A critique of the cross-lagged panel model
Open accessThe DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
Abstract
The cross-lagged panel model (CLPM) is believed by many to overcome the problems associated with the use of cross-lagged correlations as a way to study causal influences in longitudinal panel data. The current article, however, shows that if stability of constructs is to some extent of a trait-like, time-invariant nature, the autoregressive relationships of the CLPM fail to adequately account for this. As a result, the lagged parameters that are obtained with the CLPM do not represent the actual within-person relationships over time, and this may lead to erroneous conclusions regarding the presence, predominance, and sign of causal influences. In this article we present an alternative model that separates the within-person process from stable between-person differences through the inclusion of random intercepts, and we discuss how this model is related to existing structural equation models that include cross-lagged relationships. We derive the analytical relationship between the cross-lagged parameters from the CLPM and the alternative model, and use simulations to demonstrate the spurious results that may arise when using the CLPM to analyze data that include stable, trait-like individual differences. We also present a modeling strategy to avoid this pitfall and illustrate this using an empirical data set. The implications for both existing and future cross-lagged panel research are discussed.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The CLPM has been criticized for conflating these two distinct types of effects (Hamaker et al., 2015).”
From Navigating Beauty Standards on Social Media: Impact of Appearance Activity on Adolescents’ Body Dissatisfaction (2025) · cites this paper as Hamaker et al., 2015
In the citing paper
“there are statistical analyses that can help disentangle this relationship (eg, cross-lagged panel models41) even when there is overlap with measurement timepoints.”
From Target mechanisms of mindfulness-based programmes and practices: a scoping review (2024) · cites this paper as [41]
In the citing paper
“Third, much of the existing evidence relies on cross-sectional designs, which cannot adequately disentangle the temporal ordering among media consumption, attentional control, self-regulation, and learning experience”
From Algorithmic short-video music consumption and academic related functions: a three-wave longitudinal study of university students (2026) · cites this paper as Hamaker et al., 2015
In the citing paper
“The traditional CLPM combines stable between-person differences with within-person fluctuations.”
From Algorithmic short-video music consumption and academic related functions: a three-wave longitudinal study of university students (2026) · cites this paper as Hamaker et al., 2015
In the citing paper
“The cross-lagged parameters of the RI-CLPM reflect individual deviations from their expected score over time, therefore adjustment for inter-individual differences such as gender and socio-economic status as well trait-like characteristics is not needed on the within-person level [6,31,37].”
From Social Media and Mental Health Among Early Adolescents in Sweden: A Longitudinal Study With 2-Year Follow-Up (KUPOL Study). (2021) · cites this paper as [31]
11 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
R: A Language and Environment for Statistical Computing
R Core Team (2025) · doi:10.32614/r.manuals · Cited by 352,181
Investigating causal relations by econometric models and cross-spectral methods
Granger, C. W. J. (1969) · Econometrica · doi:10.2307/1912791 · Cited by 22,989
Breitung, J., & Hamilton, J. D. (1995) · Contemporary Sociology · doi:10.2307/2076916 · Cited by 10,966
Fixed Effects Regression Models
Allison, P. (2009) · doi:10.4135/9781412993869 · Cited by 3,999 · cited 2×
“This illustrates the fact that difference scores are a way to eliminate the effect of stable, unobserved variables, which is sometimes considered a major advantage of difference score modeling over other approaches (cf. Allison, 2009; Liker et al., 1985).”
Latent Variable Modeling of Differences and Changes with Longitudinal Data
McArdle, J. J. (2009) · Annual Review of Psychology · doi:10.1146/annurev.psych.60.110707.163612 · Cited by 1,952 · cited 4×
“…order to determine which variable is causally dominant, the coupling parameters are used to set up a vector field which depicts the expected changes from one occasion to the next on both variables as a function of the current state (see Boker & McArdle, 1995; McArdle, 2009; McArdle & Grimm, 2010).”
