Understanding a phenomenon from observed data requires contextual and efficient statistical models.Such models are based on probability distributions having sufficiently flexible statistical properties to adapt to a m...Understanding a phenomenon from observed data requires contextual and efficient statistical models.Such models are based on probability distributions having sufficiently flexible statistical properties to adapt to a maximum of situations.Modern examples include the distributions of the truncated Fréchet generated family.In this paper,we go even further by introducing a more general family,based on a truncated version of the generalized Fréchet distribution.This generalization involves a new shape parameter modulating to the extreme some central and dispersion parameters,as well as the skewness and weight of the tails.We also investigate the main functions of the new family,stress-strength parameter,diverse functional series expansions,incomplete moments,various entropy measures,theoretical and practical parameters estimation,bivariate extensions through the use of copulas,and the estimation of the model parameters.By considering a special member of the family having the Weibull distribution as the parent,we fit two data sets of interest,one about waiting times and the other about precipitation.Solid statistical criteria attest that the proposed model is superior over other extended Weibull models,including the one derived to the former truncated Fréchet generated family.展开更多
In the distribution family with common support and the one side truncated distribution family, Bickle, I. A. Ibragimov and R. Z. Hasminskii proved two important convolution theorems. As to the two-side truncated case,...In the distribution family with common support and the one side truncated distribution family, Bickle, I. A. Ibragimov and R. Z. Hasminskii proved two important convolution theorems. As to the two-side truncated case, we also proved a convolution theorem, which plays an extraordinary role in the efficiency theory. In this paper, we will study another kind of two-side truncated distribution family, and prove a convolution result with normal form. On the basis of this convolution result, a new kind of efficiency concept is given; meanwhile, we will show that MLE is an efficient estimate in this distribution family.展开更多
The purpose of this paper is to broaden the knowledge of mean difference and, in particular, of an important distribution model known as truncated normal distribution, which is widely used in applied sciences and econ...The purpose of this paper is to broaden the knowledge of mean difference and, in particular, of an important distribution model known as truncated normal distribution, which is widely used in applied sciences and economics. In this work, we obtained the general formula of mean difference, which is not yet reported in literature, for the aforementioned distribution model and also for particular truncated cases.展开更多
In random network models, sizes for pores and throats are distributed according to a truncated Weibull distribution. As a result, parameters defining the shape of the distribution are critical for the characteristic o...In random network models, sizes for pores and throats are distributed according to a truncated Weibull distribution. As a result, parameters defining the shape of the distribution are critical for the characteristic of the network. In this paper, an algorithm to distribute pores and throats in random network was established to more representatively describe the topology of porous media. First, relations between Weibull parameters and the distribution of dimensionless throat sizes were studied and a series of standard curves were obtained. Then, by analyzing the capillary pressure curve of the core sample, frequency distribution histogram of throat sizes was obtained. All the sizes were transformed to dimensionless numbers ranged from 0 to 1. Curves of the core were compared to the standard curves, and truncated Weibull parameters could be determined according an inverse algorithm. Finally, aspect ratio and average length of throats were adjusted to simultaneously fit the porosity and the capillary pressure curves and the whole network was established. The predicted relative permeability curves were in good agreement with the experimental data of cores, indicating the validity of the algorithm.展开更多
In this paper we propose an absolute error loss EB estimator for parameter of one-side truncation distribution families. Under some conditions we have proved that the convergence rates of its Bayes risk is o, where 0&...In this paper we propose an absolute error loss EB estimator for parameter of one-side truncation distribution families. Under some conditions we have proved that the convergence rates of its Bayes risk is o, where 0<λ,r≤1,Mn≤lnln n (for large n),Mn→∞ as n→∞.展开更多
Truncated elliptical distributions occur naturally in theoretical and applied statistics and are essential for the study of other classes of multivariate distributions.Two members of this class are the multivariate tr...Truncated elliptical distributions occur naturally in theoretical and applied statistics and are essential for the study of other classes of multivariate distributions.Two members of this class are the multivariate truncated normal and multivariate truncated t distributions.We derive statistical properties of the truncated elliptical distributions.Applications of our results establish new properties of the multivariate truncated slash and multivariate truncated power exponential distributions.展开更多
