Assessment of Multiple Membership Multilevel Models: An Application to Interviewer Effects on Nonresponse

Multilevel multiple membership models account for situations where lower level units are nested within multiple higher level units from the same classification. Not accounting correctly for such multiple membership structures leads to biased results. The use of a multiple membership model requires selection of weights reflecting the hypothesized contribution of each level two unit and their relationship to the level one outcome. The Deviance Information Criterion (DIC) has been proposed to identify such weights. For the case of logistic regression, this study assesses, through simulation, the model identification rates of the DIC to detect the correct multiple membership weights, and the properties of model variance estimators for different weight specifications across a range of scenarios. The study is motivated by analyzing interviewer effects across waves in a longitudinal study. Interviewers can substantially influence the behavior of sample survey respondents, including their decision to participate in the survey. In the case of a longitudinal survey several interviewers may contact sample members to participate across different waves. Multilevel multiple membership models are suitable to account for the inclusion of higher-level random effects for interviewers at various waves, and to assess, for example, the relative importance of previous and current wave interviewers on current wave nonresponse. To illustrate the application, multiple membership models are applied to the UK Family and Children Survey to identify interviewer effects in a longitudinal study. The paper takes a critical view on the substantive interpretation of the model weights and provides practical guidance to statistical modelers. The main recommendation is that it is best to specify the weights in a multiple membership model by exploring different weight specifications based on the DIC, rather than prespecifying the weights.     

Unemployed people in search of a job: Reconsidering the role of search behavior

A three-wave longitudinal study of unemployed persons in Croatia was used to examine the antecedents of job-seeking behavior and reemployment. A series of demographic, motivational and job-constraint variables were posited to influence job-seeking behavior, which, in turn, was hypothesized to affect (re)employment. The participants were surveyed in 2003 (N = 1138), and their employment status was checked in 2004 (N = 601) and 2005 (N = 452). Regression analyzes supported only one slice of the model—the antecedent-job-search relations. All motivational variables, in particular employment commitment and perceived financial strain, proved to be relatively strong predictors of job-search intensity. However, they appeared to be only weakly related to the (re)employment outcome. Demographic variables—in particular education, age, and employment duration—appeared to be the main determinants of (re)employment, operating presumably through their influence on employers’ hiring decisions. It was suggested that existing theory and heuristic frameworks overstate the importance of job-seeking activity. Further research is suggested to examine why purposeful and proactive job searching does not pay more.     

跨期选择的性质探索

跨期选择指人们对发生在不同时间点的价值做出的权衡与决策。大量研究证明, 跨期选择中人们存在普遍的时间折扣倾向, 即将未来的价值折扣后与当前价值进行权衡。跨期选择研究不仅与人类心智的起源与机制等基础科学问题密切相关, 也关系到国家公共政策的制定等现实问题。本项目拟采用实验室研究和大规模问卷调查结合的方法, 深入探索跨期选择的本质。一方面, 采用实验室研究法探讨影响跨期选择的重要因素, 以探索：(1) 跨期选择的效价及其与价值数量、延迟时间的交互作用及其心理机制; (2) 跨期选择中是否存在领域特异性及其心理机制; 另一方面, 通过全国范围的调查, 从而：(1) 建立中国城镇居民时间折扣率的常模; (2) 测量不同类型人群的时间折扣率, 以探讨跨期选择的性质与内涵。项目研究结果将有利于加深学界对跨期选择现象的理解。     

地方高校新生UPI调查结果的比较与分析

对多所地方高皎新生UPI调查的筛选率、自杀意念、主要心理症状的选择率进行比较,发现：一类学生的筛选率分布在6．3％-40．08％之间,曾有自杀意念者在0．66％-3．30％之间．学校之间差异显著;主要心理问题有情绪和性格问题、强迫倾向、人际关系障碍等,在主要心理问题的性质上各有较高的一致性、仅在个别项目上和选择率上存在差异;从整体看师范与非师范之间、本科与专科之间并无规律性差别,论文还就各校测量结果的差异性与一致性的原因及高校UPI稠查与研究中存在的主要问题进行了讨论。     

Population sex differences in IQ at age 11: the Scottish mental survey 1932

There is uncertainty whether the sexes differ with respect to their mean levels and variabilities in mental ability test scores. Here we describe the cognitive ability distribution in 80,000+ children—almost everyone born in Scotland in 1921—tested at age 11 in 1932. There were no significant mean differences in cognitive test scores between boys and girls, but there was a highly significant difference in their standard deviations (P<.001). Boys were over-represented at the low and high extremes of cognitive ability. These findings, the first to be presented from a whole population, might in part explain such cognitive outcomes as the slight excess of men achieving first class university degrees, and the excess of males with learning difficulties.     

Counselling students' views and concerns about weeping with clients: A pilot study

This study examines counselling students' concerns and views about a phenomenon that has received little attention in the counselling literature: the counsellor weeping during a session with a client. Over 20 per cent of the counselling students who were surveyed reported being concerned about weeping in session with clients. However, the majority of students believed, to varying degrees, that weeping with clients could facilitate the therapeutic process. This paper sheds light on this unexplored dimension of countertransference, and has implications for those involved in providing counsellor training.     

Evaluating the Distorting Effects of Inattentive Responding and Social Desirability on Self‐Report Scales in Creativity and the Arts

Inattentiveness and social desirability might be particularly problematic for self‐report scales in creativity and arts research. Respondents who are inattentive or who present themselves favorably will score highly on scales that yield positively skewed distributions and that assess socially valued constructs, such as scales measuring creativity and arts knowledge. A total of 204 undergraduates completed an online survey with several self‐report measures (the Creative Achievement Questionnaire, the Biographical Inventory of Creative Behavior, and the Aesthetic Fluency Scale). Many metrics of inattentiveness were included, such as directed response items, self‐reported attentiveness, and scales to catch inconsistent and patterned responses. The Balanced Inventory of Desirable Responding measured facets of social desirability. We found high rates of inattentive responding. A latent class analysis indicated that around 25% of the sample was potentially inattentive, and inattentive respondents received higher scores on the creativity and arts scales. Excluding problematic participants increased the effect sizes of interest, consistent with the coarsening effect of careless participants. Social desirability, in contrast, had essentially no relationship with the creativity and arts scales. These findings suggest that social desirability is probably less of a problem than researchers fear, but that inattentiveness is an underappreciated threat. Some practical guidelines are suggested.