Quantile Plots,Partial Orders,and Financial Risk

Quantile-quantile plots are most commonly used to compare the shapes of distributions, but they may also be used in conjunction with partial orders on distributions to compare the level and dispersion of distributions that have different shapes. We discuss several easily recognized patterns in quantile-quantile plots that suffice to demonstrate that one distribution is smaller than another in terms of each of several partial orders. We illustrate with financial applications, proposing a quantile plot for comparing the risks and returns of portfolios of investments. As competing portfolios have distributions that differ in level, dispersion, and shape, it is not sufficient to compare portfolios using measures of location and dispersion, such as expected returns and variances; however, quantile plots, with suitable scaling, do aid in such comparisons. In two plots, we compare specific portfolios to the stock market as a whole, finding these portfolios to have higher returns, greater risks or dispersion, thicker tails than their greater dispersion alone would justify. Nonetheless, investors in these risky portfolios are more than adequately compensated for the risks undertaken.     

Specifications of a continual reassessment method design for phase I trials of combined drugs

In studies of combinations of agents in phase I oncology trials, the dose–toxicity relationship may not be monotone for all combinations, in which case the toxicity probabilities follow a partial order. The continual reassessment method for partial orders (PO‐CRM) is a design for phase I trials of combinations that leans upon identifying possible complete orders associated with the partial order. This article addresses some practical design considerations not previously undertaken when describing the PO‐CRM. We describe an approach in choosing a proper subset of possible orderings, formulated according to the known toxicity relationships within a matrix of combination therapies. Other design issues, such as working model selection and stopping rules, are also discussed. We demonstrate the practical ability of PO‐CRM as a phase I design for combinations through its use in a recent trial designed at the University of Virginia Cancer Center. Copyright © 2013 John Wiley & Sons, Ltd.     

On Estimating The Quantile Function For Distributions Constrained by Star-Shaped Ordering

Consider distributions F and G such that G ^-1 F is star-shaped. In the problem of estimating the quantile functions for lifetime distributions, the estimators developed by Rojo (1998) are compared with the commonly used empirical quantile function. Both the one-sample and the two-sample methods of estimation are considered for a wide class of lifetime distributions. In addition, the behavior of the estimators is examined for star-shaped ordered lifetime distributions of the important class of coherent k- out-of-n reliability systems. Results of a Monte Carlo study are presented which compare the behavior of the new estimators with that of the empirical quantile function interms of bias and mean-squared error. As the behavior of these estimators typically depends on the tail behavior of the underlying distributions, the examples presented here include distributions with short, medium and long tails. A formula for the inverse of the Kaplan-Meier estimator is provided and used to generate the simulations in the case of censored data.     

Kurtosis and spread

An increase in kurtosis is achieved through the location- and scale-free movement of probability mass from the “shoulders” of a distribution into its centre and tails. We introduce a coherent structure of ordering and measures, requiring no symmetry assumption, that represent different formalizations of this movement. For this purpose spread functions and spread-spread plots are defined. The orderings impose growth patterns on the spread-spread plot of the distributions involved, and the weakest involve both a specific scale-matching technique and placement of “shoulders”. The role of existing kurtosis orderings and measures in this general context is identified and examples discussed throughout.     

Quasi-Maximum Likelihood Estimation of GARCH Models With Heavy-Tailed Likelihoods

The non-Gaussian maximum likelihood estimator is frequently used in GARCH models with the intention of capturing heavy-tailed returns. However, unless the parametric likelihood family contains the true likelihood, the estimator is inconsistent due to density misspecification. To correct this bias, we identify an unknown scale parameter η_f that is critical to the identification for consistency and propose a three-step quasi-maximum likelihood procedure with non-Gaussian likelihood functions. This novel approach is consistent and asymptotically normal under weak moment conditions. Moreover, it achieves better efficiency than the Gaussian alternative, particularly when the innovation error has heavy tails. We also summarize and compare the values of the scale parameter and the asymptotic efficiency for estimators based on different choices of likelihood functions with an increasing level of heaviness in the innovation tails. Numerical studies confirm the advantages of the proposed approach.     

