💡 Research
My research aims to bridge methodological innovation, artificial intelligence, and precision health, organized around three interconnected pillars:
Advancing Methodology for Intensive Longitudinal Data. I develop and refine statistical models to address core challenges in intensive longitudinal data (ILD), such as time-related issues, dynamic bidirectional modeling, and the modeling and evaluation of intensive longitudinal interventions (e.g., just-in-time adaptive interventions).
Integrating Machine Learning and LLMs into Dynamic Analysis. I am actively extending my methodological toolkit by incorporating machine learning and large language models (LLMs) into ILD frameworks. My focus is on leveraging multimodal ILD (e.g., integrating self-reports with digital phenotyping, text, audio, and video data) to build LLM-based multi-agent systems capable of AI-driven conversational screening and diagnosis, real-time risk prediction and automated insight generation.
Translating Methods into Clinical-Health Applications. This line of research applies intensive longitudinal data analysis methods to tackle practical problems in health, clinical, and developmental psychology. It also involves collaborative efforts aimed at identifying real-world challenges and addressing them through joint projects.
🚀 Publication Highlights
20 peer-reviewed articles (15 first-authored, 5 second-authored)
First-authored papers published in
Methodological journals:
- Psychological Methods [IF: 7.5/11.5, Q1]
- Behavior Research Methods [IF: 5/7.2, Q1]
- Multivariate Behavioral Research [IF: 3.5/6, Q1]
- Structural Equation Modeling: A Multidisciplinary Journal [IF: 3.5/5.8, Q1]
- Psychometrika [IF: 2.9/4.1, Q1]
Substantive journals:
- Accident Analysis and Prevention [IF: 7.4/8, Q1]
- Journal of Youth and Adolescence [IF: 4.5/5.9, Q1]
- Mindfulness [IF: 4.1/4.9, Q1]
- Assessment [IF: 3/4.9, Q2]
- Health Psychology [IF: 2.9/3.9, Q2]
✚ 3 first-authored manuscripts under review/in revision/revised & resubmit
Notes: IF = impact factor [for 2025 / the past five years]; *corresponding author(s); +co-first authors.
Peer‐Reviewed Articles
- Luo, X.+, Dong, J.+, Liu, H.*, Liu, Y., & Merkle, E. C. (2026). Bayesian evaluation for latent variable models: A tutorial on computing information criteria and bayes factors with the R package bleval. Psychological Methods. [doi] [IF: 7.5/11.5, Q1]
- Luo, X., Hu, Y.*, Liu, H.*, & Liu, Y. (2026). Enhancing two-stage estimation in differential equation models: A bias correction method via stochastic approximation. Psychometrika. Advanced Online Publication. [doi] [IF: 2.9/4.1, Q1]
- Luo, X., Hu, Y.*, & Liu, H.* (2025). Timescale mismatch in intensive longitudinal data: Current issues and possible solutions based on dynamic structural equation models. Psychological Methods. Advanced Online Publication. [doi] [IF: 7.5/11.5, Q1]
Click to expand for more details
- Download the full article : Download PDF
- Open Data & Code : OSF Repository
- Luo, X., Hu, Y.*, & Liu, H.* (2025). Dynamic prediction of depressive states using stress processes: A multilevel decision tree approach. Acta Psychologica Sinica (心理学报), 57(8), 1363–1377. [doi]
Click to expand for more details
- Open Data & Code : OSF Repository
- Download the full article : Download PDF
- Luo, X., Liu, Y.*, & Liu, H.* (2025). Incorporating qualitative distinctions in within-person effect analyses [Abstract]. Multivariate Behavioral Research, 60(1), 21–22. [doi] [IF: 3.5/6, Q1]
- Luo, X.+, Wang, H.+, Xu, J., Liu, H.*, Suveg, C., & Han, Z.* (2025). Dynamic processes of parent-adolescent conflict and warmth in Chinese families: Differences between mothers and fathers. Journal of Youth and Adolescence, 54, 1985–1998. [doi] [IF: 4.5/5.9, Q1]
- Luo, X., Ma, J., & Hu, Y.* (2025). A dynamic bidirectional system of stress processes: Feedback loops between stressors, psychological distress, and physical symptoms. Health Psychology, 44(2), 154–165. [doi] [IF: 2.9/3.9, Q2]
Click to expand for more details
- Download the full article : Download PDF
- Open Data & Code : OSF Repository
