R. Peschanski, C. Royon, Phys. Rev. Lett. 87 (2001) 251806; Nucl. Phys. B 669 (2003) 277; R. Enberg, G. Ingelman, A. Kissavos, N. Timneanu, Phys. Rev. Lett. 89 (2002) 081801; R. Enberg, G. Ingelman, L. Motyka, Phys. Lett. B 524 (2002) 273; R. Enberg, G. Ingelman, N. Timneanu, Phys. Rev. D 67 (2003) 011301; B. Cox, J. Forshaw, Comput. Phys. Comm. 144 (2002) 104; B. Cox, J. Forshaw, B. Heinemann, Phys. Lett. B 540 (2002) 26; V. Khoze, A. Martin, M. Ryskin, Phys. Lett. B 401 (1997) 330; Eur. Phys. J. C 14 (2000) 525; Eur. Phys. J. C 19 (2001) 477; Erratum, Eur. Phys. J. C 20 (2001) 599; Eur. Phys. J. C 23 (2002) 311]. This program implements some of the more significant ones, enabling the simulation of central particle production through color singlet exchange between interacting protons or antiprotons.Method of solution: The Monte Carlo method is used to simulate all elementary 2→2 and 2→1 processes available in HERWIG. The color singlet exchanges implemented in DPEMC are implemented as functions reweighting the photon flux already present in HERWIG.Restriction on the complexity of the problem: The program relying extensively on HERWIG, the limitations are the same as in [G. Marchesini, B.R. Webber, G. Abbiendi, I.G. Knowles, M.H. Seymour, L. Stanco, Comput. Phys. Comm. 67 (1992) 465; G. Corcella, I.G. Knowles, G. Marchesini, S. Moretti, K. Odagiri, P. Richardson, M. Seymour, B. Webber, JHEP 0101 (2001) 010].Typical running time: Approximate times on a 800 MHz Pentium III: 5-20 min per 10 000 unweighted events, depending on the process under consideration.     

A comparable study of image approximations to the reaction field

The recently developed high-order accurate multiple image approximation to the reaction field for a charge inside a dielectric sphere [J. Comput. Phys. 223 (2007) 846-864] is compared favorably to other commonly employed reaction field schemes. These methods are of particular interest because they are useful in the study of biological macromolecules by the Monte Carlo and Molecular Dynamics methods.     

A DAFT DL_POLY distributed memory adaptation of the Smoothed Particle Mesh Ewald method

The Smoothed Particle Mesh Ewald method [U. Essmann, L. Perera, M.L. Berkowtz, T. Darden, H. Lee, L.G. Pedersen, J. Chem. Phys. 103 (1995) 8577] for calculating long ranged forces in molecular simulation has been adapted for the parallel molecular dynamics code DL_POLY_3 [I.T. Todorov, W. Smith, Philos. Trans. Roy. Soc. London 362 (2004) 1835], making use of a novel 3D Fast Fourier Transform (DAFT) [I.J. Bush, The Daresbury Advanced Fourier transform, Daresbury Laboratory, 1999] that perfectly matches the Domain Decomposition (DD) parallelisation strategy [W. Smith, Comput. Phys. Comm. 62 (1991) 229; M.R.S. Pinches, D. Tildesley, W. Smith, Mol. Sim. 6 (1991) 51; D. Rapaport, Comput. Phys. Comm. 62 (1991) 217] of the DL_POLY_3 code. In this article we describe software adaptations undertaken to import this functionality and provide a review of its performance.     

A quadratic identity for the number of perfect matchings of plane graphs

We present a quadratic identity on the number of perfect matchings of plane graphs by the method of graphical condensation, which generalizes the results found by Propp [J. Propp, Generalized domino-shuffling, Theoret. Comput. Sci. 303 (2003) 267–301], Kuo [E.H. Kuo, Applications of graphical condensation for enumerating matchings and tilings, Theoret. Comput. Sci. 319 (2004) 29–57], and Yan, Yeh, and Zhang [W.G. Yan, Y.-N. Yeh, F.J. Zhang, Graphical condensation of plane graphs: A combinatorial approach, Theoret. Comput. Sci. 349 (2005) 452–461].     

