About

Zita Oravecz is an Assistant Professor of Human Development & Family Studies and a Graduate Faculty member in Social Data Analytics at Pennsylvania State University. She is also a C-SoDA Faculty Affiliate. Her primary research interest lies in studying individual differences from a process modeling perspective, with a focus on emotion and cognition. She aims to develop and apply advanced statistical approaches, particularly within the Bayesian framework, to analyze complex data that would be difficult to study using traditional methods. Her work includes developing models such as the Ornstein-Uhlenbeck process to describe temporal changes in psychologically meaningful parameters and creating multivariate versions of these models to capture changes and synchronicity in different aspects of well-being over time. She is especially interested in how Bayesian methods can be used for the analysis of continuously streaming data from sources like social media and health monitors, enabling continuous inference from large volumes of data through sequential updating routines.

Research topics

• Computer Science
• Psychology
• Artificial Intelligence
• Developmental psychology
• Psychotherapist
• Embedded system
• World Wide Web
• Data science
• Statistics
• Social psychology
• Human–computer interaction
• Cognitive psychology

Selected publications

• Mitigating Retest Effects in Cognitive Ecological Momentary Assessment Data - A Tutorial in PyMC, Stan and JAGS

  2026-03-20

  articleOpen accessSenior author

  This tutorial provides a comprehensive, step-by-step guide for implementing the Bayesian Double Exponential Model (BDEM) in PyMC, Stan, and JAGS. The BDEM is a statistical framework designed to disentangle retest (practice) effects from true longitudinal cognitive change in high-frequency Ecological Momentary Assessment (EMA) and measurement burst designs. We highlight the unique features of the three approaches in terms of accessibility, flexibility, sampling algorithms, and computational time, focusing on their practical implications for implementing complex hierarchical models. A simulation study was conducted to evaluate the performance of these software programs across both small and large sample sizes. Results indicated that while all three programs successfully recover most model parameters, Stan yielded the highest sampling quality, whereas JAGS offered the lowest computational time under the same MCMC settings (e.g., number of total iterations). Learning rates remained the most challenging features to estimate, particularly in small samples. This tutorial equips researchers with the necessary tools to apply advanced multilevel cognitive modeling to high-frequency cognitive assessments in measurement burst designs.

  PublisherDOI

• Mitigating Retest Effects in Cognitive Ecological Momentary Assessment Data - A Tutorial in PyMC, Stan and JAGS

  PsyArXiv (OSF Preprints) · 2026-03-31

  preprintOpen access

  This tutorial provides a comprehensive, step-by-step guide for implementing the Bayesian Double Exponential Model (BDEM) in PyMC, Stan, and JAGS. The BDEM is a statistical framework designed to disentangle retest (practice) effects from true longitudinal cognitive change in high-frequency Ecological Momentary Assessment (EMA) and measurement burst designs. We highlight the unique features of the three approaches in terms of accessibility, flexibility, sampling algorithms, and computational time, focusing on their practical implications for implementing complex hierarchical models. A simulation study was conducted to evaluate the performance of these software programs across both small and large sample sizes. Results indicated that while all three programs successfully recover most model parameters, Stan yielded the highest sampling quality, whereas JAGS offered the lowest computational time under the same MCMC settings (e.g., number of total iterations). Learning rates remained the most challenging features to estimate, particularly in small samples. This tutorial equips researchers with the necessary tools to apply advanced multilevel cognitive modeling to high-frequency cognitive assessments in measurement burst designs.

  Publisher

• Simultaneous detection of gradual and abrupt structural changes in Bayesian longitudinal modelling using entropy and model fit measures

  British Journal of Mathematical and Statistical Psychology · 2026-01-07 · 1 citations

  articleOpen access

  Although individuals may exhibit both gradual and abrupt changes in their dynamic properties as shaped by both slowly accumulating influences and acute events, existing statistical frameworks offer limited capacity for the simultaneous detection and representation of these distinct change patterns. We propose a Bayesian regime-switching (RS) modelling framework and an entropy measure adapted from the frequentist framework to facilitate simultaneous representation and testing of postulates of gradual and abrupt changes. Results from Monte Carlo simulation studies indicated that using a combination of entropy and information criterion measures such as the Bayesian information criterion was consistently most effective at facilitating the selection of the best-fitting model across varying magnitudes of abrupt changes. We found that slight lower entropy thresholds may be helpful in facilitating the selection of longitudinal models with RS properties as this class of models tended to yield lower entropy values than conventional thresholds for reliable classification in cross-sectional mixture models-even under satisfactory parameter recovery and classification results. We fitted the proposed models and other candidate models to the data collected from an intervention study on the psychological well-being (PWB) of college-attending early adults. Results suggested abrupt, regime-related transitions in the intra-individual variability levels of PWB dynamics among some participants following the intervention period. Practical usage of the entropy measure in conjunction with other model selection measures, and guidelines to enhance simultaneous detection of true abrupt and gradual changes are discussed.

