Analysis of clustered data in community psychology: With an example from a worksite smoking cessation project

Although it is common in community psychology research to have data at both the community, or cluster, and individual level, the analysis of such clustered data often presents difficulties for many researchers. Since the individuals within the cluster cannot be assumed to be independent, the use of many traditional statistical techniques that assumes independence of observations is problematic. Further, there is often interest in assessing the degree of dependence in the data resulting from the clustering of individuals within communities. In this paper, a random-effects regression model is described for analysis of clustered data. Unlike ordinary regression analysis of clustered data, random-effects regression models do not assume that each observation is independent, but do assume data within clusters are dependent to some degree. The degree of this dependency is estimated along with estimates of the usual model parameters, thus adjusting these effects for the dependency resulting from the clustering of the data. Models are described for both continuous and dichotomous outcome variables, and available statistical software for these models is discussed. An analysis of a data set where individuals are clustered within firms is used to illustrate fetatures of random-effects regression analysis, relative to both individual-level analysis which ignores the clustering of the data, and cluster-level analysis which aggregates the individual data. Preparation of this article was supported by National Heart, Lung, and Blood Institute Grant R18 HL42987-01A1, National Institutes of Mental Health Grant MH44826-01A2, and University of Illinois at Chicago Prevention Research Center Developmental Project CDC Grant R48/CCR505025.     

How Emotional Are Populists Really? Factors Explaining Emotional Appeals in the Communication of Political Parties

Are populists really more emotional than mainstream parties? The alleged link between populism and emotional communication has barely been subject to systematic empirical scrutiny. I use literature on populist communication and appraisal theory to generate expectations about which political parties use which emotional appeals. I test these claims by applying a novel emotional dictionary to a large set of text data including more than 700,000 press releases and tweets from three European countries. As expected, I find that populist parties use significantly more negative emotional appeals (anger, fear, disgust, sadness) and less positive emotional appeals (joy, enthusiasm, pride, hope) than mainstream parties. Furthermore, I find that political actors adapt the usage of emotional appeals to different purposes depending on the communication medium and the politicians' status level. This study entails important implications for the research on emotional appeals in politics and populist communication.     

A Gibbs sampler for the multidimensional four-parameter logistic item response model via a data augmentation scheme

The four-parameter logistic (4PL) item response model, which includes an upper asymptote for the correct response probability, has drawn increasing interest due to its suitability for many practical scenarios. This paper proposes a new Gibbs sampling algorithm for estimation of the multidimensional 4PL model based on an efficient data augmentation scheme (DAGS). With the introduction of three continuous latent variables, the full conditional distributions are tractable, allowing easy implementation of a Gibbs sampler. Simulation studies are conducted to evaluate the proposed method and several popular alternatives. An empirical data set was analysed using the 4PL model to show its improved performance over the three-parameter and two-parameter logistic models. The proposed estimation scheme is easily accessible to practitioners through the open-source IRTlogit package.     

Traiter ses données proprement : vers un meilleur usage du data cleaning

Data cleaning has long been shown to be an essential step in data analysis but its application is not systematic and varies between researchers. The aim of the present article is to study the effect of the different elements of data cleaning and to give recommendations. The steps considered are normality, outliers and missing values. Firstly, we advise a close examination of the data and its normality with a view to transformation. Secondly, we look at outliers and their treatment (trimming and winsorizing). Lastly, we turn our attention to missing values and how to deal with them depending on their randomness. We also cover the importance of visualizing data before analysis. Finally, we illustrate the effect of these data cleaning practices on a real data set. We show that data cleaning can lead to a significant result becoming non-significant and therefore demonstrate the importance of these steps before starting data analysis.     

The development and validation of the Privacy and Data Security Concerns Scale (PDSCS)

This study describes the development and validation of the Privacy and Data Security Concerns Scale (PDSCS), designed to assess job applicants’ privacy and data security concerns. Validity evidence for the PDSCS was established with four steps including: item generation and content validation, item reduction, confirmatory factor analysis, and construct and criterion validity. Our findings supported the content and proposed factor structure of the nine‐item PDSCS. Specifically, the proposed three‐factor structure (with the subdimensions: Secure connection, inappropriate use of information, and mistrust in employer security practices) as well as a second‐order factor, (termed privacy and data security concerns) were confirmed. Additionally, evidence is presented for the criterion validity of the PDSCS and its subdimensions.     

