Latent class models for time series analysis

Latent class analysis of time series designed to classify and compare sets of series is discussed. For a particular time series in latent class the data are independently normally distributed with a vector of means, and common variance , that is, . The function of time, , can be represented by a linear combination of low-order splines (piecewise polynomials). The probability density function for the data of a time series is posited to be a finite mixture of spherical multivariate normal densities. The maximum-likelihood function is optimized by means of an EM algorithm. The stability of the estimates is investigated using a bootstrap procedure. Examples of real and artificial data are presented. Copyright © 1999 John Wiley & Sons, Ltd.     

Latent models for cross-covariance

We consider models for the covariance between two blocks of variables. Such models are often used in situations where latent variables are believed to present. In this paper we characterize exactly the set of distributions given by a class of models with one-dimensional latent variables. These models relate two blocks of observed variables, modeling only the cross-covariance matrix. We describe the relation of this model to the singular value decomposition of the cross-covariance matrix. We show that, although the model is underidentified, useful information may be extracted. We further consider an alternative parameterization in which one latent variable is associated with each block, and we extend the result to models with r-dimensional latent variables.     

Latent class analysis variable selection

We propose a method for selecting variables in latent class analysis, which is the most common model-based clustering method for discrete data. The method assesses a variable’s usefulness for clustering by comparing two models, given the clustering variables already selected. In one model the variable contributes information about cluster allocation beyond that contained in the already selected variables, and in the other model it does not. A headlong search algorithm is used to explore the model space and select clustering variables. In simulated datasets we found that the method selected the correct clustering variables, and also led to improvements in classification performance and in accuracy of the choice of the number of classes. In two real datasets, our method discovered the same group structure with fewer variables. In a dataset from the International HapMap Project consisting of 639 single nucleotide polymorphisms (SNPs) from 210 members of different groups, our method discovered the same group structure with a much smaller number of SNPs.     

Completeness theorem for topological class models

A topological class logic is an infinitary logic formed by combining a first-order logic with the quantifier symbols O and C. The meaning of a formula closed by quantifier O is that the set defined by the formula is open. Similarly, a formula closed by quantifier C means that the set is closed. The corresponding models are a topological class spaces introduced by Ćirić and Mijajlović (Math Bakanica 1990). The completeness theorem is proved. This research was supported by the Ministry of Science, Technology and Development, Republic of Serbia, through Mathematical Institute, under grant 144013.     

A class of multivariate skew-normal models

The existing model for multivariate skew normal data does not cohere with the joint distribution of a random sample from a univariate skew normal distribution. This incoherence causes awkward interpretation for data analysis in practice, especially in the development of the sampling distribution theory. In this paper, we propose a refined model that is coherent with the joint distribution of the univariate skew normal random sample, for multivariate skew normal data. The proposed model extends and strengthens the multivariate skew model described in Azzalini (1985,Scandinavian Journal of Statistics,12, 171–178). We present a stochastic representation for the newly proposed model, and discuss a bivariate setting, which confirms that the newly proposed model is more plausible than the one given by Azzalini and Dalla Valle (1996,Biometrika,83, 715–726).     

Latent class model with conditional dependency per modes to cluster categorical data

We propose a parsimonious extension of the classical latent class model to cluster categorical data by relaxing the conditional independence assumption. Under this new mixture model, named conditional modes model (CMM), variables are grouped into conditionally independent blocks. Each block follows a parsimonious multinomial distribution where the few free parameters model the probabilities of the most likely levels, while the remaining probability mass is uniformly spread over the other levels of the block. Thus, when the conditional independence assumption holds, this model defines parsimonious versions of the standard latent class model. Moreover, when this assumption is violated, the proposed model brings out the main intra-class dependencies between variables, summarizing thus each class with relatively few characteristic levels. The model selection is carried out by an hybrid MCMC algorithm that does not require preliminary parameter estimation. Then, the maximum likelihood estimation is performed via an EM algorithm only for the best model. The model properties are illustrated on simulated data and on three real data sets by using the associated R package CoModes. The results show that this model allows to reduce biases involved by the conditional independence assumption while providing meaningful parameters.     

