GENERALIZED PARETO DISTRIBUTION FIT TO MEDICAL INSURANCE CLAIMS DATA

How to choose an optimal threshold is a key problem in the generalized Pareto distribution （GPD） model. This paper attains the exact threshold by testing for GPD,and shows that GPD model allows the actuary to easily estimate high quantiles and the probable maximum loss from the medical insurance claims data.

Generalized Pareto Distribution Model and Its Application to Hydrocarbon Resource Structure Prediction of the Huanghua Depression

The generalized Pareto distribution model is a kind of hydrocarbon pool size probability statistical method for resource assessment. By introducing the time variable, resource conversion rate and the geological variable, resource density, such model can describe not only different types of basins, but also any exploration samples at different phases of exploration, up to the parent population. It is a dynamic distribution model with profound geological significance and wide applicability. Its basic principle and the process of resource assessment are described in this paper. The petroleum accumulation system is an appropriate assessment unit for such method. The hydrocarbon resource structure of the Huanghua Depression in Bohai Bay Basin was predicted by using this model. The prediction results accord with the knowledge of exploration in the Huanghua Depression, and point out the remaining resources potential and structure of different petroleum accumulation systems, which are of great significance for guiding future exploration in the Huanghua Depression.

Control charts for the Pareto distribution

The Pareto distribution plays an important role in various areas of research. In this paper, the average run length （ARL） unbiased control charts, which monitor the shape and threshold parameters of the Pareto distribution respectively, are proposed when the incontrol parameters are known. The effects of parameter estimation on the performance of the proposed control charts are also studied. Results show that the control charts with the estimated parameters are not suitable to be used in the known parameter case, thus the ARL-unbiased control charts for the shape and threshold parameters with the desired ARLo, which consider the variability of the parameter estimates, are further developed. The performance of the proposed control charts is investigated in terms of the ARL. Finally, an example is given to illustrate the proposed control charts.

Application of Pareto Distribution in Wage Models

This paper deals with the use of Pareto distribution in models of wage distribution. Pareto distribution cannot generally be used as a model of the whole wage distribution, but only as a model for the distribution of higher or of the highest wages. It is usually about wages higher than the median. The parameter b is called the Pareto coefficient and it is often used as a characteristic of differentiation of fifty percent of the highest wages. Pareto distribution is so much the more applicable model of a specific wage distribution, the more specific differentiation of fifty percent of the highest wages will resemble to differentiation that is expected by Pareto distribution. Pareto distribution assumes a differentiation of wages, in which the following ratios are the same： ratio of the upper quartile to the median; ratio of the eighth decile to the sixth decile; ratio of the ninth decile to the eighth decile. This finding may serve as one of the empirical criterions for assessing, whether Pareto distribution is a suitable or less suitable model of a particular wage distribution. If we find only small differences between the ratios of these quantiles in a specific wage distribution, Pareto distribution is a good model of a specific wage distribution. Approximation of a specific wage distribution by Pareto distribution will be less suitable or even unsuitable when more expressive differences of mentioned ratios. If we choose Pareto distribution as a model of a specific wage distribution, we must reckon with the fact that the model is always only an approximation. It will describe only approximately the actual wage distribution and the relationships in the model will only partially reflect the relationships in a specific wage distribution.

Characterization of Pareto Distribution Through Expectation of Function of Order Statistics

For characterization of Pareto distribution one needs any arbitrary non constant function only by approach of identity of distribution and equality of expectation of function of random variable in place of approaches such as relation （linear） in （economic variation） reported and true income, independency of suitable function of order statistics, mean and the extreme observation of the sample etc. Examples are given for illustrative purpose

Estimation of Poisson-Generalized Pareto Compound Extreme Value Distribution by Probability-Weighted Moments and Empirical Analysis