InfluentialCausal Analysis with Panel Data
Finkel, S. (1995) · Sage eBooks · doi:10.4135/9781412983594 · Cited by 1,348
Causal Analysis With Panel Data
(2020) · SAGE Research Methods Foundations · doi:10.4135/9781526421036825836 · Cited by 1,083
Wood, A. M., Maltby, J., Gillett, R., Linley, P. A., & Joseph, S. (2008) · Journal of Research in Personality · doi:10.1016/j.jrp.2007.11.003 · Cited by 761 · cited 2×
“To give an impression of the kinds of questions researchers have tried to tackle using the CLPM, consider the following anthology: Do maternal warmth and praise reduce internalizing and externalizing problems in children with autism (Smith, Greenberg, Mailick Seltzer, & Hong, 2008)? Is the relationship between parenti…”
Emotional Inertia and Psychological Maladjustment
Kuppens, P., Allen, N. B., & Sheeber, L. B. (2010) · Psychological Science · doi:10.1177/0956797610372634 · Cited by 724
A Network Approach to Psychopathology: New Insights into Clinical Longitudinal Data
Bringmann, L. F., Vissers, N., Wichers, M., Geschwind, N., Kuppens, P., Peeters, F., Borsboom, D., & Tuerlinckx, F. (2013) · PLoS ONE · doi:10.1371/journal.pone.0060188 · Cited by 680 · cited 1×
“To this end, one can use multilevel modeling, in which the lagged variables (either centered per person or not) are included as predictors (Bringmann et al., 2013).”
Method
Cited by
Items 1,001–1,033 of 1,033
Kauff, M., Kotzur, P. F., Assche, J. V., Schäfer, S. J., van Zalk, M. H. W., & Wagner, U. (2023) · European Journal of Social Psychology · doi:10.1002/ejsp.2966 · Cited by 19
Abplanalp, S. J., Reavis, E. A., Le, T. P., & Green, M. F. (2024) · NPP—Digital Psychiatry and Neuroscience · doi:10.1038/s44277-024-00004-x · Cited by 17
“The mlVAR model, a multilevel extension of the vector auto-regression (VAR) model, describes dynamic relationships among variables measured repeatedly over time [9, 10].”
A daily diary study into the effects on mental health of COVID-19 pandemic-related behaviors
Shaw, P., Blizzard, S., Shastri, G., Kundzicz, P., Curtis, B., Ungar, L., & Koehly, L. (2021) · Psychological Medicine · doi:10.1017/s0033291721001896 · Cited by 14
Tibbs, M., Deschênes, S., van der Velden, P., & Fitzgerald, A. (2025) · Journal of Youth and Adolescence · doi:10.1007/s10964-024-02093-5 · Cited by 16
“…effects as represented by random intercepts, and dynamic within-person variance, determined by an individual ’ s deviation from their expected score (i.e., the difference between individual scores and the sum of the grand mean at each wave and the random intercept) (Hamaker et al., 2015).”
InfluentialThompson, K. N., Agnew-Blais, J. C., Allegrini, A. G., Bryan, B. T., Danese, A., Odgers, C. L., Matthews, T., & Arseneault, L. (2023) · JAACAP Open · doi:10.1016/j.jaacop.2023.02.001 · Cited by 16
“We used the random intercept cross-lagged panel model (RI-CLPM) 30 to assess bidirectional associations between social isolation and ADHD across ages 5, 7, 10, and 12 years.”
Lindsäter, E., Axelsson, E., Salomonsson, S., Santoft, F., Ljótsson, B., Åkerstedt, T., Lekander, M., & Hedman-Lagerlöf, E. (2021) · Behaviour Research and Therapy · doi:10.1016/j.brat.2020.103782 · Cited by 15
Nguyen, C. G. (2019) · doi:10.31235/osf.io/e2wm6 · Cited by 15
Laposa, J. M., Katz, D. E., Lisi, D. M., Hawley, L. L., Quigley, L., & Rector, N. A. (2022) · Journal of Anxiety Disorders · doi:10.1016/j.janxdis.2022.102623 · Cited by 14
Axelsson, E., Hesser, H., Andersson, E., Ljótsson, B., & Hedman-Lagerlöf, E. (2020) · Journal of Anxiety Disorders · doi:10.1016/j.janxdis.2019.102172 · Cited by 12
Williams, M. N., Marques, M. D., Kerr, J. R., Hill, S. R., Ling, M., & Clarke, E. J. R. (2025) · European Journal of Social Psychology · doi:10.1002/ejsp.3153 · Cited by 12
Narcissism and friendship quality: A longitudinal approach to long-term friendships
Wehner, C., & Ziegler, M. (2023) · Journal of Social and Personal Relationships · doi:10.1177/02654075221122023 · Cited by 13
“We used random intercepts cross-lagged panel models (RI-CLPM; Hamaker et al., 2015) to observe the effects of temporary deviation from the average narcissism level (admiration and rivalry) on temporary deviation from the friendship quality level (appreciation, conflict, dominance, and intimacy) and…”
MethodKvardova, N., Machackova, H., Maes, C., & Vandenbosch, L. (2025) · Journal of Youth and Adolescence · doi:10.1007/s10964-025-02159-y · Cited by 11
“Finally, the random intercept cross-lagged panel model (RI-CLPM; Hamaker et al., 2015) was set up.”
