QUALITY CONTROL METHODS IN LARGE-SCALE ASSESSMENT PROCEDURES USING 'DOUBLE-MARKING' OR 'PARTIAL DOUBLE-MARKING'

Ensuring a standard of assessment in situations where marking panels are used is fraught with difficulties, particularly where essay-type responses are to be marked. This paper discusses statistical process control procedures, similar to those used in industry, to help moderate marking quality when ‘double-marking’ or ‘partial double-marking’ are used. When questions are assessed by the same two markers, the scores assigned to responses by each marker may be adjusted so that their assessments are on average equal in terms of location and scale. The paper also discusses methods of controlling sequential assessment, and demonstrates the application of these techniques in evaluating marker consistency, using data from school leaving examinations in geography.     

Multivariate distributions with generalized inverse gaussian marginals,and associated poisson mixtures

Several types of multivariate extensions of the inverse Gaussian (IG) distribution and the reciprocal inverse Gaussian (RIG) distribution are proposed. Some of these types are obtained as random-additive-effect models by means of well-known convolution properties of the IG and RIG distributions, and they have one-dimensional IG or RIG marginals. They are used to define a flexible class of multivariate Poisson mixtures.     

Adjustments for reporting delays and the prediction of occurred but not reported events

We consider delays that occur in the reporting of events such as cases of a reportable disease or insurance claims. Estimation of the number of events that have occurred but not yet been reported (OBNR events) is then important. Current methods of doing this do not allow random temporal fluctuations in reporting delays, and consequently, confidence or prediction limits on OBNR events tend to be too narrow. We develop an approach that uses recent reporting data and incorporates random effects, thus leading to more reasonable and robust predictions     

马尔科夫链在市场预测中的作用

马尔科夫链预测法是一种适用于随机过程的科学、有效的动态预测方法,其基本原理和方法可用来预测企业产品的市场占有率。在运用马尔科夫链对市场占有率进行预测时,应做好市场调查工作,并借助计算机和简捷表加以计算。     

重“事实”的现代散文观——谈废名散文观的特质

废名提出"重事实"的散文观念,发展了周作人的小品文观,产生以"隔"为特色的散文风格。辨析废名和周作人师生之间"隔"的异同,可窥其"重事实"散文观内质是重灵感、崇自然。废名从六朝文总结出"乱写"的技法,推崇无意为文,重内在灵感之线索。二者共同形成废名散文独特的"隔"之美学风格。     

影响RFA高尔夫产业发展的因素分析与对策

我国高尔夫产业已有20多年的发展历史,在经济高速增长与高尔夫旅游业快速发展的刺激下,我国高尔夫产业已初具规模。文章基于机器学习的随机森林算法,对影响我国高尔夫产业发展的因素进行分析与探讨。结果表明,首先是固定资产投资规模对高尔夫产业的发展影响最大,其次是影响高尔夫产业发展的是国内生产总值、旅游消费和旅游人数,居民消费水平和第三产业增加值对于高尔夫球场数量的影响程度较小。     

基于价值链视角的保险业声誉价值研究

现阶段我国保险业声誉不佳、形象不好的问题日益突出,严重制约了保险业的健康发展。基于价值链视角,构建声誉的价值支持系统和保险业的价值链模型,并从价值链模型中的价值创造、价值经营、价值实现三个方面来确定保险业声誉价值的影响因素。通过随机效应模型得到影响保险业声誉价值的影响因素,并将其按重要程度排序依次是市场占有、社会责任披露程度、盈利能力、工作环境、产品与服务质量和财务稳健性。保险业应从这六个方面入手,塑造和提升企业声誉价值,建立以声誉为导向的企业文化。     

Simultaneous estimation of mortality and dispersal rates of an artificially released population

Mark-recapture methods cannot estimate both mortality and dispersal rates of a wild population simultaneously. However, when an artificially cultured population is released into an area, the initial population size and the initial population distribution are usually known. If artificially cultured individuals are released with marks or distinguished from wild individuals or if no wild individual exists in the study area, we can estimate both the mortality and dispersal rates of the artificial population. The numbers of dispersed and dead individuals are estimated from the dispersal rate from the diffusion model and the total decreasing rate estimated from a mark-recapture data. We can estimate both the time-dependent and time-independent dispersal rates from the data. We choose the best fit model that has the smallest value of Akaike's Information Criteria. We also consider ‘concentric circles approximation” of spatial distribution, in which the cumulative and frequency distributions are analytically obtained.     

Likelihood-based approach for analysis of longitudinal nominal data using marginalized random effects models

Likelihood-based marginalized models using random effects have become popular for analyzing longitudinal categorical data. These models permit direct interpretation of marginal mean parameters and characterize the serial dependence of longitudinal outcomes using random effects [12,22]. In this paper, we propose model that expands the use of previous models to accommodate longitudinal nominal data. Random effects using a new covariance matrix with a Kronecker product composition are used to explain serial and categorical dependence. The Quasi-Newton algorithm is developed for estimation. These proposed methods are illustrated with a real data set and compared with other standard methods.     

Risk efficient estimation of fully dependent random coefficient autoregressive models of general order

We consider a stochastic dynamic model with autoregressive progression. The drift coefficients of the autoregressive model are random where the randomness in the coefficients can have any dependence structure. We propose a two-step sequential estimator and study the asymptotic behavior of few important properties. Paradigm of sequential estimation has its own advantage in reducing sample size and plugging estimates of nuisance parameters while inferring about the main parameters. Our proposed estimator is asymptotically optimal as the predictive risk of the proposed estimator attains the risk of the oracle that assumes known nuisance parameters. Extensive simulation confirms our results.