Latent variable models for ordinal data by using the adaptive quadrature approximation

Latent variable models for ordinal data represent a useful tool in different fields of research in which the constructs of interest are not directly observable so that one or more latent variables are required to reduce the complexity of the data. In these cases problems related to the integration of the likelihood function of the model can arise. Indeed analytical solutions do not exist and in presence of several latent variables the most used classical numerical approximation, the Gauss Hermite quadrature, cannot be applied since it requires several quadrature points per dimension in order to obtain quite accurate estimates and hence the computational effort becomes not feasible. Alternative solutions have been proposed in the literature, like the Laplace approximation and the adaptive quadrature. Different studies demonstrated the superiority of the latter method particularly in presence of categorical data. In this work we present a simulation study for evaluating the performance of the adaptive quadrature approximation for a general class of latent variable models for ordinal data under different conditions of study. A real data example is also illustrated.     

On one class of dynamic transportation models

A model is studied that describes the process of good transportation occurring in some technologies. Transportation regimes satisfying a given management system are examined. Such regimes are described by traveling-wave solutions to a nonlinear finite-difference analogue of a parabolic equation. Possible transportation regimes are described, and the stability of stationary regimes is analyzed.     

A class of arbitrage-free log-normal-short-rate two-factor models

An arbitrage-free two-factor model is presented, which is driven by the short rate and the consol yield, and which ensures log-normal short rate and positive rates. The market price of an arbitrary (discrete) set of discount bonds is recovered by construction, and an arbitrary degree of correlation can be accommodated between the long yield and the spread. By virtue of its Markovian nature, the model can be mapped onto a recombining tree, and therefore readily lends itself to the evaluation of American and compound options, which are difficult to evaluate with non-Markovian log-normal forward-rate models such as HJM. Comparison with such a two-factor HJM model has given good agreement in so far as the pricing of one-look triggers is concerned. The calibration to caplets and European swaptions is discussed in detail.     

A class of exactly solvable many-particle models

Conclusions We have found a class of exactly solvable many-particle two-component quantum models with arbitrary form of the two-body interaction for which it is possible to construct exact eigenstates corresponding to a condensate of noninteracting composite particles. The fulfillment of the necessary symmetry conditions between the components means effectively that there are no many-particle correlations in the state with condensate. This can be regarded as the reason why an exact solution is possible. In the case of physical realizations, for which the required properties cannot be satisfied with complete accuracy, our treatment may be helpful as a good initial approximation.Examples of such systems are quasitwo-dimensional electron-hole (and multicomponent electron) systems in a strong magnetic field, when as a result of the action of the field and size quantization the particles have no kinetic energy. There could also be other physical realizations, including discrete models.Scientific-Research Center for Technological Lasers, USSR Academy of Sciences. Translated from Teoreticheskaya i Matematicheskaya Fizika, Vol. 86, No. 1, pp. 98–110, January, 1991.     

A class of models for uncorrelated random variables

We consider the class of multivariate distributions that gives the distribution of the sum of uncorrelated random variables by the product of their marginal distributions. This class is defined by a representation of the assumption of sub-independence, formulated previously in terms of the characteristic function and convolution, as a weaker assumption than independence for derivation of the distribution of the sum of random variables. The new representation is in terms of stochastic equivalence and the class of distributions is referred to as the summable uncorrelated marginals (SUM) distributions. The SUM distributions can be used as models for the joint distribution of uncorrelated random variables, irrespective of the strength of dependence between them. We provide a method for the construction of bivariate SUM distributions through linking any pair of identical symmetric probability density functions. We also give a formula for measuring the strength of dependence of the SUM models. A final result shows that under the condition of positive or negative orthant dependence, the SUM property implies independence.     