Analytical results for IGFR and DRPFR distributions,with actuarial applications

An increasing generalized failure rate of a lifetime X defines an ageing concept, denoted by IGFR. Another notion, denoted by DRPFR, is defined by the decreasingness of the reversed proportional failure rate. In this article, we provide characterizations for both IGFR and DRPFR absolutely continuous lifetimes, based on monotonicity of quotients of probabilistic functionals and a result by Nanda and Shaked (2001 Nanda, A.K., Shaked, M. (2001). The hazard rate and the reversed hazard rate orders, with applications to order statistics. Ann. Inst. Stat. Math. 53:853–864.[Crossref], [Web of Science ®] , [Google Scholar]). We derive the necessary conditions for the IGFR notion, based on stochastic orderings of truncated distributions, and we prove that the product of DRPFR lifetimes is also DRPFR; that the IGFR property is preserved by composition with certain risk aversion utility functions; and that the order statistics and the records (and the subsequent order statistic (record)) are IGFR under suitable assumptions, with similar results for DRPFR lifetimes. Also, we provide sufficient conditions for the hazard rate ordering of products and random products of IGFR lifetimes, and similar results for the reversed hazard rate order and DRPFR lifetimes, with a complementary result for the mean residual life order of random products of two families of IGFR lifetimes, we derive the upper and lower bounds for the cumulative distribution function of the product of IGFR lifetimes, and we provide the lower bounds for the risk function of an IGFR lifetime based on the distribution moments, and these bounds are extended for the product of IGFR lifetimes. We discuss extensively the applications of the results in insurance portfolios.     

Power kurtosis transformations: Definition, properties and ordering

Summary Heavy tail distributions can be generated by applying specific non-linear transformations to a Gaussian random variable. Within this work we introduce power kurtosis transformations which are essentially determined by their generator function. Examples are theH-transformation of Tukey (1960), theK-transformation of MacGillivray and Cannon (1997) and theJ-transformation of Fischer and Klein (2004).Furthermore, we derive a general condition on the generator function which guarantees that the corresponding transformation is actually tail-increasing. In this case the exponent of the power kurtosis transformation can be interpreted as a kurtosis parameter. We also prove that the transformed distributions can be ordered with respect to the partial ordering of van Zwet (1964) for symmetric distributions.     

Improved Ordering Results for Fail-Safe Systems with Exponential Components

Let X_{2: n} and Y_{2: m} be the second order statistics from n independent exponential variables with hazards λ₁, …, λ_n, and an independent exponential sample of size m with hazard change to λ, respectively. When m ? n, we obtain necessary and sufficient conditions for comparing X_{2: n} and Y_{2: m} in mean residual life, dispersive, hazard rate, and likelihood ratio orderings based on some inequalities between λ_i’s and λ. The established results show how one can compare an (n ? 1)-out-of-n system consisting of heterogeneous components with exponential lifetimes with any (m ? 1)-out-of-m system consisting of homogeneous components with exponential lifetimes.     

A specification strategy for order determination in arma models

In this paper a specification strategy is proposed for the determination of the orders in ARMA models. The strategy is based on two newly defined concepts: the q-conditioned partial auto-regressive function and the p-conditioned partial moving average function. These concepts are similar to the generalized partial autocorrelation function which has been recently suggested for order determination. The main difference is that they are defined and employed in connection with an asymptotically efficient estimation method instead of the rather inefficient generalized Yule-Walker method. The specification is performed by using sequential Wald type tests. In contrast to the traditional testing of hypotheses, these tests use critical values which increase with the sample size at an appropriate rate     

Asymptotic Results for Spatial ARMA Models

Causal quadrantal-type spatial ARMA(p, q) models with independent and identically distributed innovations are considered. In order to select the orders (p, q) of these models and estimate their autoregressive parameters, estimators of the autoregressive coefficients, derived from the extended Yule–Walker equations are defined. Consistency and asymptotic normality are obtained for these estimators. Then, spatial ARMA model identification is considered and simulation study is given.     

Skewness by Splitting the Scale Parameter

This article describes a recursive nonparametric estimation for the local partial first derivative of an arbitrary function satisfied some regularity conditions and establishes its consistency and asymptotic normality under the assumption of strong mixing sequence. The proposed estimator is a variable window width version of the Watson-Nadaraya type of derivative estimator. The window width varied as more data points become available enables a recursive algorithm that reduce computational complexity from order N ³ normally required by batch methods for kernel regression to order N ². This approach is computationally simple and attractive from practical viewpoint especially when the situation call for frequent updating of first derivative estimates. For example, maintaining a delta-hedged position of a portfolio of equities with index options is one of many applications of such estimation.     

A bivariate density estimation method based on level crossings

This article introduces a method of nonparametric bivariate density estimation based on a bivariate sample level crossing function, which leads to the construction of a bivariate level crossing empirical distribution function (BLCEDF). An efficiency function for this BLCEDF relative to the classical empirical distribution function (EDF), is derived. The BLCEDF gives more efficient estimates than the EDF in the tails of any underlying continuous distribution, for both small and large sample sizes. On the basis of BLCEDF we define a bivariate level crossing kernel density estimator (BLCKDE) and study its properties. We apply the BLCEDF and BLCKDE for various distributions and provide results of simulations that confirm the theoretical properties. A real-world example is given.     