This paper puts forward a Poisson-generalized Pareto (Poisson-GP) distribution. This new form of compound extreme value distribution expands the existing application of compound extreme value distribution, and can be applied to predicting financial risk, large insurance settlement and high-grade earthquake, etc. Compared with the maximum likelihood estimation (MLE) and compound moment estimation (CME), probability-weighted moment estimation (PWME) is used to estimate the parameters of the distribution function. The specific formulas are presented. Through Monte Carlo simulation with sample sizes 10, 20, 50, 100, 1 000, it is concluded that PWME is an efficient method and it behaves steadily. The mean square errors (MSE) of estimators by PWME are much smaller than those of estimators by CME, and there is no significant difference between PWME and MLE. Finally, an example of foreign exchange rate is given. For Dollar/Pound exchange rates from 1990-01-02 to 2006-12-29, this paper formulates the distribution function of the largest loss among the investment losses exceeding a certain threshold by Poisson-GP compound extreme value distribution, and obtains predictive values at different confidence levels.

Prediction of Short-Term Distributions of Load Extremes of Offshore Wind Turbines

This paper proposes a new methodology to select an optimal threshold level to be used in the peak over threshold （POT） method for the prediction of short-term distributions of load extremes of offshore wind turbines. Such an optimal threshold level is found based on the estimation of the variance-to-mean ratio for the occurrence of peak values, which characterizes the Poisson assumption. A generalized Pareto distribution is then fitted to the extracted peaks over the optimal threshold level and the distribution parameters are estimated by the method of the maximum spacing estimation. This methodology is applied to estimate the short-term distributions of load extremes of the blade bending moment and the tower base bending moment at the mudline of a monopile-supported 5MW offshore wind turbine as an example. The accuracy of the POT method using the optimal threshold level is shown to be better, in terms of the distribution fitting, than that of the POT methods using empirical threshold levels. The comparisons among the short-term extreme response values predicted by using the POT method with the optimal threshold levels and with the empirical threshold levels and by using direct simulation results further substantiate the validity of the proposed new methodology.

Power Law Distributions in the Experiment for Adjustment of the Ion Source of the NBI System

The experiential adjustment process in an experiment on the ion source of the neutral beam injector system for the HT-7 Tokamak is reported in this paper. With regard to the data obtained in the same condition, in arranging the arc current intensities of every shot with a decay rank, the distributions of the arc current intensity correspond to the power laws, and the distribution obtained in the condition with the cryo-pump corresponds to the double Pareto distribution. Using the similar study method, the distributions of the arc duration are close to the power laws too. These power law distributions are formed rather naturally instead of being the results of purposeful seeking.

Statistical Inference of Stress-Strength Model for Exponentiated Pareto Model with Censored Data

The reliability of a system is discussed when the strength of the system and the stress imposed on it are independent and non-identical exponentiated Pareto distributed random variables with progressively censored scheme.Different interval estimations are proposed.The interval estimations obtained are exact,approximate and bootstrap confidence intervals.Different methods and the corresponding confidence intervals are compared using Monte-Carlo simulations.Simulation results show that the confidence intervals(CIs)of exact and approximate methods are really better than those of the bootstrap method.

A Newly-Discovered GPD-GEV Relationship Together with Comparing Their Models of Extreme Precipitation in Summer

It has been theoretically proven that at a high threshold an approximate expression for a quantile of GEV （Generalized Extreme Values） distribution can be derived from GPD （Generalized Pareto Distribution）. Afterwards, a quantile of extreme rainfall events in a certain return period is found using L-moment estimation and extreme rainfall events simulated by GPD and GEV, with all aspects of their results compared. Numerical simulations show that POT （Peaks Over Threshold）-based GPD is advantageous in its simple operation and subjected to practically no effect of the sample size of the primitive series, producing steady high-precision fittings in the whole field of values （including the high-end heavy tailed）. In comparison, BM （Block Maximum）-based GEV is limited, to some extent, to the probability and quantile simulation, thereby showing that GPD is an extension of GEV, the former being of greater utility and higher significance to climate research compared to the latter.

