Sampling from multimodal distributions using tempered transitions

I present a new Markov chain sampling method appropriate for distributions with isolated modes. Like the recently developed method of simulated tempering, the tempered transition method uses a series of distributions that interpolate between the distribution of interest and a distribution for which sampling is easier. The new method has the advantage that it does not require approximate values for the normalizing constants of these distributions, which are needed for simulated tempering, and can be tedious to estimate. Simulated tempering performs a random walk along the series of distributions used. In contrast, the tempered transitions of the new method move systematically from the desired distribution, to the easily-sampled distribution, and back to the desired distribution. This systematic movement avoids the inefficiency of a random walk, an advantage that is unfortunately cancelled by an increase in the number of interpolating distributions required. Because of this, the sampling efficiency of the tempered transition method in simple problems is similar to that of simulated tempering. On more complex distributions, however, simulated tempering and tempered transitions may perform differently. Which is better depends on the ways in which the interpolating distributions are deceptive.     

The normal tempered stable regression model

Abstract

This paper deals with the statistical studies of the normal tempered stable model defined by Barndorff-Nielsen and Shephard. It represents the natural extension of the normal inverse Gaussian one introduced by Barndorff-Nielsen. We basically use the Monte-Carlo’s approximation in order to simulate this distribution. We introduce a linear regression model with normal tempered stable error. We apply this model for the analyzing of the daily logarithm returns data on CAC40 index. The parameters estimation results show that this model better deals with long tailed distribution which is the case for the CAC40 logarithm returns.     

A strong convergence to the tempered fractional Brownian motion

In this paper, we give a strong approximation of the tempered fractional Brownian motion via transport processes and derive the rate of convergence.     

Modelling cell generation times by using the tempered stable distribution

Summary.  We show that the family of tempered stable distributions has considerable potential for modelling cell generation time data. Several real examples illustrate how these distributions can improve on currently assumed models, including the gamma and inverse Gaussian distributions which arise as special cases. Our applications concentrate on the generation times of oligodendrocyte progenitor cells and the yeast Saccharomyces cerevisiae . Numerical inversion of the Laplace transform of the probability density function provides fast and accurate approximations to the tempered stable density, for which no closed form generally exists. We also show how the asymptotic population growth rate is easily calculated under a tempered stable model.     

Multi-modal tempered stable distributions and prosses with applications to finance

Abstract

The assumption of underlying return distribution plays an important role in asset pricing models. While the return distribution used in the traditional theories of asset pricing is the unimodal distribution, numerous studies which have investigated the empirical behavior of asset returns in financial markets use multi-modal distribution. We introduce a new parsimonious multi-modal distribution, referred to as the multi-modal tempered stable (MMTS) distribution. In this article we also generate the exponential Lévy market models and derive the value-at-risk (VaR) induced from them. To demonstrate the advantages, we will present the results of the parameter estimation and the VaRs for financial data.     

Fractionally integrated GARCH model with tempered stable distribution: a simulation study

With the growing availability of high-frequency data, long memory has become a popular topic in finance research. Fractionally Integrated GARCH (FIGARCH) model is a standard approach to study the long memory of financial volatility. The original specification of FIGARCH model is developed using Normal distribution, which cannot accommodate fat-tailed properties commonly existing in financial time series. Traditionally, the Student-t distribution and General Error Distribution (GED) are used instead to solve that problem. However, a recent study points out that the Student-t lacks stability. Instead, the Stable distribution is introduced. The issue of this distribution is that its second moment does not exist. To overcome this new problem, the tempered stable distribution, which retains most attractive characteristics of the Stable distribution and has defined moments, is a natural candidate. In this paper, we describe the estimation procedure of the FIGARCH model with tempered stable distribution and conduct a series of simulation studies to demonstrate that it consistently outperforms FIGARCH models with the Normal, Student-t and GED distributions. An empirical evidence of the S&P 500 hourly return is also provided with robust results. Therefore, we argue that the tempered stable distribution could be a widely useful tool for modelling the high-frequency financial volatility in general contexts with a FIGARCH-type specification.     

Tuning Parameter Selection in Penalized Frailty Models

The penalized likelihood approach of Fan and Li (2001 Fan, J., Li, R. (2001). Variable selection via nonconcave penalized likelihood and its oracle properties. Journal of the American Association 96:1348–1360.[Taylor &; Francis Online], [Web of Science ®] , [Google Scholar], 2002 Fan, J., Li, R. (2002). Variable selection for Cox’s proportional hazards model and frailty model. The Annals of Statistics 30:74–99.[Crossref], [Web of Science ®] , [Google Scholar]) differs from the traditional variable selection procedures in that it deletes the non-significant variables by estimating their coefficients as zero. Nevertheless, the desirable performance of this shrinkage methodology relies heavily on an appropriate selection of the tuning parameter which is involved in the penalty functions. In this work, new estimates of the norm of the error are firstly proposed through the use of Kantorovich inequalities and, subsequently, applied to the frailty models framework. These estimates are used in order to derive a tuning parameter selection procedure for penalized frailty models and clustered data. In contrast with the standard methods, the proposed approach does not depend on resampling and therefore results in a considerable gain in computational time. Moreover, it produces improved results. Simulation studies are presented to support theoretical findings and two real medical data sets are analyzed.     

