Best unbiased estimators for the parameters of a two-parameter Pareto distribution

Summary For a two-parameter Pareto distributionMalik [1970] has shown that the maximum likelihood estimators of the parameters are jointly sufficient. In this article the maximum likelihood estimators are shown to be jointly complete. Furthermore, unbiased estimators for the two parameters are obtained and are shown to be functions of the jointly complete sufficient statistics, thereby establishing them as the best unblased estimators of the two parameters.This research is a part of the first author's Ph.D. dissertation. The authors wish to thank Dr. Kenny S. Crump, for many helpful suggestions and a referee for improvements in the proofs.     

Joint confidence region for the parameters of pareto distribution

The Pareto distribution is commonly used by economists as a model for the distribution of incomes. Separate confidence intervals or approximate confidence intervals for the parameters of Pareto distribution were discussed by some authors. This paper discusses exact joint confidence region for the parameters of Pareto distribution. The method can be used for both complete samples and type II censored samples.     

Afschatting van verdelingen van kwadratische vormen met toepassingen op aanpassingstoetsen voor normaliteit en exponentialiteit

Summary  In this paper a simple approximation is given for the distribution of the quadratic form

being a weighted sum of squares of independent, identically distributed standardized normal variates. Using the formulae, the Monte Carlo results concerning some goodness of fit tests for normality and exponentiality are verified and extended.     

Record values from generalized Pareto distribution and associated inference

In this paper, we derive exact explicit expressions for the single, double, triple and quadruple moments of the upper record values from a generalized Pareto distribution. We then use these expressions to compute the mean, variance, and the coefficients of skewness and kurtosis of certain linear functions of record values. Finally, we develop approximate confidence intervals for the location and scale parameters of the generalized Pareto distribution using the Edgeworth approximation and compare them with the intervals constructed through Monte Carlo simulations. Received: June 1999     

The Pareto optimality distribution

Pareto optimality (sometimes known as Pareto efficiency) is an important notion in social sciences and related areas, see e.g. Klaus (2006), Chun (2005), Hild (2004), Kibris (2003), Nandeibam (2003), Papai (2001), Peris and Sanchez (2001), Brams and Fishburn (2000), Denicolo (1999), Klaus et al. (1998), Peremans et al. (1997), and Vohra (1992). This notion invariably involves the comparison of the utility of one outcome versus another, i.e. the ratio of two utilities or in general the ratio of two random variables. In this note, we derive the exact distribution of the ratio X/(X + Y) when X and Y are Pareto random variables, Pareto distribution being the first and the most popular distribution used in social sciences and related areas.     

On elementary functions of Pareto variables

Pareto variables are widely used. It is useful to be able to obtain the distribution of some simple functions of Pareto variables in a convenient manner. The Mellin transform with its convolution and exponentiation properties is utilized to that end. Specifically, expressions are written for products, quotients, and sums of products of Pareto variables. These include the distribution of the geometric mean and the product of minimum values of Pareto variables.The Office of Naval Research partially supported the work under Contract No. N000-14-75-C-0254.     

A product Pareto distribution

The Pareto distributions are becoming increasing prominent in several applied areas. In this note, a new Pareto distribution is introduced. It takes the form of the product of two Pareto probability density functions. Various structural properties of this distribution are derived, including its cumulative distribution function, moments, mean deviation about the mean, mean deviation about the median, entropy, asymptotic distribution of the extreme order statistics, method of moments estimates, maximum likelihood estimates and the Fisher information matrix. The calculations involve the use of several special functions.     

Understanding the economic determinants of the severity of operational losses: A regularized generalized Pareto regression approach

We investigate a novel database of 10,217 extreme operational losses from the Italian bank UniCredit. Our goal is to shed light on the dependence between the severity distribution of these losses and a set of macroeconomic, financial, and firm‐specific factors. To do so, we use generalized Pareto regression techniques, where both the scale and shape parameters are assumed to be functions of these explanatory variables. We perform the selection of the relevant covariates with a state‐of‐the‐art penalized‐likelihood estimation procedure relying on L₁‐penalty terms. A simulation study indicates that this approach efficiently selects covariates of interest and tackles spurious regression issues encountered when dealing with integrated time series. Lastly, we illustrate the impact of different economic scenarios on the requested capital for operational risk. Our results have important implications in terms of risk management and regulatory policy.     

On the linear combinations of stochastic variables

Summary In this article we give a general distribution of the linear combinations of independent non-negative stochastic variables. This result generalizes a class of distributions of the linear combinations of independent non-negative variates and further a number of other particular cases can be obtained from the general distribution discussed in this article. In deriving the general distribution we used the properties of the most generalized special function, namely, the H-function ofFox [1961] andBraaksma [1964].     

Record values of the Lomax distribution

In this paper, firstly an introduction to the idea of record values for a sequence of independent and identically (Lomax or Pareto II) distributed random variables is given. Some of the distributional properties of these record values and moments up to second order are derived. These moments clearly depend on the location, scale and shape parameter of the Lomax distribution and two types of estlmators of these parameters, based on a series of observed record values are presented.     

