Modelling extremes of time-dependent data by Markov-switching structures

We investigate the extremal clustering behaviour of stationary time series that possess two regimes, where the switch is governed by a hidden two-state Markov chain. We also suppose that the process is conditionally Markovian in each latent regime. We prove under general assumptions that above high thresholds these models behave approximately as a random walk in one (called dominant) regime and as a stationary autoregression in the other (dominated) regime. Based on this observation, we propose an estimation and simulation scheme to analyse the extremal dependence structure of such models, taking into account only observations above high thresholds. The properties of the estimation method are also investigated. Finally, as an application, we fit a model to high-level exceedances of water discharge data, simulate extremal events from the fitted model, and show that the (model-based) flood peak, flood duration and flood volume distributions match their observed counterparts.     

Scatter Plot and Additional Variables

We often want to complete the interpretation of the usual graphs (x, y) with additional quantitative variables. The Prefmap method (vectorial model) proposes a representation of these additional variables but this representation has some drawbacks when the variables x and y are correlated. To solve this problem, we propose to substitute the coefficients of the linear regression by the coefficient of the PLS regression in the Prefmap method. The graph obtained is made operational thanks to contour lines of quality of representation and it becomes richer than the Prefmap one.     

中国技术国际收支统计可行性研究

一、问题的提出随着现代科技的发展 ,人们越来越认识到技术的重要性。它不仅是一个国家经济增长的主要推动因素 ,还决定一个国家的经济结构、生产力水平并最终影响一国的综合实力。有关技术的输入和输出逐渐引起人们的关注。技术的流动可以通过有形的高科技商品交易 ,无形的技术转让、科技人员交流等形式进行。我国海关近年来对高科技产品进出口已经建立并实施了较为系统的统计 ,从中可观察到高技术产品各种分类及流向。而对于以人或文件为载体的技术转让 ,由于其无形性和复杂性 (常伴随着其他形式的技术流动 ) ,对其实施统计无疑是十分困难…     

Chance-Corrected Measures of Reliability and Validity in 2 × 2 Tables

It is customary to use two groups of indices to evaluate a diagnostic method with a binary outcome: validity indices with a standard rater (sensitivity, specificity, and positive or negative predictive values) and reliability indices (positive, negative and overall agreements) without a standard rater. However neither of these classic indices is chance-corrected, and this may distort the analysis of the problem (especially in comparative studies). One way of chance-correcting these indices is by using the Delta model (an alternative to the Kappa model), but this means having to use a computer program to work out the calculations. This paper gives an asymptotic version of the Delta model, thus allowing simple expressions to be obtained for the estimator of each of the above-mentioned chance-corrected indices (as well as for its standard error).     

Optimal correction for continuity in the chi-squared test in 2×2 tables

The most common asymptotic procedure for analyzing a 2 × 2 table (under the conditioning principle) is the ‰ chi-squared test with correction for continuity (c.f.c). According to the way this is applied, up to the present four methods have been obtained: one for one-tailed tests (Yates') and three for two-tailed tests (those of Mantel, Conover and Haber). In this paper two further methods are defined (one for each case), the 6 resulting methods are grouped in families, their individual behaviour studied and the optimal is selected. The conclusions are established on the assumption that the method studied is applied indiscriminately (without being subjected to validity conditions), and taking a basis of 400,000 tables (with the values of sample size n between 20 and 300 and exact P-values between 1% and 10%) and a criterion of evaluation based on the percentage of times in which the approximate P-value differs from the exact (Fisher's exact test) by an excessive amount. The optimal c.f.c. depends on n, on E (the minimum quantity expected) and on the error α to be used, but the rule of selection is not complicated and the new methods proposed are frequently selected. In the paper we also study what occurs when E ≥ 5, as well as whether the chi-squared by factor (n-1).     

上市公司智力资本信息披露对投资评级影响的实证分析——基于分析师跟踪的中介效应研究

目的/意义 以女性CFO为代表的“她力量”在企业行为决策过程中发挥越来越积极的作用。随着资本市场对金融类上市公司增强智力资本信息透明度的呼声日益高涨,有着风险厌恶与高道德标准性格特质的女性CFO如何影响金融类公司的智力资本信息披露决策无疑是一项迫切需要解答的现实问题。 设计/方法 以2011～2016年我国金融类A股上市公司为研究对象,利用手工采集智力资本信息披露数据,首次构建测度了我国金融类上市公司的智力资本信息披露指数（ICDI）,并利用该指数实证考察了女性CFO与智力资本信息披露行为间的关系以及产权性质、产品市场竞争强度对这一关系的调节效应。 结论/发现 研究结果表明：（1）近年来我国金融类上市公司日益重视智力资本信息,披露水平呈现明显的上升趋势;（2）女性CFO显著提高了智力资本信息披露水平,即相比男性CFO,更加厌恶风险且道德观念更强的女性CFO能够对外披露更多的智力资本信息;（3）产权性质与产品市场竞争在女性CFO与智力资本信息披露关系中发挥显著的正向调节效应,即相比在非国有控股企业、竞争水平较低的环境中,在国有控股企业与激烈市场竞争环境中的女性CFO能够更有效地增加智力资本信息披露。进一步研究还显示,金融类公司的智力资本信息披露能够显著提升企业市场价值,降低企业内外部信息不对称性。多维度的研究结论为现阶段引导、规范我国金融企业智力资本信息披露、营造对女性更包容的高管培育环境提供了有益启示。     