A new expectation-maximization（EM） algorithm is proposed to estimate the parameters of the truncated multinormal distribution with linear restriction on the variables. Compared with the generalized method of moments...A new expectation-maximization（EM） algorithm is proposed to estimate the parameters of the truncated multinormal distribution with linear restriction on the variables. Compared with the generalized method of moments（GMM） estimation and the maximum likelihood estimation（MLE） for the truncated multivariate normal distribution, the EM algorithm features in fast calculation and high accuracy which are shown in the simulation results. For the real data of the national college entrance exams（NCEE）, we estimate the distribution of the NCEE examinees＇ scores in Anhui, 2003, who were admitted to the university of science and technology of China（USTC）. Based on our analysis, we have also given the ratio truncated by the NCEE admission line of USTC in Anhui, 2003.展开更多
An approach is developed to examine the mean and uncertainty of thermal conductivity of a heterogeneous multiparticle system,where the particle concentration or void fraction is treated as a truncated fractal distribu...An approach is developed to examine the mean and uncertainty of thermal conductivity of a heterogeneous multiparticle system,where the particle concentration or void fraction is treated as a truncated fractal distribution.The truncated fractal distribution is then integrated into the Maxwell model,which is equivalent to a cell model in which the multiparticle system is conceptualized as a spherical fluid cell that envelopes a solid particle.The developed mean thermal conductivity is compared with four experimental data sets of liquid-saturated media from the literature.The effect of fractal characteristics is quantified and discussed.Incorporating particle concentration or void fraction truncated fractal distribution can better capture scatters in the experimental results.The thermal conductivity and its standard deviation decrease with increasing fractal dimensions.When the void fraction is truncated fractal,the uncertainty increases mostly in the low mean void fraction range and drops more quickly with the increasing mean void fraction compared to the case where the particle concentration is truncated fractal.In a typical case of multiparticle system when the solid particles are more conductive than the fluid,the faster increase rate of standard deviation with the ratio of solid over fluid conductivities occurs when the mean void fraction is smaller.展开更多
In order to measure the uncertainty of financial asset returns in the stock market, this paper presents a new model, called SV-dt C model, a stochastic volatility(SV) model assuming that the stock return has a doubly ...In order to measure the uncertainty of financial asset returns in the stock market, this paper presents a new model, called SV-dt C model, a stochastic volatility(SV) model assuming that the stock return has a doubly truncated Cauchy distribution, which takes into account the high peak and fat tail of the empirical distribution simultaneously. Under the Bayesian framework, a prior and posterior analysis for the parameters is made and Markov Chain Monte Carlo(MCMC) is used for computing the posterior estimates of the model parameters and forecasting in the empirical application of Shanghai Stock Exchange Composite Index(SSECI) with respect to the proposed SV-dt C model and two classic SV-N(SV model with Normal distribution)and SV-T(SV model with Student-t distribution) models. The empirical analysis shows that the proposed SV-dt C model has better performance by model checking, including independence test(Projection correlation test), Kolmogorov-Smirnov test(K-S test) and Q-Q plot. Additionally, deviance information criterion(DIC) also shows that the proposed model has a significant improvement in model fit over the others.展开更多
Sampling from a truncated multivariate normal distribution （TMVND） constitutes the core computational module in fitting many statistical and econometric models. We propose two efficient methods, an iterative data au...Sampling from a truncated multivariate normal distribution （TMVND） constitutes the core computational module in fitting many statistical and econometric models. We propose two efficient methods, an iterative data augmentation （DA） algorithm and a non-iterative inverse Bayes formulae （IBF） sampler, to simulate TMVND and generalize them to multivariate normal distributions with linear inequality constraints. By creating a Bayesian incomplete-data structure, the posterior step of the DA Mgorithm directly generates random vector draws as opposed to single element draws, resulting obvious computational advantage and easy coding with common statistical software packages such as S-PLUS, MATLAB and GAUSS. Furthermore, the DA provides a ready structure for implementing a fast EM algorithm to identify the mode of TMVND, which has many potential applications in statistical inference of constrained parameter problems. In addition, utilizing this mode as an intermediate result, the IBF sampling provides a novel alternative to Gibbs sampling and elimi- nares problems with convergence and possible slow convergence due to the high correlation between components of a TMVND. The DA algorithm is applied to a linear regression model with constrained parameters and is illustrated with a published data set. Numerical comparisons show that the proposed DA algorithm and IBF sampler are more efficient than the Gibbs sampler and the accept-reject algorithm.展开更多