- Luo, X., Hu, Y., & Liu, H.* (2025). Assessing between- and within-person reliabilities of items and scale for daily procrastination: A multilevel and dynamic approach. Assessment, 32(1), 61–76. [doi] [IF: 3/4.9, Q2]
Click to expand for more details
- Download the full article : Download PDF - Ma, J.+, Luo, X.+, & Hu, Y.* (2025). Positive stress mindset is vulnerable: Unpacking the internal system and external loop of dynamic stress mindset. Stress and Health, 41(4), e70089. [doi] [IF: 2.9/3.8, Q2]
- Luo, X., Liu, H.*, & Hu, Y.* (2024). From cross-lagged effects to feedback effects: Further insights into the estimation and interpretation of bidirectional relations. Behavior Research Methods, 56(4), 3685–3705. [doi] [IF: 5/7.2, Q1]
Click to expand for more details
- Download the full article : Download PDF
- Open Data & Code : OSF Repository
- Luo, X., & Liu, H.* (2024). Estimating test reliability of intensive longitudinal studies: Perspectives on multilevel structure and dynamic nature. Advances in Psychological Science (心理科学进展), 32(4), 700–714. [doi]
Click to expand for more details
- Download the full article : Download PDF
- Open Data & Code : OSF Repository - Luo, X., & Hu, Y.* (2024). Temporal misalignment in intensive longitudinal data: Consequences and solutions based on dynamic structural equation models. Structural Equation Modeling: A Multidisciplinary Journal, 31(1), 118–131. [doi] [IF: 3.5/5.8, Q1]
- Luo, X., Ma, J., & Hu, Y.* (2023). Dynamic and bidirectional relation between mindfulness and procrastination among female college students. Mindfulness, 14(9), 2265–2275. [doi] [IF: 4.1/4.9, Q1]
- Luo, X., & Hu, Y.* (2023). The competitive interaction between food cravings and unhealthy snacking: An application of the predator-prey model in psychology. Current Psychology, 42(32), 28484–28492. [doi] [IF: 2.7/3.3, Q1]
- Luo, X., Ge, Y., & Qu, W.* (2023). The association between big five personality and driving behaviors: A systematic review and meta-analysis. Accident Analysis and Prevention, 183, 106968. [doi] [IF: 7.2/8, Q1]
-
Liu, Y., Luo, X., & Liu, H.* (2026). Planned Measurement-Missing Designs in Intensive Longitudinal Studies: How Well Do They Recover Power and Parameter Estimates? Structural Equation Modeling: A Multidisciplinary Journal. [IF: 3.5/5.8, Q1]
-
Jin, Z., Luo, X., Ma, J., & Hu, Y. * (2026). The dynamic impact of stress mindsets on fatigue: Insights from an ecological momentary assessment and RDSEM approach. Applied Psychology: Health and Well-Being, 18(1), e70118. [doi] [IF: 3.3/4.3, Q2]
-
Li, J., Luo, X., & Liu, H.* (2025). Dynamic bidirectional relation between multidimensional state mindfulness and suicidal ideation among female college students: The moderating effect of trait mindfulness. Death Studies, 49(4), 347–358. [doi] [IF: 2.1/2.8, Q2]
-
Ge, Y., Luo, X., & Qu, W.* (2023). Impact of feedback content on dangerous driving behaviors based on the triangle model of responsibility. Transportation Research Part F: Traffic Psychology and Behaviour, 93, 1–10. [doi] [IF: 5/5.6, Q1]
- Qu, W., Luo, X., Wang, Y., & Ge, Y.* (2022). Effects of personality on driving behaviors among professional truck drivers: the mediating effect of safety climate. Transportation Research Part F: Traffic Psychology and Behaviour, 89, 289–302. [doi] [IF: 5/5.6, Q1]
Manuscripts Under Review or Revised & Resubmit
- Luo, X., Hu, Y.*, & Liu, H.* (revised & resubmit). Examining within-person variability of each individual: How should we deal with non-varying individuals? Behavior Research Methods.
- Luo, X., Dou, J., & Liu, H.* (revised & resubmit). When standard two-method measurement planned missing designs reach their limits: Time-embedded adaptations for intensive longitudinal studies. Behavior Research Methods.
- Luo, X., Castro-Alvarez, S., & Liu, H.*, & Bringmann, L. F. (under review). Beyond aggregate accuracy: A Bayesian time-varying autoregressive model and its multilevel extension. Preprint
- Liu, Y., Luo, X., Dong, J., Hu, Y.*, Liu, H.*, & Bauer, D. (under review). Two-stage estimation of latent variable regression models: A general, root-n consistent solution.