AN ANALYSIS OF THE WINTER EXTREME PRECIPITATION EVENTS ON THE BACKGROUND OF CLIMATE WARMING IN SOUTHERN CHINA

Based on daily precipitation and monthly temperature data in southern China, the winter extreme precipitation changes in southern China have been investigated by using the Mann-Kendall test and the return values of Generalized Pareto Distribution. The results show that a winter climate catastrophe in southern China occurred around i99I, and the intensity of winter extreme precipitation was strengthened after climate wanning. The anomalous circulation characteristics before and after the climate wanning was further analyzed by using the U.S. National Centers for Environmental Prediction/National Center for Atmospheric Research reanalysis data. It is found that the tropical winter monsoon over East Asia is negatively correlated with the precipitation in southeastern China. After climate warming the meridionality of the circulations in middle and high latitudes increases, which is favorable for the southward movement of the cold air from the north. In addition, the increase of the temperature over southern China may lead to the decrease of the differential heating between the continent and the ocean. Consequently, the tropical winter monsoon over East Asia is weakened, which is favorable for the transport of the warm and humid air to southeastem China and the formation of the anomalous convergence of the moisture flux, resulting in large precipitation over southeastern China. As a result, the interaction between the anomalous circulations in the middle and high latitudes and lower latitudes after the climate warming plays a major role in the increase of the winter precipitation intensity over southeastem China.

Non-conventional modeling of extreme significant wave height through random sets

The analysis and design of offshore structures necessitates the consideration of wave loads. Realistic modeling of wave loads is particularly important to ensure reliable performance of these structures. Among the available methods for the modeling of the extreme significant wave height on a statistical basis, the peak over threshold method has attracted most attention. This method employs Poisson process to character- ize time-varying properties in the parameters of an extreme value distribution. In this paper, the peak over threshold method is reviewed and extended to account for subjectivity in the modeling. The freedom in selecting the threshold and the time span to separate extremes from the original time series data is incorpo- rated as imprecision in the model. This leads to an extension from random variables to random sets in the probabilistic model for the extreme significant wave height. The extended model is also applied to different periods of the sampled data to evaluate the significance of the climatic conditions on the uncertainties of the parameters.

Variable bit rate video traffic modeling by multiplicative multifractal model

Multiplicative multifractal process could well modal video traffic. The multiplier distributions in the multiplicatire multifractal model for video traffic are investigated and it is found that Gaussian is not suitable for describing the multipliers on the small time scales. A new statistical distribution-symmetric Pareto distribution is introduced. It is applied instead of Gaussian for the multipliers on those scales. Based on that, the algorithm is updated so that symmetric pareto distribution and Gaussian distribution are used to model video traffic but on different time scales. The simulation results demonstrate that the algorithm could model video traffic more accurately.

Network Traffic Based on GARCH-M Model and Extreme Value Theory

GARCH-M ( generalized autoregressive conditional heteroskedasticity in the mean) model is used to analyse the volatility clustering phenomenon in mobile communication network traffic. Normal distribution, t distribution and generalized Pareto distribution assumptions are adopted re- spectively to simulate the random component in the model. The demonstration of the quantile of network traffic series indicates that common GARCH-M model can partially deal with the "fat tail" problem. However, the "fat tail" characteristic of the random component directly affects the accura- cy of the calculation. Even t distribution is based on the assumption for all the data. On the other hand, extreme value theory, which only concentrates on the tail distribution, can provide more ac- curate result for high quantiles. The best result is obtained based on the generalized Pareto distribu- tion assumption for the random component in the GARCH-M model.

Consistency of the <i>φ</i>-Divergence Based Change Point Estimator

This paper utilizes a change-point estimator based on the φ-divergence. Since we seek a near perfect translation to reality, then locations of parameter change within a finite set of data have to be accounted for since the assumption of stationary model is too restrictive especially for long time series. The estimator is shown to be consistent through asymptotic theory and finally proven through simulations. The estimator is applied to the generalized Pareto distribution to estimate changes in the scale and shape parameters.