THE USE OF THE LORENZ CURVE AND THE PARETO DISTRIBUTION IN INTERNAL PAY STRUCTURING: A RESEARCH NOTE

This note presents some findings from the early stages of research into the effectiveness of company pay structures. ¹ 1 A two-year project sponsored by the S.S.R.C. The authors gratefully acknowledge the assistance of the S.S.R.C. in this work.
The use of the Lorenz curve as a measure of inequality of distribution of a firm's payroll is described. Values for L, the Lorenz coefficient, are presented for the total payroll of a chemical processing firm and for the earnings of manual workers in a medium-heavy engineering company. The use of the Pareto distribution for management salary structuring is demonstrated. Values for α, the Pareto coefficient, are presented for two chemical companies and two engineering firms. Some possible practical uses for such Lorenz and Pareto values are suggested.     

Instrumental values

This paper studies identification of partial differences of nonseparable structural functions. A model is defined which admits structural functions exhibiting a degree of monotonicity with respect to a latent variate. The model identifies partial differences when there are instrumental values of covariates over which the latent variate exhibits a local quantile invariance, and a local order condition holds. The result is useful when covariates exhibit discrete variation, as arises often in practice, and when restricting latent variates and covariates to be statistically independent is unpalatable. The results are illustrated with data from the returns-to-schooling study of Angrist and Krueger [1991. Does compulsory schooling attendance affect schooling and earnings? Quarterly Journal of Economics 106, 979–1014].     

Afschatting van verdelingen van kwadratische vormen met toepassingen op aanpassingstoetsen voor normaliteit en exponentialiteit

Summary In this paper a simple approximation is given for the distribution of the quadratic form being a weighted sum of squares of independent, identically distributed standardized normal variates. Using the formulae, the Monte Carlo results concerning some goodness of fit tests for normality and exponentiality are verified and extended.     

The distribution function of a statistic for testing the equality of scale parameters in two gamma populations

Summary The exact distribution function of the ratio of two sums of gamma variates is derived in this paper. The result applies to ratios of quadratic forms and to a statistic used for testing the equality of scale parameters in two gamma populations.     

A note on estimation based on record data

In data-processing standpoint, an efficient algorithm for identifying the minimum value among a set of measurements are record statistics. From a sequence of n independent identically distributed continuous random variables only about log(n) records are expected, so we expect to have little data, hence any prior information is welcome (Houchens, Record value theory and inference, Ph.D. thesis, University of California, Riverside, 1984). In this paper, non-Bayesian and Bayesian estimates are derived for the two parameters of the Exponential distribution based on record statistics with respect to the squared error and Linear-Exponential loss functions and then compared with together. The admissibility of some estimators is discussed.     

Implementation in generalized matching problems

We search for (Nash) implementable solutions on a class of one-to-one matching problems which includes both the housing market (Shapley and Scarf, Journal of Mathematical Economics, 1974, 1, 23–28) and marriage problems (Gale and Shapley, American Mathematical Monthly, 1962, 69, 9–15). We show that the core correspondence is implementable. We show, furthermore, that any solution that is Pareto efficient, individually rational, and implementable is a supersolution of the core correspondence. That is, the core correspondence is the minimal solution that is Pareto efficient, individually rational, and implementable. A corollary of independent interest in the context of the housing market is that the core correspondence is the only single-valued solution that is Pareto efficient, individually rational, and implementable.     

Compound gamma,beta and F distributions

Summary In this paper a compound gamma distribution has been derived by compounding a gamma distribution with another gamma distribution. The resulting compound gamma distribution has been reduced to the Beta distributions of the first kind and the second kind and to theF distribution by suitable transformations. This includes theLomax distribution as a special case which enjoys a useful property. Moment estimators for two of its parameters are explicitly obtained, which tend to a bivariate normal distribution. The paper contains expressions for a bivariate probability density function, its conditional expectation, conditional variance and the product moment correlation coefficient. Finally, all the parameters of the compound gamma distribution are explicitly expressed in terms of the functions of the moments of the functions of random variables in two different ways. This note is based on a technical report prepared by the author while he was with the Procter and Gamble Company.     

Robustness of some non-uniform random variate generators

Often the usefulness of a random variate generator for a distribution is based on the successful generation of independent variates from the uniform distribution. However, no pseudo-random number generator is capable of generating a truly random uniform sequence. As the cost of computations is now dramatically reduced, the computational efficiency should not be the primary criterion in choosing a good generator. Proposed here is a robustness criterion which is designed to study the effect of an imperfect pseudo-random number generator on the accuracy of a random variate generator. In particular, the beta and binomial variate generators are examined for their robustness to the non-uniformity of a pseudo-random number generator.     

A note on characterization by the conditional expectation

Summary Various distributions like exponential, Pareto, power and Burr's distribution are characterized in terms of conditional expectation of a functionh (·) of the absolutely continuous random variable.     

Estimation in the pareto distribution

The unique minimum variance unbiased (UMVU) estimate of the probability distribution function of the Pareto distribution is derived. It is shown that the distribution function and ther ^th moment associated with the UMVU estimate are also UMVU estimators. The p.d.f. and its estimator are compared graphically. An estimate of the 100p ^th percentile is given. It is seen that a function of this estimator has a chi-square distribution.