A5061913766- Statistical Methods and Bayesian Inference
- Survey Methodology and Nonresponse
- Psychometric Methodologies and Testing
- Advanced Causal Inference Techniques
- Machine Learning in Healthcare
- Statistical Methods and Inference
- Mental Health Research Topics
- Urban, Neighborhood, and Segregation Studies
- Biomedical Text Mining and Ontologies
- Topic Modeling
- Data Quality and Management
- Social Capital and Networks
- Advanced Statistical Methods and Models
- Bayesian Modeling and Causal Inference
- Health disparities and outcomes
- Spatial and Panel Data Analysis
- Privacy-Preserving Technologies in Data
- Social and Intergroup Psychology
- Survey Sampling and Estimation Techniques
- Personality Traits and Psychology
- Computational and Text Analysis Methods
- Electoral Systems and Political Participation
- Cultural Differences and Values
- Meta-analysis and systematic reviews
- Advanced Statistical Modeling Techniques
Utrecht University
2016-2024
University Medical Center Utrecht
2020-2024
Heidelberg University
2023
University Hospital Heidelberg
2023
Max Planck Institute for Biology of Ageing
2019
Humboldt-Universität zu Berlin
2019
Max Planck Institute for Human Development
2019
Tilburg University
2011-2018
Institut Barcelona d'Estudis Internacionals
2014
University of Westminster
2014
This paper introduces the R package lavaan.survey, a user-friendly interface to design-based complex survey analysis of structural equation models (SEMs). By leveraging existing code in lavaan and packages, lavaan.survey allows for SEM analyses stratified, clustered, weighted data, as well multiply imputed data. provides several features such SEMs with replicate weights, variety resampling techniques samples, finite population corrections, that should prove useful practitioners faced common...
Using data from 2 large and overlapping cohorts of Dutch adolescents, containing up to 7 waves longitudinal each (N = 2,230), the present study examined Big Five personality trait stability, change, codevelopment in friendship sibling dyads age 12 22. Four findings stand out. First, 1-year rank-order stability traits was already substantial at 12, increased strongly early through middle adolescence, remained rather stable during late adolescence adulthood. Second, we found linear mean-level...
Conducting a systematic review demands significant amount of effort in screening titles and abstracts. To accelerate this process, various tools that utilize active learning have been proposed. These allow the reviewer to interact with machine software identify relevant publications as early possible. The goal study is gain comprehensive understanding models for reducing workload reviews through simulation study.
Personal growth initiative (PGI), defined as being proactive about one's personal development, is critical to graduate students' academic success. Prior research has shown that PGI can be enhanced through interventions focus on stimulating developmental activities. Within this study, we aimed investigate whether an intervention stimulates development in the area of strengths (strengths intervention) more beneficial effects than individual deficiencies (deficiency intervention). We conducted...
Bayesian structural equation modeling (BSEM) has recently gained popularity because it enables researchers to fit complex models and solve some of the issues often encountered in classical maximum likelihood estimation, such as nonconvergence inadmissible solutions. An important component any analysis is prior distribution unknown model parameters. Often, rely on default priors, which are constructed an automatic fashion without requiring substantive information. However, can have a serious...
Contextual theories of political behaviour assert that the contexts in which people live influence their beliefs and vote choices. Most studies, however, fail to distinguish contextual from self-selection individuals into areas. This article advances understanding this controversy by tracking left–right position party identification thousands over an eighteen-year period England before after residential moves across areas with different orientations. There is evidence both non-random...
Latent class analysis is used in the political science literature both substantive applications and as a tool to estimate measurement error. Many studies social sciences relate estimated assignments from latent model external variables. Although common, such “three-step” procedure effectively ignores classification error assignments; Vermunt (2010, “Latent modeling with covariates: Two improved three-step approaches,” Political Analysis 18:450–69) showed that this leads inconsistent...
Greenness in the urban living environment is inconsistently associated with mental health. Satellite-derived measures of greenness may inadequately characterize how people encounter visually on site, but systematic comparisons are lacking. We aimed 1) to compare associations between remotely sensed and street view (SV) greenness, 2) examine whether these metrics differently health outcomes. used cross-sectional depressive anxiety symptoms data adults Amsterdam, Netherlands. employed a...