Parallel implementation of an efficient preconditioned linear solver for grid-based applications in chemical physics. III: Improved parallel scalability for sparse matrix–vector products

The linear solve problems arising in chemical physics and many other fields involve large sparse matrices with a certain block structure, for which special block Jacobi preconditioners are found to be very efficient. In two previous papers [W. Chen, B. Poirier, Parallel implementation of efficient preconditioned linear solver for grid-based applications in chemical physics. I. Block Jacobi diagonalization, J. Comput. Phys. 219 (1) (2006) 185–197; W. Chen, B. Poirier, Parallel implementation of efficient preconditioned linear solver for grid-based applications in chemical physics. II. QMR linear solver, J. Comput. Phys. 219 (1) (2006) 198–209], a parallel implementation was presented. Excellent parallel scalability was observed for preconditioner construction, but not for the matrix–vector product itself. In this paper, we introduce a new algorithm with (1) greatly improved parallel scalability and (2) generalization for arbitrary number of nodes and data sizes.     

ExHuME 1.3: A Monte Carlo event generator for exclusive diffraction

We have written the Exclusive Hadronic Monte Carlo Event (ExHuME) generator. ExHuME is based around the perturbative QCD calculation of Khoze, Martin and Ryskin of the process pp→p+X+p, where X is a centrally produced colour singlet system.

Program summary

Title of program:ExHuMECatalogue identifier:ADYA_v1_0Program summary URL:http://cpc.cs.qub.ac.uk/summaries/ADYA_v1_0Program obtainable from:CPC Program Library, Queen's University of Belfast, N. IrelandLicensing provisions:NoneProgramming language used:C++, some FORTRANComputer:Any computer with UNIX capability. Users should refer to the README file distributed with the source code for further detailsOperating system:Linux, Mac OS XNo. of lines in distributed program, including test data, etc.:111 145No. of bytes in distributed program, including test data, etc.: 791 085Distribution format:tar.gzRAM:60 MBExternal routines/libraries:LHAPDF [http://durpdg.dur.ac.uk/lhapdf/], CLHEP v1.8 or v1.9 [L. Lönnblad, Comput. Phys. Comm. 84 (1994) 307; http://wwwinfo.cern.ch/asd/lhc++/clhep/]Subprograms used:Pythia [T. Sjostrand et al., Comput. Phys. Comm. 135 (2001) 238], HDECAY [A. Djouadi, J. Kalinowski, M. Spira, HDECAY: A program for Higgs boson decays in the standard model and its supersymmetric extension, Comput. Phys. Comm. 108 (1998) 56, hep-ph/9704448]. Both are distributed with the source codeNature of problem:Central exclusive production offers the opportunity to study particle production in a uniquely clean environment for a hadron collider. This program implements the KMR model [V.A. Khoze, A.D. Martin, M.G. Ryskin, Prospects for New Physics observations in diffractive processes at the LHC and Tevatron, Eur. Phys. J. C 23 (2002) 311, hep-ph/0111078], which is the only fully perturbative model of exclusive production.Solution method:Monte Carlo techniques are used to produce the central exclusive parton level system. Pythia routines are then used to develop a realistic hadronic system.Restrictions:The program is, at present, limited to Higgs, di-gluon and di-quark production. However, in principle it is not difficult to include more.Running time:Approximately 10 minutes for 10000 Higgs events on an Apple 1 GHz G4 PowerPC.     

A thermal lattice Boltzmann model with diffuse scattering boundary condition for micro thermal flows

A lattice Boltzmann model for simulating isothermal micro flows has been proposed by us recently [Niu XD, Chew YT, Shu C. A lattice Boltzmann BGK model for simulation of micro flows. Europhys Lett 2004;67(4):600]. In this paper, we extend the model to simulate the micro thermal flows. In particular, the thermal lattice Boltzmann equation (TLBE) [He X, Chen S, Doolen GD. A novel thermal model for the lattice Boltzmann method in incompressible limit. J Comput Phys 1998;146:282] is used with modification of the relaxation times linking to the Knudsen number. The diffuse scattering boundary condition (DSBC) derived in our early model is extended to consider temperature jump at wall boundaries. Simple theoretical analyses of the DSBC are presented and the results are found to be consistent with the conventional velocity slip and temperature jump boundary conditions. Numerical validations are carried out by simulating two-dimensional thermal Couette flows and developing thermal flows in a microchannel, and the obtained results are found to be in good agreement with those given from the direct simulation Monte Carlo (DSMC), the molecular dynamics (MD) approaches and the Maxwell theoretical prediction.     

