Multivariate mixture modeling using skew-normal independent distributions

In this paper we consider a flexible class of models, with elements that are finite mixtures of multivariate skew-normal independent distributions. A general EM-type algorithm is employed for iteratively computing parameter estimates and this is discussed with emphasis on finite mixtures of skew-normal, skew-t, skew-slash and skew-contaminated normal distributions. Further, a general information-based method for approximating the asymptotic covariance matrix of the estimates is also presented. The accuracy of the associated estimates and the efficiency of some information criteria are evaluated via simulation studies. Results obtained from the analysis of artificial and real data sets are reported illustrating the usefulness of the proposed methodology. The proposed EM-type algorithm and methods are implemented in the R package mixsmsn.     

hsmm — An R package for analyzing hidden semi-Markov models

Hidden semi-Markov models are a generalization of the well-known hidden Markov model. They allow for a greater flexibility of sojourn time distributions, which implicitly follow a geometric distribution in the case of a hidden Markov chain. The aim of this paper is to describe hsmm, a new software package for the statistical computing environment R. This package allows for the simulation and maximum likelihood estimation of hidden semi-Markov models. The implemented Expectation Maximization algorithm assumes that the time spent in the last visited state is subject to right-censoring. It is therefore not subject to the common limitation that the last visited state terminates at the last observation. Additionally, hsmm permits the user to make inferences about the underlying state sequence via the Viterbi algorithm and smoothing probabilities.     

Generalized linear models with clustered data: Fixed and random effects models

The statistical analysis of mixed effects models for binary and count data is investigated. In the statistical computing environment R, there are a few packages that estimate models of this kind. The package lme4 is a de facto standard for mixed effects models. The package glmmML allows non-normal distributions in the specification of random intercepts. It also allows for the estimation of a fixed effects model, assuming that all cluster intercepts are distinct fixed parameters; moreover, a bootstrapping technique is implemented to replace asymptotic analysis. The random intercepts model is fitted using a maximum likelihood estimator with adaptive Gauss-Hermite and Laplace quadrature approximations of the likelihood function. The fixed effects model is fitted through a profiling approach, which is necessary when the number of clusters is large. In a simulation study, the two approaches are compared. The fixed effects model has severe bias when the mixed effects variance is positive and the number of clusters is large.     

CPMC-Lab: A Matlab package for Constrained Path Monte Carlo calculations

We describe CPMC-Lab, a Matlab program for the constrained-path and phaseless auxiliary-field Monte Carlo methods. These methods have allowed applications ranging from the study of strongly correlated models, such as the Hubbard model, to ab initio calculations in molecules and solids. The present package implements the full ground-state constrained-path Monte Carlo (CPMC) method in Matlab with a graphical interface, using the Hubbard model as an example. The package can perform calculations in finite supercells in any dimensions, under periodic or twist boundary conditions. Importance sampling and all other algorithmic details of a total energy calculation are included and illustrated. This open-source tool allows users to experiment with various model and run parameters and visualize the results. It provides a direct and interactive environment to learn the method and study the code with minimal overhead for setup. Furthermore, the package can be easily generalized for auxiliary-field quantum Monte Carlo (AFQMC) calculations in many other models for correlated electron systems, and can serve as a template for developing a production code for AFQMC total energy calculations in real materials. Several illustrative studies are carried out in one- and two-dimensional lattices on total energy, kinetic energy, potential energy, and charge- and spin-gaps.     

Confidence intervals for median survival time with recurrent event data

Several methods of constructing confidence intervals for the median survival time of a recurrent event data are developed. One of them is based on asymptotic variances estimated using some transformations. Others are based on bootstrap techniques. Two types of recurrent event models are considered: the first one is a model where the inter-event times are independent and identically distributed, and the second one is a model where the inter-event times are associated, with the association arising from a gamma frailty model. Bootstrap and asymptotic confidence intervals are studied through simulation. These methods are applied and compared using two real data sets arising in the biomedical and public health settings, using an available R package. The first example belongs to data from a study concerning small bowel motility where an independent model may be assumed. The second example involves hospital readmissions in patients diagnosed with colorectal cancer. In this example the interoccurrence times are correlated.     

