Estimation of actuarial quantities at fractional ages with Kriging

ABSTRACT

Life tables used in life insurance are often calibrated to show the survival function of the age of death distribution at exact integer ages. Actuaries usually make fractional age assumptions (FAAs) when having to value payments that are not restricted to integer ages. Traditional FAAs have the advantage of simplicity but cannot guarantee to capture precisely the real trends of the survival functions and sometimes even result in a non intuitive overall shape of the force of mortality. In fact, an FAA is an interpolation between integer age values which are accepted as given. In this article, we introduce Kriging model, which is widely used as a metamodel for expensive simulations, to fit the survival function at integer ages, and furthermore use the precisely constructed survival function to build the force of mortality and the life expectancy. The experimental results obtained from a simulated life table (Makehamized life table) and two “real” life tables (the Chinese and US life tables) show that these actuarial quantities (survival function, force of mortality, and life expectancy) presented by Kriging model are much more accurate than those presented by commonly-used FAAs: the uniform distribution of death (UDD) assumption, the constant force assumption, and the Balducci assumption.     

Probabilistic approaches to current life table estimation

"Two simple current life table estimators of conditional probabilities of death result from making either a uniform or exponential distributional assumption of time at death in the age interval. Each is compared with Chiang's estimator based on the concept of fraction of the last age interval of life. Graphical and numerical results are presented to assess the magnitude and direction of differences between estimators when the true value of Chiang's fraction takes on specific values."     

Probabilistic Approaches to Current Life Table Estimation

Two simple current life table estimators of conditional probabilities of death result from making either a uniform or exponential distributional assumption of time at death in the age interval. Each is compared with Chiang's estimator based on the concept of fraction of the last age interval of life. Graphical and numerical results are presented to assess the magnitude and direction of differences between estimators when the true value of Chiang's fraction takes on specific values.     

C55. Quick and accurate rule of thumb for determining the critical value of the coefficient of correlation

Life table analysis techniques in epidemiology depend upon the asymptotic properties of the statistical test methods employed. In some instances, the statistical procedures indicate highly significant results which are, in reality, unjustified. The phenomenon may occur when the asymptotic methods are applied in situations where the cases of interest are few in number. This situation is illustrated by the 20 multiple myeloma deaths observed in the RERF Life Span Study cohort. A permutation test is applied to the life table data, although the test requires the false assumption that the censoring distribution is independent of the radiation dose. A simulation test is developed which does not require equal censoring, which has the same asymptotics as the usual test methods, and which is less likely to overestimate significance in small samples. It is found that both of these small-sample tests provide reasonable numerical solutions. In addition, the simulation test is recommended in general for analyzing life table data with unequal censoring. Finally, by using the small-sample tests, the frequency of death from multiple myeloma is shown to be positively associated with radiation dose (P<0.01).     

Log-linear models for correlated marginal totals of a contingency table

The marginal totals of a contingency table can be rearranged to form a new table. If at least twoof these totals include the same cell of the original table, the new table cannot be treated as anordinary contingency table. An iterative method is proposed to calculate maximum likelihood estimators for the expected cell frequencies of the original table under the assumption that some marginal totals (or more generally, some linear functions) of these expected frequencies satisfy a log-linear model.In some cases, a table of correlated marginal totals is treated as if it was an ordinary contingency table. The effects of ignoring the special structure of the marginal table on thedistributionof the goodness-of-fit test statistics are discussed and illustrated, with special reference to stationary Markov chains.     

A time series approach to life table construction

This paper deals with the construction of the life table. A discussion of basic facts about the life table is followed by the proposal of a nonstationary, autoregressive model for the life table. The moment structure of the nonstationary, autoregressive model is developed. Some estimation procedures are proposed followed by several examples.     

The effect of individual variability on the life table

A general formulation of the life table in the presence of individual jeterogeneity is presented. The possible effects of heterogeneity on the various life table functions are outlined. For the case of ordinary life tables, a method is presented for the evaluation of these effects. The proposed method id illustrated by a numerical example.     