Estimation of Risk Assessment of Some Heavy Metals Intake Through Black Scabbardfish (Aphanopus carbo) Consumption in Portugal

The intake of Cd, methyl‐Hg, and Pb through consumption of black scabbardfish (BSF) (Aphanopus carbo) in Portugal as well as the associated probability of exceeding the respective provisional tolerable weekly intakes (PTWIs) was estimated. For this purpose, the contamination levels of heavy metals in this fish species were combined with constructed consumption scenarios or with a hypothesized consumption distribution. Whereas Cd and Pb posed no serious risk, the consumption of at least one portion of BSF per month as well as the hypothetical study in the Portuguese population produced nonnegligible probabilities of surpassing the PTWI for Me‐Hg. Risk assessment for Portuguese consumers revealed a higher risk regarding Me‐Hg, 1.19% and 1.81% with the plug‐in (PI) and the tail estimation (TE) estimators, respectively. On the other hand, the risk for Cd and Pb was less than 1 in 100,000. TE was more realistic and accurate for Cd and Pb. Concerning Me‐Hg, TE and PI estimators produced similar results. Furthermore, the limitations of a deterministic approach were shown.     

Marginally restricted sequential D‐optimal designs

In many experiments, not all explanatory variables can be controlled. When the units arise sequentially, different approaches may be used. The authors study a natural sequential procedure for “marginally restricted” D‐optimal designs. They assume that one set of explanatory variables (x₁) is observed sequentially, and that the experimenter responds by choosing an appropriate value of the explanatory variable x₂. In order to solve the sequential problem a priori, the authors consider the problem of constructing optimal designs with a prior marginal distribution for x₁. This eliminates the influence of units already observed on the next unit to be designed. They give explicit designs for various cases in which the mean response follows a linear regression model; they also consider a case study with a nonlinear logistic response. They find that the optimal strategy often consists of randomizing the assignment of the values of x₂.     

Heterogeneity and Unemployment Duration

ABSTRACT: Various unemployment duration models are estimated on a large Norwegian dataset covering labour market history 1.1.1989-31.12.1992 for all persons who became unemployed during October 1990. As many unemployed leave the unemployment register without going directly to a job, two alternative definitions of unemployment are used — register unemployment and joblessness. The problem of heterogeneity is addressed both by partitioning the individuals into four categories by previous unemployment history, and by including a random term in the job hazard. Observed as well as unobserved heterogeneity affects the estimates of expected duration to a great extent. When gamma-distributed unobserved heterogeneity is accounted for, the estimates of duration dependence become more positive relative to models where unobserved heterogeneity is ignored. Among persons who are entitled to unemployment benefit, the duration dependence appears to be significantly positive. Alternative specifications of the baseline hazard hardly affect estimates of the effects of the covariates on duration.     

Bringing the Firms into Globalization Research: The Effects of Foreign Investment and Exports on Wages in Mexican Manufacturing Firms

Researchers specializing in organizations and labor markets have paid insufficient attention to the effects that foreign ownership of a firm and its orientation towards export production may have on the wages it pays to its workers. Using information from a nationally-representative sample of manufacturing firms in Mexico, a paradigmatic case of a developing country that is highly integrated into world markets, we find that foreign-owned and export-oriented firms pay considerably more than nationally-owned firms engaged in the production of goods for sale in the domestic market. Second, beyond paying higher wages to their workers, foreign-owned firms also raise the wages paid by domestic firms operating in the same regional labor markets. The wage premium in foreign and export-oriented firms cannot be explained by their size, industry, geographical location, productivity, use of advanced technology, or the sociodemographic composition of their workforce. We find evidence that wages in foreign-owned companies in Mexico are dependent on the country of origin of the capital investment. A greater difference between the industry-specific wages paid in the country of ownership and Mexico is associated with a higher wage premium in Mexican affiliates. Future work should strive to link information from foreign-owned affiliates with their parent companies abroad.