Welzel et al. (2021) claim that non-invariance of instruments is inconclusive and inconsequential in the field for cross-cultural value measurement. In this response, we contend several key arguments on which base their critique invariance testing are conceptually statistically incorrect. First, measurement follows a formative rather than reflective logic. Yet they do not provide sufficient theoretical conceptualization, nor discuss disadvantages approach validation instruments. Second,...
Latent variable models can only be compared across groups when these exhibit measurement equivalence or “invariance,” since otherwise substantive differences may confounded with differences. This article suggests examining directly whether present could confound analyses, by the expected parameter change (EPC)-interest. The EPC-interest approximates in parameters of interest that freeing cross-group invariance restrictions. Monte Carlo simulations suggest changes well. Three empirical...
Current approaches to model responses and response times psychometric tests solely focus on between-subject differences in speed ability. Within subjects, ability are assumed be constants. Violations of this assumption generally absorbed the residual model. As a result, within-subject departures from level remain undetected. These may interest researcher as they reflect processes adopted items test. In article, we propose dynamic approach for based hidden Markov modeling account times. A...
To help researchers conduct a systematic review or meta-analysis as efficiently and transparently possible, we designed tool (ASReview) to accelerate the step of screening titles abstracts. For many tasks - including but not limited reviews meta-analyses scientific literature needs be checked systematically. Currently, scholars practitioners screen thousands studies by hand determine which include in their meta-analysis. This is error prone inefficient because extremely imbalanced data: only...
A potentially powerful method of social-scientific data collection and investigation has been created by an unexpected institution: the law. Article 15 EU’s 2018 General Data Protection Regulation (GDPR) mandates that individuals have electronic access to a copy their personal data, all major digital platforms now comply with this law providing users “data download packages” (DDPs). Through voluntary donation DDPs, collected public private entities during course citizens’ life can be...
Abstract Background In recent years, human microbiome studies have received increasing attention as this field is considered a potential source for clinical applications. With the advancements in omics technologies and AI, research focused on discovery biomarkers using machine learning tools has produced positive outcomes. Despite promising results, several issues can still be found these such datasets with small number of samples, inconsistent lack uniform processing methodologies, other...
In most medical research, treatment effectiveness is assessed using the average effect or some version of subgroup analysis. The practice individualized precision medicine, however, requires new approaches that predict how an individual will respond to treatment, rather than relying on aggregate measures effect. this study, we present a conceptual framework for estimating effects, referred as predicted effects. We first apply approach randomized controlled trial designed improve behavioral...
Latent Markov models with covariates can be estimated via 1-step maximum likelihood. However, this approach has various disadvantages, such as that the inclusion of in model might alter formation latent states and parameter estimation could become infeasible large numbers time points, responses, covariates. This is why researchers typically prefer performing analysis a stepwise manner; is, they first construct measurement model, then obtain state classifications, subsequently study...
BackgroundConducting a systematic review requires great screening effort. Various tools have been proposed to speed up the process of thousands titles and abstracts by engaging in active learning. In such tools, reviewer interacts with machine learning software identify relevant publications as early possible. To gain comprehensive understanding models for reducing workload reviews, current study provides methodical overview models. Active were evaluated across four different classification...
Fake news is a threat to society. A huge amount of fake posted every day on social networks which read, believed and sometimes shared by number users. On the other hand, with aim raise awareness, some users share posts that debunk using information from fact-checking websites. In this paper, we are interested in exploring role various psycholinguistic characteristics differentiating between tend them. Psycholinguistic represent different linguistic can be used profile extracted or inferred...
While electrocardiogram (ECG) characteristics have been associated with life-threatening ventricular arrhythmias (LTVA) in dilated cardiomyopathy (DCM), they typically rely on human-derived parameters. Deep neural networks (DNNs) can discover complex ECG patterns, but the interpretation is hampered by their 'black-box' characteristics. We aimed to detect DCM patients at risk of LTVA using an inherently explainable DNN.
Latent class analysis (LCA) for categorical data is a model-based clustering and classification technique applied in wide range of fields including the social sciences, machine learning, psychiatry, public health, epidemiology. Its central assumption conditional independence indicators given latent class, i.e. "local independence"; violations can appear as model misfit, often leading LCA practitioners to increase number classes. However, when not all local dependence substantive scientific...