Fractional Age Assumption Based on Cubic Polynomial Interpolation

This article proposes a new fractional age assumption (FAA) based on the cubic polynomial interpolation (CPI) and applies it to estimate the mortality rate and related actuarial quantities. The validity of the method under CPI is proved theoretically and the valuable advantages of CPI assumption are discussed based on three different perspectives—utilized death information, property of mortality force, and optimality criterion. The results show that CPI assumption has distinct valuable superiority compared with other FAAs in references. Finally under CPI assumption we study the calculations of some important actuarial quantities in life contingencies.     

Life table estimator revisited

We explore the standard life table (actuarial) estimator for grouped right-censored survival data and its extensions in order to consider its relationship with the Kaplan–Meier estimator, and to investigate the critical properties of the extended life table estimators (ELTEs). We discuss certain conditions for the ELTE to be consistent and develop a characterization of the standard life table estimator using the consistency property under any choice of at least two observation times of a finite interval. We also perform a comparative analysis of the ELTEs with the corresponding maximum likelihood estimators for grouped right-censored survival data.     

A comparison of models for dynamic life tables. Application to mortality data from the Valencia Region (Spain)

The graduation of mortality data aims to estimate the probabilities of death at age x, q ( x ), by means of an age-dependent function, whose parameters are adjusted from the crude probabilities that are directly obtainable from the data. However, current life tables have a problem, the need for periodic updates due to changes in mortality over short periods of time. The table containing mortality rates for different ages in different years, q ( xt ), is called a dynamic life table, which captures mortality variation over time. This paper proposes a review of the most commonly used dynamic models and compares the results obtained by each of them when applied to mortality data from the Valencia Region (Spain). The result of the comparison leads us to the conclusion that the Lee-Carter method offers the best results for both sexes, while that based on Heligman and Pollard functions provides the best fit for men alone. Our working method is of additional interest as it may be applied to mortality data for a wide range of ages in any geographical location, allowing the most appropriate dynamic life table to be selected for the case at hand.     

Modelling Trends and Inequality in Small Area Mortality

This paper considers the modelling of mortality rates classified by age, time, and small area with a view to developing life table parameters relevant to assessing trends in inequalities in life chances. In particular, using a fully Bayes perspective, one may assess the stochastic variation in small area life table parameters, such as life expectancies, and also formally assess whether trends in indices of inequality in mortality are significant. Modelling questions include choice between random walk priors for age and time effects as against non-linear regression functions, questions of identifiability when several random effects are present in the death rates model, and the choice of model when both within and out-of-sample performance may be important. A case study application involves 44 small areas in North East London and mortality in five sub-periods (1986-88, 1989-91, 1992-94, 1995-97, 1998-2000) between 1986 and 2000, with the final period used for assessing out-of-sample performance.     

资金流量表模型体系的建立与应用

本文在资金流量核算表的基础上,依据“固定产品收入结构假定”、“固定产品支出结构假定”、“固定部门收入结构假定”、“固定部门支出结构假定”四种假定,给出了编制资金流量部门表和资金流量产品表的计算公式,建立了包含4个机构部门模型、2个金融产品模型、4个部门与产品交叉模型的资金流量表乘数模型体系。用中国2011年资金流量表数据进行了实际验证。利用这些模型可以进行部门间、产品间、部门与产品相互之间的资金流量关系分析,可以为制定政策、追踪各种资金关联效应提供方法论的支持。     

Fitting polynomial trend to time series by the method of Buys-Ballot estimators

The statistical properties of two closed-form estimators of the parameters of the quadratic time trend model are derived. The estimators are based on the derived variables from Buys-Ballot table. The estimators are derived by assuming that error term is identically and independently distributed. However, the validity of this assumption is sometimes difficult to verify. We also study, through simulations, the impact of misspecifying the error distribution on the estimation and prediction accuracy in the quadratic time trend model. It is shown that the estimators are inconsistent in the presence of misspecification. T methods are illustrated with real-life examples.     