The Beta Distribution is widely used in engineering and industrial applications. Goodness-of-fit procedures are revisited. Shapiro-Francia statistic is implemented in Beta distribution. A comparative study between the...The Beta Distribution is widely used in engineering and industrial applications. Goodness-of-fit procedures are revisited. Shapiro-Francia statistic is implemented in Beta distribution. A comparative study between the Anderson-Darling, Kolmogorov-Smirnov, Shapiro-Francia, and Chi-square goodness-of-fit test in testing for Beta distribution is performed using simulation.展开更多
To explore experimental quantization of stochastic chaos and exact wave tur-bulence in exponential oscillons,it is necessary to construct smooth random functions of time.In the current paper,we develop a new method of...To explore experimental quantization of stochastic chaos and exact wave tur-bulence in exponential oscillons,it is necessary to construct smooth random functions of time.In the current paper,we develop a new method of modeling stochastic variables described by a closed system of ordinary differential and algebraic equations.Primarily,oscillatory and pulsatory dynamic models pro-duced by the first triplet of copolar elliptic functions are studied from the view-point of the Hamiltonian and Newtonian dynamics.Secondly,the Hamilto-nian systems of the first triplet and the first triplet squared are meticulously investigated in the hyperbolic limit that results in oscillations and pulsations with rectangular and point pulses and a variable period.Thirdly,the relative Hamiltonian systems are used to develop two stochastic models of a random oscillatory cn-noise and a random pulsatory cn2-noise.Numerical experi-ments show that for the Bernoulli frequencies the random oscillatory cn-noise approaches a smooth random oscillatory variable with an unbounded period and the Gaussian probability distribution and the random pulsatory cn2-noise tends to a smooth random pulsatory variable with an unbounded period and the truncated Gaussian probability distribution as the number of elliptic modes approaches infinity.展开更多
This paper presents a stochastic modification of a limited memory BFGS method to solve bound-constrained global minimization problems with a differentiable cost function with no further smoothness. The approach is a s...This paper presents a stochastic modification of a limited memory BFGS method to solve bound-constrained global minimization problems with a differentiable cost function with no further smoothness. The approach is a stochastic descent method where the deterministic sequence, generated by a limited memory BFGS method, is replaced by a sequence of random variables. To enhance the performance of the proposed algorithm and make sure the perturbations lie within the feasible domain, we have developed a novel perturbation technique based on truncating a multivariate double exponential distribution to deal with bound-constrained problems;the theoretical study and the simulation of the developed truncated distribution are also presented. Theoretical results ensure that the proposed method converges almost surely to the global minimum. The performance of the algorithm is demonstrated through numerical experiments on some typical test functions as well as on some further engineering problems. The numerical comparisons with stochastic and meta-heuristic methods indicate that the suggested algorithm is promising.展开更多
Linear regression models for interval-valued data have been widely studied.Most literatures are to split an interval into two real numbers,i.e.,the left-and right-endpoints or the center and radius of this interval,an...Linear regression models for interval-valued data have been widely studied.Most literatures are to split an interval into two real numbers,i.e.,the left-and right-endpoints or the center and radius of this interval,and fit two separate real-valued or two dimension linear regression models.This paper is focused on the bias-corrected and heteroscedasticity-adjusted modeling by imposing order constraint to the endpoints of the response interval and weighted linear least squares with estimated covariance matrix,based on a generalized linear model for interval-valued data.A three step estimation method is proposed.Theoretical conclusions and numerical evaluations show that the proposed estimator has higher efficiency than previous estimators.展开更多
As an integral part of tolerance design in the context of design for six sigma, determining optimal product specifications has become the focus of increased activity, as manufacturing industries strive to increase pro...As an integral part of tolerance design in the context of design for six sigma, determining optimal product specifications has become the focus of increased activity, as manufacturing industries strive to increase productivity and improve the quality of their products. Although a number of research papers have been reported in the research community, there is room for improvement. Most existing research papers consider determining optimal specification limits for a single quality characteristic. In this paper, we develop the modeling and optimization procedures for optimum circular and spherical configurations by considering multiple quality characteristics. The concepts of multivariate quality loss function and truncated distribution are incorporated. This has never been adequately addressed, nor has been appropriately applied in industry. A numerical example is shown and comparison studies are made.展开更多
基金funded by the Deanship of Scientific Research(DSR),King AbdulAziz University,Jeddah,under Grant No.G:531-305-1441.