Classifying materials in the real world

Classifying materials from their appearance is challenging. Impressive results have been obtained under varying illumination and pose conditions. Still, the effect of scale variations and the possibility to generalise across different material samples are still largely unexplored. This paper (A preliminary version of this work was presented in Hayman et al. [E. Hayman, B. Caputo, M.J. Fritz, J.-O. Eklundh, On the significance of real world conditions for material classification, in: Proceedings of the ECCV, Lecture Notes in Computer Science, vol. 4, Springer, Prague, 2004, pp. 253–266].) addresses these issues, proposing a pure learning approach based on support vector machines. We study the effect of scale variations first on the artificially scaled CUReT database, showing how performance depends on the amount of scale information available during training. Since the CUReT database contains little scale variation and only one sample per material, we introduce a new database containing 10 CUReT materials at different distances, pose and illumination. This database provides scale variations, while allowing to evaluate generalisation capabilities: does training on the CUReT database enable recognition of another piece of sandpaper? Our results demonstrate that this is not yet possible, and that material classification is far from being solved in scenarios of practical interest.     

蒙特卡罗与准蒙特卡罗相互融合的整体光照计算

蒙特卡罗方法具备普适性、鲁棒性以及与问题复杂度无关性等优点，非常适于十分难解的整体光照计算问题，但缺点是生成图像随机噪声大．准蒙特卡罗方法计算连续被积函数低维积分的收敛速度快于蒙特卡罗方法，但不适于直接求解复杂的整体光照计算问题．文中研究蒙特卡罗整体光照计算最根本环节，即随机游动的抽样模式，提出融合蒙特卡罗与准蒙特卡罗的两种通用的新型整体光照计算策略．两种新型策略可以应用于所有基于蒙特卡罗的整体光照算法，不仅能够降低生成图像的随机噪声，而且实现简单、不增加计算和存储开销．     

Embedding a family of disjoint 3D meshes into a crossed cube

Crossed cubes are an important class of hypercube variants. This paper addresses how to embed a family of disjoint 3D meshes into a crossed cube. Two major contributions of this paper are: (1) for n?4, a family of two disjoint 3D meshes of size 2×2×2^n-3 can be embedded in an n-D crossed cube with unit dilation and unit expansion, and (2) for n?6, a family of four disjoint 3D meshes of size 4×2×2^n-5 can be embedded in an n-D crossed cube with unit dilation and unit expansion. These results mean that a family of two or four 3D-mesh-structured parallel algorithms can be executed on a same crossed cube efficiently and in parallel. Our work extends the results recently obtained by Fan and Jia [J. Fan, X. Jia, Embedding meshes into crossed cubes, Information Sciences 177(15) (2007) 3151-3160].     

Yet another improvement over the Mu–Varadharajan e-voting protocol

In this paper we present a fully functional RSA/DSA-based e-voting protocol for online elections that corrects and improves a scheme previously proposed by Lin- Hwang-Chang [I. Lin, M. Hwang, C. Chang, Security enhancement for anonymous secure e-voting over a network, Comput. Stand. Interfaces 25 (2) (2003) 131–139.]. We found that Lin-Hwang-Chang's scheme and a recent modification of it by Hwang-Wen-Hwang [S. Hwang, H. Wen, T. Hwang, On the security enhancement for anonymous secure e-voting over computer network, Comput. Stand. Interfaces 27 (2) (2005) 163–168.] have an important weakness. Moreover, the scheme proposed by Yang-Lin-Yang [C. Yang, C. Lin, H. Yang, Improved anonymous secure e-voting over a network, Information and Security 15 (2) (2004) 185–191.] also suffers from this same problem. We describe in detail our findings and propose a new scheme to overcome the weakness we found in these schemes effectively. Finally, we describe the implementation details of our protocol and present its preliminary performance evaluation.     

Neutrino oscillation parameter sampling with MonteCUBES

We present MonteCUBES (“Monte Carlo Utility Based Experiment Simulator”), a software package designed to sample the neutrino oscillation parameter space through Markov Chain Monte Carlo algorithms. MonteCUBES makes use of the GLoBES software so that the existing experiment definitions for GLoBES, describing long baseline and reactor experiments, can be used with MonteCUBES. MonteCUBES consists of two main parts: The first is a C library, written as a plug-in for GLoBES, implementing the Markov Chain Monte Carlo algorithm to sample the parameter space. The second part is a user-friendly graphical Matlab interface to easily read, analyze, plot and export the results of the parameter space sampling.