InfluentialLongitudinal and Bidirectional Relations Between Problematic Social Media Use and Cognitive Failures
Kasturiratna, K. T. A. S., & Hartanto, A. (2025) · Psychiatric Quarterly · doi:10.1007/s11126-025-10203-0 · Cited by 10
Yu, W., Zhou, G., Fan, B., Gao, C., Li, C., Wei, M., Lv, J., He, L., Feng, G., & Zhang, T. (2022) · BMJ Open Diabetes Research & Care · doi:10.1136/bmjdrc-2021-002653 · Cited by 8
Wang, Z., Tang, X., Hu, A., Chiu, W., Hofmann, S. G., & Liu, X. (2025) · Psychotherapy Research · doi:10.1080/10503307.2024.2426562 · Cited by 6
“Subsequently, without considering group differences, we used Random Intercept Cross-Lagged Panel Models (RI-CLPMs; Hamaker et al., 2015) to explore the temporal relationship between decen-tering and emotional distress.”
Smits, J. A. J., Zvolensky, M. J., Otto, M. W., Piper, M. E., Baird, S. O., Kauffman, B. Y., Lee-Furman, E., Alavi, N., Dutcher, C. D., Papini, S., et al. (2020) · Drug and Alcohol Dependence · doi:10.1016/j.drugalcdep.2020.107877 · Cited by 5
Diamond, G., Rivers, A. S., Winston-Lindeboom, P., Russon, J., & Roeske, M. (2024) · Child and Adolescent Psychiatry and Mental Health · doi:10.1186/s13034-024-00833-w · Cited by 5
“Therefore, we used a random-intercept, cross-lagged panel model (RI-CLPM) [54] to examine these relationships over time.”
Mediators during a Multimodal intervention for stress-induced exhaustion disorder
van de Leur, J. C., Johansson, F., McCracken, L. M., Åhs, F., Brodda Jansen, G., & Buhrman, M. (2024) · Cognitive Behaviour Therapy · doi:10.1080/16506073.2023.2295217 · Cited by 5
“…was utilized to explore if a within-individual change in the suggested mediators preceded the subsequent change in exhaustion symptoms or if a within-individual change in exhaustion symptoms preceded the subsequent change in the suggested mediators (Hamaker et al., 2015; Mulder & Hamaker, 2021).”
MethodMaes, C., & Vandenbosch, L. (2024) · Communication Research · doi:10.1177/00936502231191830 · Cited by 4
“Between-subject effects are more stable, trait-like differences between individuals (Hamaker et al., 2015).”
BackgroundGarey, L., Wirtz, M. R., Labbe, A. K., Zvolensky, M. J., Smits, J. A. J., Giordano, T. P., Rosenfield, D., Robbins, G. K., Levy, D. E., McKetchnie, S. M., et al. (2021) · Contemporary Clinical Trials · doi:10.1016/j.cct.2021.106420 · Cited by 3
Murray, A., Errington, P., Yang, Y., Wright, H., Mirman, D., Obsuth, I., Booth, T., Ribeaud, D., & Eisner, M. (2026) · JCPP Advances · doi:10.1002/jcv2.70075 · Cited by 4
“…example, the random intercepts cross - lagged panel model (RI - CLPM) can provide information about how within - person variation in a candidate treatment variable (e.g., reading) is reciprocally related to within - person changes in an outcome variable (e.g., mental health) (Hamaker et al., 2015).”
Baljé, A. E., Greeven, A., Deen, M., van Giezen, A. E., Arntz, A., & Spinhoven, P. (2025) · Clinical Psychology & Psychotherapy · doi:10.1002/cpp.70148 · Cited by 3
“All the lagged relations pertain to within-person fluctuations (Hamaker et al. 2015; Mulder and Hamaker 2021).”
Rémeau, M., Raffy, G., & Borst, G. (2026) · Journal of Youth and Adolescence · doi:10.1007/s10964-025-02281-x · Cited by 3
Nnawulezi, N., Macy, R., Wretman, C., Radtke, S., Clark, D. A., & Sullivan, C. M. (2025) · Journal of Family Violence · doi:10.1007/s10896-025-00989-9 · Cited by 3
Yang, X. (2026) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2026.2618548 · Cited by 3
“Next, we specified two RI-CLPMs in Mplus , following the methodologies proposed by Hamaker et al. (2015) and Mulder and Hamaker (2021).”