Variable selection in a class of single-index models

In this paper we discuss variable selection in a class of single-index models in which we do not assume the error term as additive. Following the idea of sufficient dimension reduction, we first propose a unified method to recover the direction, then reformulate it under the least square framework. Differing from many other existing results associated with nonparametric smoothing methods for density function, the bandwidth selection in our proposed kernel function essentially has no impact on its root-n consistency or asymptotic normality. To select the important predictors, we suggest using the adaptive lasso method which is computationally efficient. Under some regularity conditions, the adaptive lasso method enjoys the oracle property in a general class of single-index models. In addition, the resulting estimation is shown to be asymptotically normal, which enables us to construct a confidence region for the estimated direction. The asymptotic results are augmented through comprehensive simulations, and illustrated by an analysis of air pollution data.     

New features in the class of association models

The most common association models are the U-, R-, C- and RC-models, achieved when only one dimension on the association is considered as significant (M = 1). Whenever more than one dimensions are significant (M > 1), the only kind of association assumed for each dimension is of the RC-type with the exception of Goodman's R + C + RC, R + RC, C + RC, U + RC and R + C models. Extending the idea of U-, R-, and C-models to association models with M > 1, relaxing the equidistance principle for successive categories for the known scores and using orthogonal polynomials, some new models are developed. Two classical sets of data are used to illustrate the advantages of the newly introduced models. Comparisons in terms of chi-square goodness of fit indicate that some of the newly introduced models perform better than the models fitted so far on these data sets. © 1998 John Wiley & Sons, Ltd.     

Notes on a class of one-dimensional Landau-Brazovsky models

In the paper, a class of one-dimensional Landau–Brazovsky models is investigated. We present a sufficient condition under which the corresponding functional achieves its minimum. Moreover, a nonexistence result for nontrivial critical points is given. Project supported by the Doctoral Programme Foundation of the Ministry of Education of China.     

A bootstrap procedure for mixture models: applied to multidimensional scaling latent class models

A bootstrap procedure useful in latent class, or more general mixture models has been developed to determine the sufficient number of latent classes or components required to account for systematic group differences in the data. The procedure is illustrated in the context of a multidimensional scaling latent class model, CLASCAL. Also presented is a bootstrap technique for determining standard errors for estimates of the stimulus co‐ordinates, parameters of the multidimensional scaling model. Real and artificial data are presented. The bootstrap procedure for selecting a sufficient number of classes seems to correctly select the correct number of latent classes at both low and high error levels. At higher error levels it outperforms Hope's (J. Roy. Statist. Soc. Ser B 1968; 30 : 582) procedure. The bootstrap procedures to estimate parameter stability appear to correctly re‐produce Monte Carlo results. Copyright © 2002 John Wiley & Sons, Ltd.     

On a class of stochastic models with two-sided jumps

In this paper a stochastic process involving two-sided jumps and a continuous downward drift is studied. In the context of ruin theory, the model can be interpreted as the surplus process of a business enterprise which is subject to constant expense rate over time along with random gains and losses. On the other hand, such a stochastic process can also be viewed as a queueing system with instantaneous work removals (or negative customers). The key quantity of our interest pertaining to the above model is (a variant of) the Gerber–Shiu expected discounted penalty function (Gerber and Shiu in N. Am. Actuar. J. 2(1):48–72, 1998) from ruin theory context. With the distributions of the jump sizes and their inter-arrival times left arbitrary, the general structure of the Gerber–Shiu function is studied via an underlying ladder height structure and the use of defective renewal equations. The components involved in the defective renewal equations are explicitly identified when the upward jumps follow a combination of exponentials. Applications of the Gerber–Shiu function are illustrated in finding (i) the Laplace transforms of the time of ruin, the time of recovery and the duration of first negative surplus in the ruin context; (ii) the joint Laplace transform of the busy period and the subsequent idle period in the queueing context; and (iii) the expected total discounted reward for a continuous payment stream payable during idle periods in a queue.