文摘Understanding a phenomenon from observed data requires contextual and efficient statistical models.Such models are based on probability distributions having sufficiently flexible statistical properties to adapt to a maximum of situations.Modern examples include the distributions of the truncated Fréchet generated family.In this paper,we go even further by introducing a more general family,based on a truncated version of the generalized Fréchet distribution.This generalization involves a new shape parameter modulating to the extreme some central and dispersion parameters,as well as the skewness and weight of the tails.We also investigate the main functions of the new family,stress-strength parameter,diverse functional series expansions,incomplete moments,various entropy measures,theoretical and practical parameters estimation,bivariate extensions through the use of copulas,and the estimation of the model parameters.By considering a special member of the family having the Weibull distribution as the parent,we fit two data sets of interest,one about waiting times and the other about precipitation.Solid statistical criteria attest that the proposed model is superior over other extended Weibull models,including the one derived to the former truncated Fréchet generated family.
基金This research is supported by Youth Science Foundation of Beijing Normal University.
文摘In the distribution family with common support and the one side truncated distribution family, Bickle, I. A. Ibragimov and R. Z. Hasminskii proved two important convolution theorems. As to the two-side truncated case, we also proved a convolution theorem, which plays an extraordinary role in the efficiency theory. In this paper, we will study another kind of two-side truncated distribution family, and prove a convolution result with normal form. On the basis of this convolution result, a new kind of efficiency concept is given; meanwhile, we will show that MLE is an efficient estimate in this distribution family.
文摘The purpose of this paper is to broaden the knowledge of mean difference and, in particular, of an important distribution model known as truncated normal distribution, which is widely used in applied sciences and economics. In this work, we obtained the general formula of mean difference, which is not yet reported in literature, for the aforementioned distribution model and also for particular truncated cases.
文摘In random network models, sizes for pores and throats are distributed according to a truncated Weibull distribution. As a result, parameters defining the shape of the distribution are critical for the characteristic of the network. In this paper, an algorithm to distribute pores and throats in random network was established to more representatively describe the topology of porous media. First, relations between Weibull parameters and the distribution of dimensionless throat sizes were studied and a series of standard curves were obtained. Then, by analyzing the capillary pressure curve of the core sample, frequency distribution histogram of throat sizes was obtained. All the sizes were transformed to dimensionless numbers ranged from 0 to 1. Curves of the core were compared to the standard curves, and truncated Weibull parameters could be determined according an inverse algorithm. Finally, aspect ratio and average length of throats were adjusted to simultaneously fit the porosity and the capillary pressure curves and the whole network was established. The predicted relative permeability curves were in good agreement with the experimental data of cores, indicating the validity of the algorithm.
文摘In this paper we propose an absolute error loss EB estimator for parameter of one-side truncation distribution families. Under some conditions we have proved that the convergence rates of its Bayes risk is o, where 0<λ,r≤1,Mn≤lnln n (for large n),Mn→∞ as n→∞.
基金Conselho Nacional de Desenvolvi-mento Cientifico e Tecnologico-CNPq(Grant No.305963-2018-0).
文摘Truncated elliptical distributions occur naturally in theoretical and applied statistics and are essential for the study of other classes of multivariate distributions.Two members of this class are the multivariate truncated normal and multivariate truncated t distributions.We derive statistical properties of the truncated elliptical distributions.Applications of our results establish new properties of the multivariate truncated slash and multivariate truncated power exponential distributions.