Program summary

Program title: MonteCUBES (Monte Carlo Utility Based Experiment Simulator)Catalogue identifier: AEFJ_v1_0Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AEFJ_v1_0.htmlProgram obtainable from: CPC Program Library, Queen's University, Belfast, N. IrelandLicensing provisions: GNU General Public LicenceNo. of lines in distributed program, including test data, etc.: 69 634No. of bytes in distributed program, including test data, etc.: 3 980 776Distribution format: tar.gzProgramming language: CComputer: MonteCUBES builds and installs on 32 bit and 64 bit Linux systems where GLoBES is installedOperating system: 32 bit and 64 bit LinuxRAM: Typically a few MBsClassification: 11.1External routines: GLoBES [1,2] and routines/libraries used by GLoBESSubprograms used:Cat Id ADZI_v1_0, Title GLoBES, Reference CPC 177 (2007) 439Nature of problem: Since neutrino masses do not appear in the standard model of particle physics, many models of neutrino masses also induce other types of new physics, which could affect the outcome of neutrino oscillation experiments. In general, these new physics imply high-dimensional parameter spaces that are difficult to explore using classical methods such as multi-dimensional projections and minimizations, such as those used in GLoBES [1,2].Solution method: MonteCUBES is written as a plug-in to the GLoBES software [1,2] and provides the necessary methods to perform Markov Chain Monte Carlo sampling of the parameter space. This allows an efficient sampling of the parameter space and has a complexity which does not grow exponentially with the parameter space dimension. The integration of the MonteCUBES package with the GLoBES software makes sure that the experimental definitions already in use by the community can also be used with MonteCUBES, while also lowering the learning threshold for users who already know GLoBES.Additional comments: A Matlab GUI for interpretation of results is included in the distribution.Running time: The typical running time varies depending on the dimensionality of the parameter space, the complexity of the experiment, and how well the parameter space should be sampled. The running time for our simulations [3] with 15 free parameters at a Neutrino Factory with O(¹⁰⁶) samples varied from a few hours to tens of hours.References:

[1]

P. Huber, M. Lindner, W. Winter, Comput. Phys. Comm. 167 (2005) 195, hep-ph/0407333.

[2]

P. Huber, J. Kopp, M. Lindner, M. Rolinec, W. Winter, Comput. Phys. Comm. 177 (2007) 432, hep-ph/0701187.

[3]

S. Antusch, M. Blennow, E. Fernandez-Martinez, J. Lopez-Pavon, arXiv:0903.3986 [hep-ph].

     

An analysis of and a comparison between the discontinuous Galerkin and the spectral finite volume methods

The discontinuous Galerkin method has been developed and applied extensively to solve hyperbolic conservation laws in recent years. More recently Wang et al. developed a class of discontinuous Petrov–Galerkin method, termed spectral (finite) volume method [J. Comput. Phys. 78 (2002) 210; J. Comput. Phys. 179 (2002) 665; J. Sci. Comput. 20 (2004) 137]. In this paper we perform a Fourier type analysis on both methods when solving linear one-dimensional conservation laws. A comparison between the two methods is given in terms of accuracy, stability, and convergence. Numerical experiments are performed to validate this analysis and comparison.     

A practical verifiable multi-secret sharing scheme

C.-C. Yang, T.-Y. Chang, M.-S. Hwang [C.-C. Yang, T.-Y. Chang, M.-S. Hwang, A (t,n) multi-secret sharing scheme, Applied Mathematics and Computation 151 (2004) 483–490] proposed an efficient multi-secret sharing scheme based on a two-variable one-way function in 2004. But the scheme doesn't have the property of verification. A practical verifiable multi-secret sharing scheme, which is based on the YCH scheme and the intractability of the discrete logarithm, is proposed in this paper. Our scheme solves the problems in the YCH scheme; each participant chooses her/his own shadow by her/himself, so the system doesn't need a security channel and the cost of the system can be lowered. The scheme can be used in practice widely.     

Monte Carlo simulations of the HP model (the "Ising model" of protein folding)

Using Wang–Landau sampling with suitable Monte Carlo trial moves (pull moves and bond-rebridging moves combined) we have determined the density of states and thermodynamic properties for a short sequence of the HP protein model. For free chains these proteins are known to first undergo a collapse “transition” to a globule state followed by a second “transition” into a native state. When placed in the proximity of an attractive surface, there is a competition between surface adsorption and folding that leads to an intriguing sequence of “transitions”. These transitions depend upon the relative interaction strengths and are largely inaccessible to “standard” Monte Carlo methods.