On tail estimation: An improved method

  title={On tail estimation: An improved method},
  author={G. R. Dargahi‐Noubary},
  journal={Mathematical Geology},
A step is described toward better statistical treatment of data for tail estimation. The classical extreme value theory together with its practical inefficiency for tail inference are discussed briefly. The threshold method that utilizes available information in a more efficient manner is described, and its relation to extreme value theory is mentioned. Some comparison is also made using two sets of published data. 
Extreme value analysis of diamond-size distributions
Extreme value analysis provides a semiparametric method for analyzing the extreme long tails of skew distributions which may be observed when handling mining data. The estimation of important tailExpand
Bayes Quantile Estimation and Threshold Selection for the Generalized Pareto Family
An interactive program for analyzing observations above a high threshold using parameter estimators which are not too efficient but easy to compute to find the empirical optimal combination choice of threshold and choice of monotone increasing function transformation. Expand
The limiting extremal behaviour of speculative returns: an analysis of intra-daily data from the Frankfurt Stock Exchange
This paper provides a statistical analysis of high-frequency recordings of the German share price index DAX. The data set extends from November 1988 to the end of the year 1995 and includes allExpand
Generalized Maximum Likelihood Pareto‐Poisson estimators for partial duration series
This paper considers use of the generalized Pareto ∥GP) distribution with a Poisson model for arrivals to describe peaks over a threshold. This yields a three-parameter generalized extreme valueExpand
On stochastic comparisons of maximum order statistics from the location-scale family of distributions
We consider the location-scale family of distributions, which contains many standard lifetime distributions. We give conditions under which the largest order statistic of a set of random variablesExpand
Ratio of generalized random variables with application
The generalized Pareto distribution is one of the popular models in the environmental sciences. Scientists in these areas are often interested in comparing the values of an environmental variableExpand
Exponentiated Pareto distributions
Most Pareto distributions are defined on one side of the real line. For wider applicability, we introduce five exponentiated Pareto distributions and derive several of their properties including theExpand
A new probability model with application to heavy-tailed hydrological data
AbstractBecause of the dramatic changes that are being observed in the climatic conditions of the world, such as excess of rains, drought and huge floods, we introduce a versatile hydrologicExpand
Climate Time Series Analysis: Classical Statistical and Bootstrap Methods
Part I: Fundamental Concepts.- 1 Introduction.- 2 Persistence Models.- 3 Bootstrap Confidence Intervals.- Part II: Univariate Time Series.- 4 Regression I.- 5 Spectral Analysis.- 6. Extreme ValueExpand
Extreme Value Time Series
Extreme value time series refer to the outlier component in the climate equation (Eq. 1.2). Quantifying the tail probability of the PDF of a climate variable—the risk of climate extremes—is of highExpand


Modelling Excesses over High Thresholds, with an Application
In many areas of application the extremes of some process may be modelled by considering only its exceedances of a high threshold level. The natural parametric family for such excesses for continuousExpand
Maximum likeiihood estimation of the parameters of the three-parameter generalized extreme-value distribution from censored samples
Maximum likelihood estimators of the parameters of the generalized extreme-value distribution are derived for complete, left censored, right censored or doubly censored samples. Explicit expressionsExpand
Toward a general procedure for analysis of extreme random events in the earth sciences
Engineering and scientific approaches to design magnitude estimation are briefly revisited. Some defense is offered for use of annual maxima in design as if they were variables from a commonExpand
Extreme values — an improved method of fitting
Abstract The Fisher—Tippet Type 1 (FT1) probability distribution has been widely used for plotting extreme values and making long-term predictions from individual sets of data. Commonly some 20–40Expand
Classification of Probability Laws by Tail Behavior
Abstract In this article I refine Parzen's density-quantile tail exponent classification of probability laws by tail behavior by subdividing his medium-tailed class into medium-short, medium-medium,Expand
Estimating tails of probability distributions
On propose un nouvel estimateur pour un indice de variation reguliere et on montre qu'il est souvent plus performant que l'estimateur de Hill (1975)
The Statistical Analysis of Series of Events
This monograph is intended as a survey of some of the problems in theoretical statistics that stem from this sort of data, and has tried to give a simple description, with numerical examples, of the main methods that have been proposed. Expand
Abstract. A complete solution of the important problem of estimating (interpolating) the missing values of a stationary time series is obtained by decomposing it into a prediction plus regressionExpand
Probability and Statistical Inference
Probability and Statistical Inference. By Robert V. Hogg and Elliot A. Tanis. New York, Macmillan, 1977. ix, 450 p. 24 cm. £11·25.
Limiting forms of the frequency distribution of the largest or smallest member of a sample
The limiting distribution, when n is large, of the greatest or least of a sample of n , must satisfy a functional equation which limits its form to one of two main types. Of these one has, apart fromExpand