基金Supported by the National Natural Science Foundation(Grant No.11571337,11271347,71172214)
文摘A new expectation-maximization（EM） algorithm is proposed to estimate the parameters of the truncated multinormal distribution with linear restriction on the variables. Compared with the generalized method of moments（GMM） estimation and the maximum likelihood estimation（MLE） for the truncated multivariate normal distribution, the EM algorithm features in fast calculation and high accuracy which are shown in the simulation results. For the real data of the national college entrance exams（NCEE）, we estimate the distribution of the NCEE examinees＇ scores in Anhui, 2003, who were admitted to the university of science and technology of China（USTC）. Based on our analysis, we have also given the ratio truncated by the NCEE admission line of USTC in Anhui, 2003.
文摘An approach is developed to examine the mean and uncertainty of thermal conductivity of a heterogeneous multiparticle system,where the particle concentration or void fraction is treated as a truncated fractal distribution.The truncated fractal distribution is then integrated into the Maxwell model,which is equivalent to a cell model in which the multiparticle system is conceptualized as a spherical fluid cell that envelopes a solid particle.The developed mean thermal conductivity is compared with four experimental data sets of liquid-saturated media from the literature.The effect of fractal characteristics is quantified and discussed.Incorporating particle concentration or void fraction truncated fractal distribution can better capture scatters in the experimental results.The thermal conductivity and its standard deviation decrease with increasing fractal dimensions.When the void fraction is truncated fractal,the uncertainty increases mostly in the low mean void fraction range and drops more quickly with the increasing mean void fraction compared to the case where the particle concentration is truncated fractal.In a typical case of multiparticle system when the solid particles are more conductive than the fluid,the faster increase rate of standard deviation with the ratio of solid over fluid conductivities occurs when the mean void fraction is smaller.
基金supported by the Open Fund of State Key Laboratory of New Metal Materials,Beijing University of Science and Technology (No.2022Z-18)。
文摘In order to measure the uncertainty of financial asset returns in the stock market, this paper presents a new model, called SV-dt C model, a stochastic volatility(SV) model assuming that the stock return has a doubly truncated Cauchy distribution, which takes into account the high peak and fat tail of the empirical distribution simultaneously. Under the Bayesian framework, a prior and posterior analysis for the parameters is made and Markov Chain Monte Carlo(MCMC) is used for computing the posterior estimates of the model parameters and forecasting in the empirical application of Shanghai Stock Exchange Composite Index(SSECI) with respect to the proposed SV-dt C model and two classic SV-N(SV model with Normal distribution)and SV-T(SV model with Student-t distribution) models. The empirical analysis shows that the proposed SV-dt C model has better performance by model checking, including independence test(Projection correlation test), Kolmogorov-Smirnov test(K-S test) and Q-Q plot. Additionally, deviance information criterion(DIC) also shows that the proposed model has a significant improvement in model fit over the others.
基金Supported by the National Social Science Foundation of China (No. 09BTJ012)Scientific Research Fund ofHunan Provincial Education Department (No. 09c390)+1 种基金supported in part by a HKUSeed Funding Program for Basic Research (Project No. 2009-1115-9042)a grant from Hong Kong ResearchGrant Council-General Research Fund (Project No. HKU779210M)
文摘Sampling from a truncated multivariate normal distribution （TMVND） constitutes the core computational module in fitting many statistical and econometric models. We propose two efficient methods, an iterative data augmentation （DA） algorithm and a non-iterative inverse Bayes formulae （IBF） sampler, to simulate TMVND and generalize them to multivariate normal distributions with linear inequality constraints. By creating a Bayesian incomplete-data structure, the posterior step of the DA Mgorithm directly generates random vector draws as opposed to single element draws, resulting obvious computational advantage and easy coding with common statistical software packages such as S-PLUS, MATLAB and GAUSS. Furthermore, the DA provides a ready structure for implementing a fast EM algorithm to identify the mode of TMVND, which has many potential applications in statistical inference of constrained parameter problems. In addition, utilizing this mode as an intermediate result, the IBF sampling provides a novel alternative to Gibbs sampling and elimi- nares problems with convergence and possible slow convergence due to the high correlation between components of a TMVND. The DA algorithm is applied to a linear regression model with constrained parameters and is illustrated with a published data set. Numerical comparisons show that the proposed DA algorithm and IBF sampler are more efficient than the Gibbs sampler and the accept-reject algorithm.