SARAH 4: A tool for (not only SUSY) model builders

We present the new version of the Mathematica package SARAH which provides the same features for a non-supersymmetric model as previous versions for supersymmetric models. This includes an easy and straightforward definition of the model, the calculation of all vertices, mass matrices, tadpole equations, and self-energies. Also the two-loop renormalization group equations for a general gauge theory are now included and have been validated with the independent Python code PyR@TE. Model files for FeynArts, CalcHep/CompHep, WHIZARD and in the UFO format can be written, and source code for SPheno for the calculation of the mass spectrum, a set of precision observables, and the decay widths and branching ratios of all states can be generated. Furthermore, the new version includes routines to output model files for Vevacious for both, supersymmetric and non-supersymmetric, models. Global symmetries are also supported with this version and by linking Susyno the handling of Lie groups has been improved and extended.     

An efficient interface between the solvers of Maxwell’s equations and of the quasilinear kinetic equation for simulations of ion cyclotron heating in tokamak plasmas

Selfconsistent simulations of ion–cyclotron heating of tokamak plasmas require iterating between a solver of the wave equations in toroidal geometry and a solver of the Fokker–Planck equation describing the evolution of the ion distribution functions. A huge amount of information must be exchanged between the two codes at each iteration. For the package TORIC–SSFPQL, we have developed an interface which substantially reduces the CPU and memory requirements for the storage and transmission of these data. We present this interface here, and we take advantage of its efficiency to compare simulations in which the quasilinear diffusion operator in SSFPQL is evaluated superposing the TORIC results for all relevant toroidal modes excited by a given antenna with simulations using the fields of a single “representative” toroidal mode.     

Quantile regression neural networks: Implementation in R and application to precipitation downscaling

The qrnn package for R implements the quantile regression neural network, which is an artificial neural network extension of linear quantile regression. The model formulation follows from previous work on the estimation of censored regression quantiles. The result is a nonparametric, nonlinear model suitable for making probabilistic predictions of mixed discrete-continuous variables like precipitation amounts, wind speeds, or pollutant concentrations, as well as continuous variables. A differentiable approximation to the quantile regression error function is adopted so that gradient-based optimization algorithms can be used to estimate model parameters. Weight penalty and bootstrap aggregation methods are used to avoid overfitting. For convenience, functions for quantile-based probability density, cumulative distribution, and inverse cumulative distribution functions are also provided. Package functions are demonstrated on a simple precipitation downscaling task.     

Learning aspect models with partially labeled data

In this paper, we address the problem of learning aspect models with partially labeled data for the task of document categorization. The motivation of this work is to take advantage of the amount of available unlabeled data together with the set of labeled examples to learn latent models whose structure and underlying hypotheses take more accurately into account the document generation process, compared to other mixture-based generative models. We present one semi-supervised variant of the Probabilistic Latent Semantic Analysis (PLSA) model (Hofmann, 2001). In our approach, we try to capture the possible data mislabeling errors which occur during the training of our model. This is done by iteratively assigning class labels to unlabeled examples using the current aspect model and re-estimating the probabilities of the mislabeling errors. We perform experiments over the 20Newsgroups, WebKB and Reuters document collections, as well as over a real world dataset coming from a Business Group of Xerox and show the effectiveness of our approach compared to a semi-supervised version of Naive Bayes, another semi-supervised version of PLSA and to transductive Support Vector Machines.     

MT: A Mathematica package to compute convolutions

We introduce the Mathematica package MT which can be used to compute, both analytically and numerically, convolutions involving harmonic polylogarithms, polynomials or generalized functions. As applications contributions to next-to-next-to-next-to leading order Higgs boson production and the Drell–Yan process are discussed.     

Novosibirsk hadronic currents for τ→4π channels of τ decay library TAUOLA

The new parameterization of form factors developed for 4π channels of the τ lepton decay and based on Novosibirsk data on e⁺e⁻→4π has been coded in a form suitable for the TAUOLA Monte Carlo package. Comparison with results from TAUOLA using another parameterization, i.e. the CLEO version of 1998 is also included.     

GRACE/SUSY: Automatic generation of tree amplitudes in the minimal supersymmetric standard model

GRACE/SUSY is a program package for generating the tree-level amplitude and evaluating the corresponding cross section of processes of the minimal supersymmetric extension of the standard model (MSSM). The Higgs potential adopted in the system, however, is assumed to have a more general form indicated by the two-Higgs-doublet model. This system is an extension of GRACE for the standard model (SM) of the electroweak and strong interactions. For a given MSSM process the Feynman graphs and amplitudes at tree-level are automatically created. The Monte Carlo phase space integration by means of BASES gives the total and differential cross sections. When combined with SPRING, an event generator, the program package provides us with the simulation of the SUSY particle productions.     