Spinhoven, P., Kraaij, V., Garnefski, N., Bohlmeijer, E., & Witlox, M. (2026) · Psychotherapy Research · doi:10.1080/10503307.2025.2556836 · Cited by 2
“In RI-CLPM the variance of the observed score is divided into variance due to a between-person stable invariant trait (by adding a random intercept) and variance due to within-person fluctuation.”
InfluentialTemporal Relations Among Changes in Activation, Avoidance, and Anxiety in the Unified Protocol.
Terrill, D. R., Southward, M. W., Crowley, L., Feddock, R., Kushner, M. L., & Sauer-Zavala, S. (2024) · Journal of Psychopathology and Behavioral Assessment · doi:10.1007/s10862-023-10099-9 · Cited by 1
“Specifically, we conducted a series of random intercept cross-lagged panel models (RI-CLPM; Hamaker et al., 2015) examining the relations between behavioral activation, avoidance, and anxiety symptoms across treatment with the Unified Protocol (UP; Barlow et al., 2018), a transdiagnostic…”
Bryan, B. T., Thompson, K. N., Fisher, H. L., Matthews, T., Milne, B., & Arseneault, L. (2026) · Development and Psychopathology · doi:10.1017/s0954579426101758 · Cited by 1
Dong, J., Zhang, H., Zhao, J., & Yuan, R. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1907189
“Third, much of the existing evidence relies on cross-sectional designs, which cannot adequately disentangle the temporal ordering among media consumption, attentional control, self-regulation, and learning experience (Hamaker et al., 2015; Lucas, 2023).”
InfluentialYılmaz, M. F., Okur, S., Kütük, H., & Satıcı, B. (2026) · Counselling and Psychotherapy Research · doi:10.1002/capr.70170
Zhang, W., Duan, R., Li, H., Fang, Y., Zhao, W., Wan, F., & Fan, J. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1805798
“Cross-lagged panel modeling (CLPM), random intercept CLPM (RI-CLPM), and multi-group analyses were employed, controlling for sport type (aesthetic/weight-class vs. other sports).”
InfluentialMartins, D. S., Sampaio, T. P. D. A., & Lotufo Neto, F. (2022) · Jornal Brasileiro de Psiquiatria · doi:10.1590/0047-2085000000361 · Cited by 2
Luszawski, C. A., Luszawski, M. M., Bender, A. M., Noel, M., & Yeates, K. O. (2026) · Journal of Neurotrauma · doi:10.1177/08977151261425214
“107,108 RI-CLPMs can also control for time-invariant cofounders such as baseline sleep and emotional functioning.”
Metadata
- Authors
- Hamaker, E. L., Kuiper, R. M., & Grasman, R. P. P. P.
- Affiliations
- Utrecht University (NL)
- University of Amsterdam (NL)
- Venue
- Psychological Methods
- Published
- 2015
- Volume
- 20
- Issue
- 1
- Pages
- 102-116
- ISSN
- 1082-989X (ISSN-L)
- 1939-1463
- OpenAlex
- W1971772643
- Cited by
- 4,005
- References
- 63
- Citations by year
- 2026: 835 · 2025: 671 · 2024: 520 · 2023: 473 · 2022: 448 · 2021: 374 · 2020: 275 · 2019: 174 · 2018: 122 · 2017: 73 · 2016: 30 · 2015: 6
- FWCI
- 68.19
- Type
- journal article
- Language
- en
- Open access
- green
- dare.uva.nl
- Licence
- other-oa
- Locations
- Psychological Methods (publishedVersion)
- PubMed (publishedVersion)
- UvA-DARE (University of Amsterdam) (publishedVersion, other-oa)
- UvA-DARE (University of Amsterdam) (submittedVersion, other-oa)
- Utrecht University Repository (Utrecht University) (submittedVersion, other-oa)
- Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
- Funders
- Netherlands Organization for Scientific Research (452-10-007)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Mental Health Research Topics
- Keywords
- cross-lagged panel model, causal inference, longitudinal panel data, trait stability, random intercepts, within-person change, between-person differences, cross-lagged correlations, structural equation modeling
- MeSH terms
- Humans, Individuality, Models, Psychological, Models, Statistical
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.