基本养老保险收支测算中职工人数模型的探讨

职工人数测算在养老保险收支测算中居重要地位,通常使用的时间序列法,受波动性因素影响测算结果误差较大,在保障水平固定时误差直接表现为基期收支与实际不符。为了更准确地模拟职工年龄结构的变化,本文采用OLG方法,建立年龄变化相对稳定的职工人数递推模型。通过基期数据的对比检验,我们发现退休职工增速远大于正常的企业职工退休速度,参保职工人数测算口径偏小是造成这一现象的主要原因。     

Sociodemographic and Health-Related Risk Factors Among African-American,Caucasian and Hispanic Homeless Men: A Comparative Study

Data from a 1989-1990 cross-sectional survey of homeless adults in California were stratified by ethnicity to examine whether adverse childhood events and adult medical disorders preceding homelessness differed between 269 African-American, 599 Caucasian, 201 foreign-born Hispanic, and 136 native-born Hispanic men. Although African-Americans were overrepresented (21%) compared with their presence in local (3%) and state (7%) populations, within the homeless they were better educated and more likely to have held white collar jobs than Caucasians or Hispanics. In addition, despite being more likely to grow up in poverty, African-Americans reporled lower prevalences of alcohol and drug abuse, overnight psychiatric hospitalizations, placement in foster care, and physical or sexual abuse than Caucasians. Foreign-born Hispanics were the most likely to have low levels of education and job skills, but were least impaired by adult medical disorders. Native-born Hispanics reported lower rates of adverse childhood events, illegal drug use, and psychiatric hospitalizations than Caucasians, but were most likely among the three ethnic groups to suffer from alcohol abuse. The lower prevalences of adverse childhood events, addictive disorders, and psychiatric hospitalizations among homeless African-Americans, despite their higher representation in absolute numbers, suggests that factors such as childhood poverty may play a disproportionate role in homelessness among this ethnic minority group.     

Improving response to an establishment survey through the use of web-push data collection methods

ABSTRACT

The web-push method has been shown to increase web response rates in general public surveys. Response rates from two waves of the Emergency Medical Services for Children Program’s Performance Measures Survey, a state-administered establishment survey, were compared to determine if the second wave's revised, centralized implementation strategy improved response rates and consistency across states. The centralized strategy included the web-push design; a carefully timed contacts; and a three-month timeline. The results of the centralized web-push method included a higher overall response rate for a three-month period (81.0% compared to 56.6%) as well as greater consistency in results across states.     

Outlier Robust Small‐Area Estimation Under Spatial Correlation

Modern systems of official statistics require the estimation and publication of business statistics for disaggregated domains, for example, industry domains and geographical regions. Outlier robust methods have proven to be useful for small‐area estimation. Recently proposed outlier robust model‐based small‐area methods assume, however, uncorrelated random effects. Spatial dependencies, resulting from similar industry domains or geographic regions, often occur. In this paper, we propose an outlier robust small‐area methodology that allows for the presence of spatial correlation in the data. In particular, we present a robust predictive methodology that incorporates the potential spatial impact from other areas (domains) on the small area (domain) of interest. We further propose two parametric bootstrap methods for estimating the mean‐squared error. Simulations indicate that the proposed methodology may lead to efficiency gains. The paper concludes with an illustrative application by using business data for estimating average labour costs in Italian provinces.     

Adjusted Confidence Bands for Complex Survey Data

Confidence bands in nonparametric regression have been studied for a long time with data assumed to be generated from independent and identically distributed (iid) random variables. The methods and theoretical results for iid data, however, do not directly apply to data from stratified multistage samples. In this paper, we extend the confidence bands introduced by Zhang and Lu (2008 Zhang, G., Lu, Y. (2008). Adjusted confidence bands in nonparametric regression. Communications in Statistics-Simulation and Computation 37: 106–113.[Taylor &; Francis Online], [Web of Science ®] , [Google Scholar]) for iid case to complex surveys based on an entirely data-driven procedure; the proposed confidence bands incorporate both the sampling weights and the kernel weights. Simulation studies show that the proposed method works well.     

Two-sample Non Randomized Response Techniques for Sensitive Questions

The problem facing most researchers is how to encourage participants to respond, and then to provide truthful response in surveys with sensitive questions. In this article, we consider a non randomized triangular model for testing the equality of the proportions of people with a sensitive characteristic between two independent populations. We derive the Wald, score, and likelihood ratio tests. Their respective sample size formulae are developed as well. Simulation studies are conducted to evaluate the performance of the three proposed test procedures, which show that the score test outperforms the other two.     

Estimation of Population Means in Multivariate Stratified Random Sampling

In multivariate surveys where p (> 1) characteristics are defined on each unit of the population, the problem of allocation becomes complicated. In the present article, we propose a method to work out the compromise allocation in a multivariate stratified surveys. The problem is formulated as a Multiobjective Integer Nonlinear Programming Problem. Using the value function technique, the problem is converted into a single objective problem. A formula for continuous sample sizes is obtained using Lagrange Multipliers Technique (LMT) that can provide a near optimum solution in some cases. It may give an initial point for any integer nonlinear programing technique.     

A resampling approach to estimate variance components of multilevel models

In a multilevel model for complex survey data, the weight‐inflated estimators of variance components can be biased. We propose a resampling method to correct this bias. The performance of the bias corrected estimators is studied through simulations using populations generated from a simple random effects model. The simulations show that, without lowering the precision, the proposed procedure can reduce the bias of the estimators, especially for designs that are both informative and have small cluster sizes. Application of these resampling procedures to data from an artificial workplace survey provides further evidence for the empirical value of this method. The Canadian Journal of Statistics 40: 150–171; 2012 © 2012 Statistical Society of Canada     

Patterns of consent: evidence from a general household survey

Summary.  We analyse patterns of consent and consent bias in the context of a large general household survey, the 'Improving survey measurement of income and employment' survey, also addressing issues that arise when there are multiple consent questions. A multivariate probit regression model for four binary outcomes with two incidental truncations is used. We show that there are biases in consent to data linkage with benefit and tax credit administrative records that are held by the Department for Work and Pensions, and with wage and employment data held by employers. There are also biases in respondents' willingness and ability to supply their national insurance number. The biases differ according to the question that is considered. We also show that modelling questions on consent independently rather than jointly may lead to misleading inferences about consent bias. A positive correlation between unobservable individual factors affecting consent to Department for Work and Pensions record linkage and consent to employer record linkage is suggestive of a latent individual consent propensity.     

You are who remembers you. Detecting leadership through accuracy of recall

We measured interpersonal perception accuracy by focusing on the relationship between actors’ centrality and their ability to accurately report their social interactions. We used the network measures of actors’ betweenness centrality and degree centrality to identify the most prominent members by correlating ego-perception and alter-perception in a “non-reciprocity” type of misalignment. We found a positive correlation between actors’ centrality and their centrality as assessed by senior management, and a negative correlation between actors’ centrality and their accuracy in recalling interactions. Underreporting social interactions may represent a third way of measuring the importance of members and finding the most influential actors.