文摘The Beta Distribution is widely used in engineering and industrial applications. Goodness-of-fit procedures are revisited. Shapiro-Francia statistic is implemented in Beta distribution. A comparative study between the Anderson-Darling, Kolmogorov-Smirnov, Shapiro-Francia, and Chi-square goodness-of-fit test in testing for Beta distribution is performed using simulation.
基金The support of CAAM and the University of Mount Saint Vincent is gratefully acknowledged。
文摘To explore experimental quantization of stochastic chaos and exact wave tur-bulence in exponential oscillons,it is necessary to construct smooth random functions of time.In the current paper,we develop a new method of modeling stochastic variables described by a closed system of ordinary differential and algebraic equations.Primarily,oscillatory and pulsatory dynamic models pro-duced by the first triplet of copolar elliptic functions are studied from the view-point of the Hamiltonian and Newtonian dynamics.Secondly,the Hamilto-nian systems of the first triplet and the first triplet squared are meticulously investigated in the hyperbolic limit that results in oscillations and pulsations with rectangular and point pulses and a variable period.Thirdly,the relative Hamiltonian systems are used to develop two stochastic models of a random oscillatory cn-noise and a random pulsatory cn2-noise.Numerical experi-ments show that for the Bernoulli frequencies the random oscillatory cn-noise approaches a smooth random oscillatory variable with an unbounded period and the Gaussian probability distribution and the random pulsatory cn2-noise tends to a smooth random pulsatory variable with an unbounded period and the truncated Gaussian probability distribution as the number of elliptic modes approaches infinity.
文摘This paper presents a stochastic modification of a limited memory BFGS method to solve bound-constrained global minimization problems with a differentiable cost function with no further smoothness. The approach is a stochastic descent method where the deterministic sequence, generated by a limited memory BFGS method, is replaced by a sequence of random variables. To enhance the performance of the proposed algorithm and make sure the perturbations lie within the feasible domain, we have developed a novel perturbation technique based on truncating a multivariate double exponential distribution to deal with bound-constrained problems;the theoretical study and the simulation of the developed truncated distribution are also presented. Theoretical results ensure that the proposed method converges almost surely to the global minimum. The performance of the algorithm is demonstrated through numerical experiments on some typical test functions as well as on some further engineering problems. The numerical comparisons with stochastic and meta-heuristic methods indicate that the suggested algorithm is promising.
基金the National Nature Science Foundation of China under Grant Nos.11571024and 11771032the Humanities and Social Science Foundation of Ministry of Education of China under Grant No.20YJCZH245。
文摘Linear regression models for interval-valued data have been widely studied.Most literatures are to split an interval into two real numbers,i.e.,the left-and right-endpoints or the center and radius of this interval,and fit two separate real-valued or two dimension linear regression models.This paper is focused on the bias-corrected and heteroscedasticity-adjusted modeling by imposing order constraint to the endpoints of the response interval and weighted linear least squares with estimated covariance matrix,based on a generalized linear model for interval-valued data.A three step estimation method is proposed.Theoretical conclusions and numerical evaluations show that the proposed estimator has higher efficiency than previous estimators.
文摘As an integral part of tolerance design in the context of design for six sigma, determining optimal product specifications has become the focus of increased activity, as manufacturing industries strive to increase productivity and improve the quality of their products. Although a number of research papers have been reported in the research community, there is room for improvement. Most existing research papers consider determining optimal specification limits for a single quality characteristic. In this paper, we develop the modeling and optimization procedures for optimum circular and spherical configurations by considering multiple quality characteristics. The concepts of multivariate quality loss function and truncated distribution are incorporated. This has never been adequately addressed, nor has been appropriately applied in industry. A numerical example is shown and comparison studies are made.