Using bifactor models to identify faking on Big Five questionnaires

To identify faking, bifactor models were applied to Big Five personality data in three studies of laboratory and applicant samples using within‐subjects designs. The models were applied to homogenous data sets from separate honest, instructed faking, applicant conditions, and to simulated applicant data sets containing random individual responses from honest and faking conditions. Factor scores from the general factor in a bifactor model were found to be most highly related to response condition in both types of data sets. Domain factor scores from the faking conditions were found less affected by faking in measurement of Big Five domains than summated scale scores across studies. We conclude that bifactor models are efficacious in assessing the Big Five domains while controlling for faking.     

Exploring the interactions between modal options,destination access,and travel mood

A good understanding of subjectively experienced well-being in daily travel is critical for the design and evaluation of transportation policies and programs. Numerous studies have examined the relationship between how we travel and how we feel during travel. However, people’s travel mood is not only determined by their trip characteristics but also their potential mobility—the capacity of being mobile. Using the data collected via a smartphone application in Minneapolis-St. Paul area, we measure potential mobility in two aspects—modal options and destination access and reveal that people in households with better access to cars and alternative transportation modes are, all else equal, more likely to report more positive moods and fewer negative moods during travel. In addition, people living in neighborhoods with greater access to destinations are less likely to feel stress when traveling. We also find that associations between mode and mood are moderated by modal options and destination access. These findings confirm the importance of explicitly considering modal options and destination access in policy debates and planning initiatives addressing transportation and well-being. In doing so, they demonstrate the relevance of Sen’s Capabilities Approach to transportation planning.     

Adaptive sampling for active learning with genetic programming

Active learning is a machine learning paradigm allowing to decide which inputs to use for training. It is introduced to Genetic Programming (GP) essentially thanks to the dynamic data sampling, used to address some known issues such as the computational cost, the over-fitting problem and the imbalanced databases. The traditional dynamic sampling for GP gives to the algorithm a new sample periodically, often each generation, without considering the state of the evolution. In so doing, individuals do not have enough time to extract the hidden knowledge. An alternative approach is to use some information about the learning state to adapt the periodicity of the training data change. In this work, we propose an adaptive sampling strategy for classification tasks based on the state of solved fitness cases throughout learning. It is a flexible approach that could be applied with any dynamic sampling. We implemented some sampling algorithms extended with dynamic and adaptive controlling re-sampling frequency. We experimented them to solve the KDD intrusion detection and the Adult incomes prediction problems with GP. The experimental study demonstrates how the sampling frequency control preserves the power of dynamic sampling with possible improvements in learning time and quality. We also demonstrate that adaptive sampling can be an alternative to multi-level sampling. This work opens many new relevant extension paths.     

问卷数据建模的前传

问卷法是一种常见的实证研究方法。问卷数据建模的前期工作,就像是一栋大楼的奠基工程,基础是否扎实,影响后续的工程质量。本文专门讨论统计模型建立之前要做的事情（重点是量表评价）,内容包括：处理缺失值、评价量表的结构效度和题目删除的适当性、多维量表需要合成总分时检验同质性并计算合成信度、检验共同方法偏差和评价（变量）区分效度、题目打包、检验自变量的多重共线性,最后也涉及建模理据和无关变量控制等。     

Estimation of a Latent Variable Regression Growth Curve Model for Individuals Cross-Classified by Clusters

The cross-classified multiple membership latent variable regression (CCMM-LVR) model is a recent extension to the three-level latent variable regression (HM3-LVR) model which can be utilized for longitudinal data that contains individuals who changed clusters over time (for instance, student mobility across schools). The HM3-LVR model can include the initial status on growth effect as varying across those clusters and allows testing of more flexible hypotheses about the influence of initial status on growth and of factors that might impact that relationship, but only in the presence of pure clustering of participants within higher-level units. This Monte Carlo study was conducted to evaluate model estimation under a variety of conditions and to measure the impact of ignoring cross-classified data when estimating the incorrectly specified HM3-LVR model in a scenario in which true values for parameters are known. Furthermore, results from a real-data analysis were used to inform the design of the simulation. Overall, it would be recommended for researchers to utilize the CCMM-LVR model over the HM3-LVR model when individuals are cross-classified, and to use a bare minimum of more than 100 clustering units in order to avoid overestimation of the level-3 variance component estimates.