Tuning Parameter Estimation in Penalized Least Squares Methodology

The efficiency of the penalized methods (Fan and Li, 2001 Fan , J. , Li , R. ( 2001 ). Variable selection via nonconcave penalized likelihood and its oracle properties . Journal of the American Statistical Association 96 : 1348 – 1360 .[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) depends strongly on a tuning parameter due to the fact that it controls the extent of penalization. Therefore, it is important to select it appropriately. In general, tuning parameters are chosen by data-driven approaches, such as the commonly used generalized cross validation. In this article, we propose an alternative method for the derivation of the tuning parameter selector in penalized least squares framework, which can lead to an ameliorated estimate. Simulation studies are presented to support theoretical findings and a comparison of the Type I and Type II error rates, considering the L ₁, the hard thresholding and the Smoothly Clipped Absolute Deviation penalty functions, is performed. The results are given in tables and discussion follows.     

Multistate survival models for transitions and reverse transitions: an application to contraceptive use data

This paper extends the use of the multistate proportional hazards model proposed by R. Kay for transitions, reverse transitions, and repeated transitions. A simple method of testing the equality of vectors of parameters for transitions and repeated transitions is also shown in addition to estimates for the underlying cumulative hazards for different types of transition. The multistate survival models applied to contraceptive use data collected by the International Center for Diarrheal Disease Research, Bangladesh, for the period January 1978 to December 1982 provide useful findings relating to interstate transitions. The author stresses the need to not treat separately states of contraceptive use given their link to the acceptance of the first method, transitions from one method to another, first method discontinuation, periods of non-use, the use of subsequent methods, loss to follow-up, the use of irreversible methods, and subsequent periods of non-use. Religion is an important indicator for the acceptance of an irreversible method as a first or subsequent method; compared to women of other religions, Muslims were less likely to accept an irreversible method as a first or subsequent method. Religion is not, however, associated with the acceptance or subsequent use of a reversible method or with discontinuation of a reversible method. Higher age in the study area is associated with both lower acceptance and longer continuation of a method. Women with a larger number of living sons tend to accept their first method and subsequent methods at an higher rate than women with fewer or no sons. As for educational status, women with higher education proved to be serious users of contraception, although women with less or no education tend to accept an irreversible method at an higher rate than the women with an higher level of education. Further, the desire for more children is a strong predictor for non-use of a method even if contraception is used to space births. The score test suggested in the paper for testing the equality of parameters in models 1-4 reveals that there is no significant difference in the parameters of the models. This paper shows that the factors which affect the acceptance of any reversible method of contraception are different from those for an irreversible method. Moreover, the factors which affect a transition differ from those for a reverse transition in the case of adopting reversible methods.     

Unit roots and double smooth transitions

Techniques for testing the null hypothesis of difference stationarity against stationarity around some deterministic function have received much attention. In particular, unit root tests where the alternative is stationarity around a smooth transition in a linear trend have recently been proposed to permit the possibility of non-instantaneous structural change. In this paper we develop tests extending such an approach in order to admit more than one structural change. The analysis is motivated by time series that appear to undergo two smooth transitions in the linear trend, and the application of the new tests to two such series (average global temperature and US consumer prices) highlights the benefits of this double transition extension.     

Tuning parameter selection for a penalized estimator of species richness

Our goal is to estimate the true number of classes in a population, called the species richness. We consider the case where multiple frequency count tables have been collected from a homogeneous population and investigate a penalized maximum likelihood estimator under a negative binomial model. Because high probabilities of unobserved classes increase the variance of species richness estimates, our method penalizes the probability of a class being unobserved. Tuning the penalization parameter is challenging because the true species richness is never known, and so we propose and validate four novel methods for tuning the penalization parameter. We illustrate and contrast the performance of the proposed methods by estimating the strain-level microbial diversity of Lake Champlain over three consecutive years, and global human host-associated species-level microbial richness.     

广义线性模型下ERIC方法的调节参数选择

变量选择是处理高维统计模型的基本方法,在回归模型的变量选择中SCAD惩罚函数不仅可以很好地选择出正确模型,同时还可以对参数进行估计,而且还具有oracle性质,但这些良好的性质是基于选择出一个合适的调节参数。目前国内关于调节参数选择方面大多是对于变量选择问题的研究,针对广义线性模型基于SCAD惩罚使用新方法 ERIC准则进行调节参数的选择,并证明在一定条件下经过该准则选择的模型具有一致性。模拟与实证分析结果表明,ERIC方法在选择调节参数方面优于传统的CV准则、AIC准则和BIC准则。     

Latent class models for ecological inference on voters transitions

This paper introduces some new models of ecological inference within the context of estimation of voter transitions across elections. In particular, we assume that voters of a given party in a given occasion may be split into two latent types: faithful voters, who will certainly vote again for the same party and movers, who will reconsider their choice. Our models allow for unobserved heterogeneity across polling stations both in the weights of the two latent classes within each party and also when modelling the choice of unfaithful voters. Different ways of modelling the unobserved heterogeneity are considered by exploiting properties of the Dirichlet-multinomial distribution and the Brown Payne model of voting transitions can be seen as a special case within the class of models presented here. We discuss pseudo-maximum likelihood estimation and present an application to recent elections in Italy.     