  PublisherDOI

• Mitigating Retest Effects in Cognitive Ecological Momentary Assessment Data - A Tutorial in PyMC, Stan and JAGS

  PsyArXiv (OSF Preprints) · 2026-03-19

  preprintOpen access1st authorCorresponding

  This tutorial provides a comprehensive, step-by-step guide for implementing the Bayesian Double Exponential Model (BDEM) in PyMC, Stan, and JAGS. The BDEM is a statistical framework designed to disentangle retest (practice) effects from true longitudinal cognitive change in high-frequency Ecological Momentary Assessment (EMA) and measurement burst designs. We highlight the unique features of the three approaches in terms of accessibility, flexibility, sampling algorithms, and computational time, focusing on their practical implications for implementing complex hierarchical models. A simulation study was conducted to evaluate the performance of these software programs across both small and large sample sizes. Results indicated that while all three programs successfully recover most model parameters, Stan yielded the highest sampling quality, whereas JAGS offered the lowest computational time under the same MCMC settings (e.g., number of total iterations). Learning rates remained the most challenging features to estimate, particularly in small samples. This tutorial equips researchers with the necessary tools to apply advanced multilevel cognitive modeling to high-frequency cognitive assessments in measurement burst designs.

  Publisher

• What makes older adults feel loved? The shared agreement on expressions of love in daily life and individual differences in the consensus judgments among older adults

  2025-03-25

  preprintOpen accessSenior author

  Social connection is a key ingredient for healthy aging; however, the specific experiencesof daily living that make most older adults feel loved have not been studiedsystematically. To fill this gap, we surveyed a representative sample (N=408) of USadults over 65 years of age. They were asked to judge 61 everyday life experiencesfor their potential to generate loving feelings. We applied Cultural Consensus Theoryto uncover the shared agreement on expressions of love among older adults andtested whether there was a consensus among them. We identified the daily life experiencesthat older adults believe make most people feel loved and found that therewas a shared agreement on these. However, participants differed in terms of theirknowledge of the shared agreement: higher levels of consensus knowledge on dailylife experiences of love were credibly linked to higher levels of compassion and beingfemale.

  PublisherOA PDFDOI

• Computational Phenotyping of Cognitive Decline With Retest Learning

  The Journals of Gerontology Series B · 2025-02-17 · 5 citations

  articleOpen access1st authorCorresponding

  OBJECTIVES: Cognitive change is a complex phenomenon encompassing both retest-related performance gains and potential cognitive decline. Disentangling these dynamics is necessary for effective tracking of subtle cognitive change and risk factors for Alzheimer's Disease and Related Dementias (ADRD). METHOD: We applied a computational cognitive model of learning and forgetting to data from Einstein Aging Study (EAS; n = 316). EAS participants completed multiple bursts of ultra-brief, high-frequency cognitive assessments on smartphones. Analyzing response time data from a measure of visual short-term working memory, the Color Shapes task, and from a measure of processing speed, the Symbol Search task, we extracted several key cognitive markers: short-term intraindividual variability in performance, within-burst retest learning and asymptotic (peak) performance, across-burst change in asymptote and forgetting of retest gains. RESULTS: Asymptotic performance was related to both mild cognitive impairment (MCI) and age, and there was evidence of asymptotic slowing over time. Long-term forgetting, learning rate, and within-person variability uniquely signified MCI, irrespective of age. DISCUSSION: Computational cognitive markers hold promise as sensitive and specific indicators of preclinical cognitive change, aiding risk identification and targeted interventions.