Some Properties of Order Statistics When the Sample Size Is Random

ABSTRACT

The study of r-out-of-n systems is of utmost importance in reliability theory. In this note, we study closure of different partial orders under the formation of r-out-of-N and (N ? s)-out-of-N systems when the number of components N, forming the system, is a random variable having support {k, k + 1,…}, where k is a fixed positive integer, r ∈ {1,…, k} and s ∈ {0, 1,…, k ? 1}. This generalizes quite a few results already known in the literature. We also study the closure of different partial orders when two systems are formed out of different random number of components.     

Importance sampling with the generalized exponential power density

In this paper, the generalized exponential power (GEP) density is proposed as an importance function in Monte Carlo simulations in the context of estimation of posterior moments of a location parameter. This density is divided in five classes according to its tail behaviour which may be exponential, polynomial or logarithmic. The notion of p-credence is also defined to characterize and to order the tails of a large class of symmetric densities by comparing their tails to those of the GEP density.The choice of the GEP density as an importance function allows us to obtain reliable and effective results when p-credences of the prior and the likelihood are defined, even if there are conflicting sources of information. Characterization of the posterior tails using p-credence can be done. Hence, it is possible to choose parameters of the GEP density in order to have an importance function with slightly heavier tails than the posterior. Simulation of observations from the GEP density is also addressed.     

Semiparametric location mixtures with distinct components

We consider a two-component location mixture model with symmetric components, one of which is assumed to be known, the other is unknown. We show identifiability under assumptions on the tails of the characteristic function for the true underlying mixture, and also construct asymptotically normal estimates. The model is an extension of the contamination model in Bordes et al. [Semiparametric estimation of a two-component mixture model when a component is known, Scand. J. Statist. 33 (2006), pp. 733–752], and also related to a location mixture of one symmetric density as in Bordes et al. [Semiparametric estimation of a two component mixture model, Ann. Statist. 34 (2006), pp. 1204–1232]. We show by simulation that estimating the additional location parameter leads to a slight loss of efficiency as compared with the contamination model.     

Large-Sample Inference for the Epsilon-Skew-t Distribution

The main object of this article is to discuss maximum likelihood inference for the epsilon-skew-t distribution. Special cases of this distribution include the epsilon-skew-Cauchy and the epsilon-skew-normal distributions. We derive the information matrix for the maximum likelihood estimators. The approach is applied to a data set presenting significant amount of skewness and heavy tails. In the application we consider the epsilon-skew-t distribution with known and unknown degrees of freedom parameter, showing great flexibility in adjusting to skew data with heavy tails.     

Precise Large Deviations for Sums of Independent Random Variables with Consistently Varying Tails

In this article, we investigate the precise large deviations for a sum of independent but not identical distributed random variables. {X _n , n ≥ 1} are independent non-negative random variables with distribution functions {F _n , n ≥ 1}. We assume that the average of right tails of distribution functions F _n is equivalent to some distribution function F with consistently varying tails. In applications, we apply our main results to a realistic example (Pareto-type distribution) and obtain a specific result.     

The Effect of Trimming and Normality Assumptions on the Efficiency of the O-BLUE Estimators

The seriousness of trimming samples, and considering the trimmed samples as if they are complete samples of the retained size, from a normal distribution is explored for the parameters of the simple linear regression model. The exact efficiencies of the O-BLUE estimators of the parameters under these conditions are investigated relative to the O-BLUE estimators based upon the trimmed samples from the actual distribution G. Five symmetric distributions are considered. It is found that the overall loss in relative efficiency is quite substantial especially when the true distribution has heavier tails than the normal distribution, and in particular for larger amounts of trimming.     

On mitigating collinearity through mixtures

In linear models having near collinear columns of X, ridge and surrogate estimators often are used to mitigate collinearity. A new class of estimators is based on mixtures, either of X and a design minimal in an ordered class or of the Fisher information and a scalar matrix. Comparisons are drawn among choices for the mixing parameter, and the estimators are found to be admissible relative to ordinary least squares. Case studies demonstrate that selected mixture designs are perturbed from the original design to a lesser extent than are those of the surrogate method, while retaining reasonable efficiency characteristics.     

Testing equality of scale parameters against restricted alternatives for m≥3 gamma distributions with unknown common shape parameter

Shiue and Bain (1983) proposed an approximate F-test for the equality of the scale parameters of two gamma distributions with equal but unknown shape parameters. In this article, we propose a simple procedure to test equality of scale parameters of m≥3 gamma distributions against nonincreasing order. The test is based on Fisher's method of combining p-values. The actual size of the resulting test is investigated through Monte Carlo studies. Also asymptotic results are derived for the nominal test size. These can be used to obtain a test which achieves the desired size. The case of more general partial orders is discussed.