Comparison of two independent life tests subject to type II censoring

The problem of comparing two life distributions is considered. It Is assumed that each life test Is stopped after a predetermined number of failures without regard to the number of failures which have occurred in the other life test. A generalized Wilcoxon-rlann-Whitney test is proposed. Small and large sample distributional results are obtained for the test statistic. Under the assumption that the life distributions differ by at most a scale parameter an exact confidence interval for that parameter is obtained. An algorithm for computing the interval is given.     

Acceptance sampling based on truncated life tests for generalized Rayleigh distribution

This paper considers the problem of an acceptance sampling plan for a truncated life test when the lifetime follows the generalized Rayleigh distribution. For different acceptance numbers, confidence levels, and values of the ratio of the fixed experiment time to the specified mean life, the minimum sample sizes necessary to ensure the specified mean life are found. The operating characteristic values of the sampling plans and producer's risk are discussed. Some tables are presented and the use of the tables is illustrated by a numerical example.     

Fitting and testing the Marshall–Olkin extended Weibull model with randomly censored data

The random censorship model (RCM) is commonly used in biomedical science for modeling life distributions. The popular non-parametric Kaplan–Meier estimator and some semiparametric models such as Cox proportional hazard models are extensively discussed in the literature. In this paper, we propose to fit the RCM with the assumption that the actual life distribution and the censoring distribution have a proportional odds relationship. The parametric model is defined using Marshall–Olkin's extended Weibull distribution. We utilize the maximum-likelihood procedure to estimate model parameters, the survival distribution, the mean residual life function, and the hazard rate as well. The proportional odds assumption is also justified by the newly proposed bootstrap Komogorov–Smirnov type goodness-of-fit test. A simulation study on the MLE of model parameters and the median survival time is carried out to assess the finite sample performance of the model. Finally, we implement the proposed model on two real-life data sets.     

Acceptance sampling based on life tests: log-logistic model

The problem of acceptance sampling when the life test is truncated at a preassigned time is considered. For various acceptance numbers, confidence levels and values of the ratio of the fixed experimental time to the specified average life, the minimum sample size necessary to ensure the specified average life, are obtained under the assumption that the lifetime variate of the test items follows a distribution belonging to Burr's family XII of distributions - called the log-logistic model. The operating characteristic values of the sampling plans and producer's risk are presented. The results are illustrated by an example.     

Minimum chi-square estimator and test for incomplete multidimensional contingency tables

A modified transformed chi-square statistic is defined for testing hypotheses of quasi-independence in the incomplete multi-dimensional contingency table and a simple method for determining degrees of freedom is given. A modified transformed chi-squareestimator of the expected cell frequencies is given in closed form for a general class of exact linear constraints. The co-variance matrix of estimated cell frequencies is derived under the assumption of a conditional Poisson distribution.     

Exact confidence bounds for an exponential parameter under hybrid censoring

Consider a life testing experiment in which n units are put on test, successive failure times are recorded, and the observation is terminated either at a specified number r of failures or a specified time T whichever is reached first. This mixture of type I and type II censoring schemes, called hybrid censoring, is of wide use. Under this censoring scheme and the assumption of an exponential life distribution, the distribution of the maximum likelihood estimator of the mean life 6 is derived. It is then used to construct an exact lower confidence bound for θ.     

Exact confidence bounds for an exponential parameter under hybrid censoring

Consider a life testing experiment in which n units are put on test, successive failure times are recorded, and the observation is terminated either at a specified number r of failures or a specified time T whichever is reached first. This mixture of type I and type II censoring schemes, called hybrid censoring, is of wide use. Under this censoring scheme and the assumption of an exponential life distribution, the distribution of the maximum likelihood estimator of the mean life θ is derived. It is then used to construct an exact lower confidence bound for θ.