Peaks over Manifold (POM): A Novel Technique to Analyze Extreme Events over Surfaces

We present a novel method to analyze extreme events of flows over manifolds called Peaks Over Manifold (POM). Here we show that under general and realistic hypotheses, the distribution of affectation measures converges to a Generalized Pareto Distribution (GPD). The method is applicable to floods, ice cover extent, extreme rainfall or marine heatwaves. We present an application to a synthetic data set on tide height and to real ice cover data in Antartica.

A fuzzy quantification approach of uncertainties in an extreme wave height modeling

A non-traditional fuzzy quantification method is presented in the modeling of an extreme significant wave height. First, a set of parametric models are selected to fit time series data for the significant wave height and the extrapolation for extremes are obtained based on high quantile estimations. The quality of these results is compared and discussed. Then, the proposed fuzzy model, which combines Poisson process and gener-alized Pareto distribution （GPD） model, is applied to characterizing the wave extremes in the time series data. The estimations for a long-term return value are considered as time-varying as a threshold is regarded as non-stationary. The estimated intervals coupled with the fuzzy theory are then introduced to construct the probability bounds for the return values. This nontraditional model is analyzed in comparison with the traditional model in the degree of conservatism for the long-term estimate. The impact on the fuzzy bounds of extreme estimations from the non stationary effect in the proposed model is also investigated.

Explicit Expressions for the Ruin Probabilities of Erlang Risk Processes with Pareto Individual Claim Distributions

In this paper we first consider a risk process in which claim inter-arrival times and the time until the first claim have an Erlang (2) distribution. An explicit solution is derived for the probability of ultimate ruin, given an initial reserve of u when the claim size follows a Pareto distribution. Follow Ramsay[8], Laplace transforms and exponential integrals are used to derive the solution, which involves a single integral of real valued functions along the positive real line, and the integrand is not of an oscillating kind. Then we show that the ultimate ruin probability can be expressed as the sum of expected values of functions of two different Gamma random variables. Finally, the results are extended to the Erlang(n) case. Numerical examples are given to illustrate the main results.

Extreme air pollution events:Modeling and prediction

In order to get prepared for the coming extreme pollution events and minimize their harmful impacts, the first and most important step is to predict their possible intensity in the future. Firstly, the generalized Pareto distribution （GPD） in extreme value theory was used to fit the extreme pollution concentrations of three main pollutants： PM10, NO2 and SO：, from 2005 to 2010 in Changsha, China. Secondly, the prediction results were compared with actual data by a scatter plot. Four statistical indicators： EMA （mean absolute error）, ERMS （root mean square error）, IA （index of agreement） and R2 （coefficient of determination） were used to evaluate the goodness-of-fit as well. Thirdly, the return levels corresponding to different return periods were calculated by the fitted distributions. The fitting results show that the distribution of PM10 and SO2 belongs to exponential distribution with a short tail while that of the NOe belongs to beta distribution with a bounded tail. The scatter plot and four statistical indicators suggest that GPD agrees well with the actual data. Therefore, the fitted distribution is reliable to predict the return levels corresponding to different return periods. The predicted return levels suggest that the intensity of coming pollution events for PM10 and SO2 will be even worse in the future, which means people have to get enough preparation for them.

Calendar Effects in AAPL Value-at-Risk

This study investigates calendar anomalies： day-of-the-week effect and seasonal effect in the Value-at-Risk （VaR） analysis of stock returns for AAPL during the period of 1995 through 2015. The statistical properties are examined and a comprehensive set of diagnostic checks are made on the two decades of AAPL daily stock returns. Combing the Extreme Value Approach together with a statistical analysis, it is learnt that the lowest VaR occurs on Fridays and Mondays typically. Moreover, high Q4 and Q3 VaR are observed during the test period. These results are valuable for anyone who needs evaluation and forecasts of the risk situation in AAPL. Moreover, this methodology, which is applicable to any other stocks or portfolios, is more realistic and comprehensive than the standard normal distribution based VaR model that is commonly used.