A new R package for Bayesian estimation of multivariate normal mixtures allowing for selection of the number of components and interval-censored data

An R package mixAK is introduced which implements routines for a semiparametric density estimation through normal mixtures using the Markov chain Monte Carlo (MCMC) methodology. Besides producing the MCMC output, the package computes posterior summary statistics for important characteristics of the fitted distribution or computes and visualizes the posterior predictive density. For the estimated models, penalized expected deviance (PED) and deviance information criterion (DIC) is directly computed which allows for a selection of mixture components. Additionally, multivariate right-, left- and interval-censored observations are allowed. For univariate problems, the reversible jump MCMC algorithm has been implemented and can be used for a joint estimation of the mixture parameters and the number of mixture components. The core MCMC routines have been implemented in C++ and linked to R to ensure a reasonable computational speed. We briefly review the implemented algorithms and illustrate the use of the package on three real examples of different complexity.     

Iterative stepwise regression imputation using standard and robust methods

Imputation of missing values is one of the major tasks for data pre-processing in many areas. Whenever imputation of data from official statistics comes into mind, several (additional) challenges almost always arise, like large data sets, data sets consisting of a mixture of different variable types, or data outliers. The aim is to propose an automatic algorithm called IRMI for iterative model-based imputation using robust methods, encountering for the mentioned challenges, and to provide a software tool in R. This algorithm is compared to the algorithm IVEWARE, which is the “recommended software” for imputations in international and national statistical institutions. Using artificial data and real data sets from official statistics and other fields, the advantages of IRMI over IVEWARE-especially with respect to robustness-are demonstrated.     

Lifetime analysis based on the generalized Birnbaum-Saunders distribution

In this paper, we consider a family of generalized Birnbaum-Saunders distributions and present a lifetime analysis based mainly on the hazard function of this model. In addition, we carry out maximum likelihood estimation by using an iterative algorithm, which produces robust estimates. Asymptotic inference is also presented. Next, the quality of the estimation method is examined by means of Monte Carlo simulations. We then provide a practical example to illustrate the obtained results. From this example and based on goodness-of-fit methods, we show that the GBS distribution results in a more appropriate model for modeling fatigue data than other models commonly used to model this type of data. Finally, we estimate the hazard function and the critical point of this function.     

HypExp, a Mathematica package for expanding hypergeometric functions around integer-valued parameters

We present the Mathematica package HypExp which allows to expand hypergeometric functions around integer parameters to arbitrary order. At this, we apply two methods, the first one being based on an integral representation, the second one on the nested sums approach. The expansion works for both symbolic argument z and unit argument. We also implemented new classes of integrals that appear in the first method and that are, in part, yet unknown to Mathematica.

Program summary

Title of program:HypExpCatalogue identifier:ADXF_v1_0Program summary URL:http://cpc.cs.qub.ac.uk/summaries/ADXF_v1_0Program obtainable from: CPC Program Library, Queen's University of Belfast, N. IrelandLicence:noneComputers:Computers running Mathematica under Linux or WindowsOperating system:Linux, WindowsProgram language:MathematicaNo. of bytes in distributed program, including test data, etc.:739 410No. of lines in distributed program, including test data, etc.:89 747Distribution format:tar.gzOther package needed:the package HPL, included in the distributionExternal file required:noneNature of the physical problem:Expansion of hypergeometric functions around integer-valued parameters. These are needed in the context of dimensional regularization for loop and phase space integrals.Method of solution:Algebraic manipulation of nested sums and integral representation.Restrictions on complexity of the problem:Limited by the memory availableTypical running time:Strongly depending on the problem and the availability of libraries.     

An analysis of the parametrization by data driven local coordinates for multivariable linear systems

In this paper, we study a novel parametrization for state-space systems, namely data driven local coordinates (DDLC) which have recently been introduced and applied. Even though DDLC has meanwhile become the default parametrization used in the system identification toolbox of the software package MATLAB, an analysis of properties of DDLC, which are relevant to identification, has not been performed up to now. In this paper, we provide insights into the geometry and topology of the DDLC construction and show a number of results which are important for actual identification such as maximum likelihood-type estimation.     

DIRHB—A relativistic self-consistent mean-field framework for atomic nuclei

The DIRHB package consists of three Fortran computer codes for the calculation of the ground-state properties of even–even atomic nuclei using the framework of relativistic self-consistent mean-field models. Each code corresponds to a particular choice of spatial symmetry: the DIRHBS, DIRHBZ and DIRHBT codes are used to calculate nuclei with spherical symmetry, axially symmetric quadrupole deformation, and triaxial quadrupole shapes, respectively. Reflection symmetry is assumed in all three cases. The latest relativistic nuclear energy density functionals are implemented in the codes, thus enabling efficient and accurate calculations over the entire nuclide chart.