Tuning Parameter Selector for the Penalized Likelihood Method in Multivariate Generalized Linear Models

Variable selection is fundamental to high-dimensional multivariate generalized linear models. The smoothly clipped absolute deviation (SCAD) method can solve the problem of variable selection and estimation. The choice of the tuning parameter in the SCAD method is critical, which controls the complexity of the selected model. This article proposes a criterion to select the tuning parameter for the SCAD method in multivariate generalized linear models, which is shown to be able to identify the true model consistently. Simulation studies are conducted to support theoretical findings, and two real data analysis are given to illustrate the proposed method.     

Computational Method for Jackknifed Generalized Ridge Tuning Parameter based on Generalized Maximum Entropy

In this article, a new method to estimate the Jackknifed generalized ridge tuning parameter, based on the Jackknifed Ridge-trace and an analytical method borrowed from generalized maximum entropy, is presented. The ideas in the article are illustrated and evaluated using to the well-known Portland cement data set and simulations.     

Tuning Parameter Selection in Cox Proportional Hazards Model with a Diverging Number of Parameters

Regularized variable selection is a powerful tool for identifying the true regression model from a large number of candidates by applying penalties to the objective functions. The penalty functions typically involve a tuning parameter that controls the complexity of the selected model. The ability of the regularized variable selection methods to identify the true model critically depends on the correct choice of the tuning parameter. In this study, we develop a consistent tuning parameter selection method for regularized Cox's proportional hazards model with a diverging number of parameters. The tuning parameter is selected by minimizing the generalized information criterion. We prove that, for any penalty that possesses the oracle property, the proposed tuning parameter selection method identifies the true model with probability approaching one as sample size increases. Its finite sample performance is evaluated by simulations. Its practical use is demonstrated in The Cancer Genome Atlas breast cancer data.     

Tuning Parameter Selection and Various Good Fitting Characteristics for the Liu-Type Estimator in Linear Regression

Liu (2003 Liu , K. ( 2003 ). Using Liu-Type estimator to combat collinearity . Commun. Statist. Theor. Meth. 32 ( 5 ): 1009 – 1020 .[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) proposed the Liu-Type estimator (LTE) to combat the well-known multicollinearity problem in linear regression. In this article, various better fitting characteristics of the LTE than those of the ordinary ridge regression estimator (Hoerl and Kennard, 1970 Hoerl , A. E. , Kennard , R. W. ( 1970 ). Ridge regression: Biased estimation for non-orthogonal problems . Technometrics 12 : 55 – 67 .[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) are considered. In particular, we derived two methods to determine the parameter d for the LTE and find that the ridge parameter k could serve for regularization of an ill-conditioned design matrix, while the other parameter d could be used for tuning the fit quality. In addition, the coefficients of regression, coefficient of multiple determination, residual error variance, and generalized cross validation (GCV) of the prediction quality are very stable, and as the ridge parameter increases they eventually reach asymptotic levels, which produces robust regression models. Furthermore, a Monte Carlo evaluation of these features is also given to illustrate some of the theoretical results.     

Monte Carlo integration: An application to labour market states and transitions

This paper is concerned with the application of simulation estimation methods to micro-econometric labour market models. Based on a multi-period probit model for direct job changes and unemployment, estimators for the likelihood of individual employment histories are obtained by Monte Carlo integration and employed in a standard ML-procedure. The results for West German panel data suggest that dynamic effects are largely prevalent on labour markets and that in particular, past unemployment has drastic negative effects on future employment chances. Further, there are no indications that foreigners have a different labour market performance, nor that they are crowding natives out into unemployment.     

Predicting successful and unsuccessful transitions from school to work by using sequence methods

Policy makers recognize the importance of identifying early young people who are likely to end up jobless on entry to the adult labour market. This paper uses sequence techniques to characterize 712 young peoples' transitions from school to work into `types', with jobless types interpreted as unsuccessful transitions. A logit model is estimated for transition type using a collection of static individual, family and school characteristics. This allows us to identify which young people are most likely to experience unsuccessful transitions into the adult labour market. Policy makers might use such information to target social and educational policy more effectively to promote social inclusion.     

A new characterization of the jump rate for piecewise-deterministic Markov processes with discrete transitions

Piecewise-deterministic Markov processes form a general class of non diffusion stochastic models that involve both deterministic trajectories and random jumps at random times. In this paper, we state a new characterization of the jump rate of such a process with discrete transitions. We deduce from this result a non parametric technique for estimating this feature of interest. We state the uniform convergence in probability of the estimator. The methodology is illustrated on a numerical example.