  PublisherOA PDFDOI

• Partially observable predictor models for identifying cognitive markers

  2025-03-05

  preprintOpen access1st authorCorresponding

  Repeated assessments of cognitive performance yield rich data from which we can extract markers of cognitive performance. Computational cognitive process models are often fit to repeated cognitive assessments to quantify individual differences in terms of substantively meaningful cognitive markers and link them to other person-level variables. Most studies stop at this point, and do not test whether these cognitive markers have utility for predicting some meaningful outcomes. Here, we demonstrate a partially observable predictor modeling framework that can fill this gap. In this framework, we can simultaneously extract cognitive markers from repeated assessment data and use these together with demographic covariates for predictive modeling of a clinically interesting outcome, implemented in a Bayesian multilevel modeling framework. We describe this approach by constructing a predictive process model in which features of learning are combined with demographic variables to predict mild cognitive impairment, and demonstrate it using data from the Einstein Aging Study.

  PublisherOA PDFDOI

• Current Methodological Approaches for Studying the Association Between Love and Psychological Well-Being in Daily Life

  2025-01-01

  book-chapterSenior author
  PublisherDOI

• Current Methodological Approaches for Studying the Association Between Love and Psychological Well-Being in Daily Life

  2025-01-01

  book-chapterSenior author
  PublisherDOI

• Optimizing the Color Shapes Task for Ambulatory Assessment and Drift Diffusion Modeling: A Factorial Experiment

  JMIR Formative Research · 2025-07-14

  articleOpen accessSenior author

  BACKGROUND: Recent advances in cognitive digital assessment methodology, including high-frequency, ambulatory assessments, promise to improve the detection of subtle cognitive changes. Computational modeling approaches may further improve the sensitivity of digital cognitive assessments to detect subtle cognitive changes by capturing features that map onto core cognitive processes. OBJECTIVE: We explored the validity of a brief smartphone-based adaptation of a visual working memory task that has shown sensitivity for detecting preclinical Alzheimer disease risk. We aimed to optimize properties of the task for computational cognitive feature extraction with drift diffusion modeling. METHODS: We analyzed data from 68 participants (n=47, 69% women; n=55, 81% White; mean age 49, SD 14; range 24-80 years) who completed 60 trials for each of 16 variations of a visual working memory binding task (the Color Shapes task) on smartphones, over an 8-day period. A drift diffusion model was fit to the response time and accuracy data from the task. We experimentally manipulated 3 properties of the Color Shapes task (study time, probability of change, and choice urgency) to test how they yielded differences in key drift diffusion model parameters (drift rate, initial bias toward a response option, and caution in decision-making). We also evaluated how an additional task property, the test array size, impacted responses across all conditions. For array size, we tested a whole display of 3 shapes against a single probe of 1 shape only. RESULTS: The 3 task property manipulations yielded the following results: (1) increasing the ratio of different responses was credibly associated with higher initial bias toward the different response (mean 0.06, SD 0.02 for the whole display; mean 0.15, SD 0.02, for the single probe condition); (2) increasing the choice urgency during the test phase was credibly associated with decreased caution in decision-making in the single probe condition (mean -0.04, SD 0.02) but not in the whole display (mean -0.01, SD 0.02); and (3) contrary to expectation, longer study times did not yield a credibly faster drift rate but produced credibly slower ones for the whole display condition (mean -0.28, SD 0.05) and a null effect for the single probe condition (mean 0.01, SD 0.05). In addition, as expected, we found that individual differences in drift rate were associated with age in both array sizes (r=-0.45 with Bayes factor=191), with older participants having a slower drift rate. Older participants also showed higher caution (r=0.42 with Bayes factor=80.76) in the single probe condition. CONCLUSIONS: We identified a version of the Color Shapes task optimized for smartphone-based cognitive assessments in real-world settings, with data designed for analysis through computational cognitive modeling. Our proposed approach can advance the development of tools for efficient and effective early detection and monitoring of risk for Alzheimer disease.

  PublisherDOI

Frequent coauthors

• Joachim Vandekerckhove

  27 shared

• Sy‐Miin Chow

  Pennsylvania State University

  18 shared

• Saeideh Heshmati

  Claremont Graduate University

  17 shared

• Yanling Li

  14 shared

• Timothy R. Brick

  Pennsylvania State University

  14 shared

• Francis Tuerlinckx

  KU Leuven

  9 shared

• Robert W. Roeser

  9 shared

• Chelsea Muth

  Claremont Graduate University

  8 shared

Labs

• Social Data AnalyticsPI

Education

• Postdoc, Cognitive Sciences

  University of California Irvine

  2014

• Postdoc, Psychology and Educational Sciences

  University of Leuven

  2011

• PhD - Quantitative Psychology, Psychology and Education Sciences

  University of Leuven

  2009