A critique of the cross-lagged panel model.

Cross-lagged panel models (CLPMs) are commonly used to estimate causal influences between two variables with repeated assessments. The lagged effects in a CLPM depend on the time interval between assessments, eventually becoming undetectable at longer intervals. To address this limitation, we incorporate instrumental variables (IVs) into the CLPM with two study waves and two variables. Doing so enables estimation of both the lagged (i.e., “distal”) effects and the bidirectional cross-sectional (i.e., “proximal”) effects at each wave. The distal effects reflect Granger-causal influences across time, which decay with increasing time intervals. The proximal effects capture causal influences that accrue over time and can help infer causality when the distal effects become undetectable at longer intervals. Significant proximal effects, with a negligible distal effect, would imply that the time interval is too long to estimate a lagged effect at that time interval using the standard CLPM. Through simulations and an empirical application, we demonstrate the impact of time intervals on causal inference in the CLPM and present modeling strategies to detect causal influences regardless of the time interval in a study. Furthermore, to motivate empirical applications of the proposed model, we highlight the utility and limitations of using genetic variables as IVs in large-scale panel studies.

Non-suicidal self-injury (NSSI) is highly prevalent during adolescence and has been linked to adverse family environments. However, little is known about the dynamic mechanisms through which harsh parenting contributes to NSSI over time. This study examined the longitudinal associations among harsh parenting, basic psychological needs frustration (BPNF), and adolescent NSSI, and tested whether BPNF mediates this relationship at both the between-person and within-person levels. A three-wave longitudinal study was conducted among 1014 Chinese adolescents recruited from 10 middle schools in Beijing. Data were collected at three time points: February 2025 (T1), June 2025 (T2), and October 2025 (T3). Harsh parenting, BPNF, and NSSI were assessed using validated self-report measures. Cross-lagged panel models (CLPM) and random-intercept cross-lagged panel models (RI-CLPM) were estimated to distinguish stable between-person differences from within-person fluctuations over time, controlling for key demographic variables. The CLPM indicated reciprocal associations between harsh parenting and NSSI and revealed a significant indirect pathway from harsh parenting to NSSI via BPNF. After accounting for stable between-person differences, the RI-CLPM showed that within-person increases in harsh parenting predicted subsequent increases in BPNF, which in turn predicted later increases in NSSI. The longitudinal indirect effect remained significant at the within-person level. These findings suggest that fluctuations in harsh parenting contribute to adolescent NSSI through increased frustration of basic psychological needs. Targeting family interactions and adolescents' psychological need satisfaction may represent important avenues for preventing NSSI.

BackgroundThe directionality of longitudinal associations between children’s food fussiness and parental feeding behaviors remains contested. This study aimed to assess the dynamic relationship between children’s food fussiness and feeding behaviors.MethodsTo disentangle these effects, this study employed cross-lagged panel models (CLPMs) and random-intercept cross-lagged panel models (RI-CLPMs) using longitudinal data from 588 Chinese children (Mean age = 3.7 years, SD = 0.3, 51.7% boys) across three waves over two years. CLPMs capture between-person associations, while RI-CLPMs isolate within-person dynamics over time. Within-person effects represent how temporary deviations predict subsequent changes beyond stable traits, whereas between-person effects reflect enduring cross-family differences.ResultsAnalyses revealed distinct patterns depending on the feeding behavior and model type: for restrictions, the CLPM showed parent-driven effects (restrictions at 3.7 years→ fussiness at 4.8 years, β = −0.104, p = 0.003), whereas the RI-CLPM identified child-driven effects (fussiness at 4.8 years → restrictions at 5.7 years, β = 0.179, p = 0.033). Both models consistently revealed child-driven effects for pressure to eat (CLPM: β = 0.151, p = 0.002; RI-CLPM: β = 0.218, p = 0.013). Food as a reward showed bidirectionality in CLPM (reward at 4.8 years → fussiness at 5.7 years: β = 0.112, p < 0.001; fussiness at 4.8 years→ reward at 5.7 years: β = 0.144, p = 0.005) but no significant cross-lagged paths in the RI-CLPM. Notably, the multi-group analysis revealed no moderating effect of child sex.ConclusionsAfter accounting for stable between-person differences, RI-CLPM findings reveal that child food fussiness prospectively drives increases in parental use of restriction and pressure to eat at the within-person level. This suggests that these specific feeding behaviors may function more as reactive responses to children’s eating behaviors than as caregiver-initiated strategies.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12966-025-01830-8.

How to model cross-lagged relations in panel data continues to be a source of disagreement in psychological research. While the cross-lagged panel model (CLPM) was the modeling approach of choice for many years, it has also been criticized repeatedly for its inability to separate within-person dynamics from stable between-person differences. Hence, various alternative models that disentangle these forms of variability have been proposed, and these are now rapidly gaining popularity. But not everyone agrees this is the right way forward. CLPM advocates point out that many psychological theories are concerned with longer-lasting differences between individuals, while these differences are not allowed to contribute to the estimation of cross-lagged effects in the novel within-between approaches. Reasoning this way, it is argued that the CLPM is superior when studying such processes, precisely because it includes the chronic between-person differences when estimating prospective effects. The goal of the current paper is to consider this within-between dispute in its broader context and to examine various directions in which this discussion needs expansion. To this end, three different perspectives are adopted: that of the study design, patterns in empirical data, and the nature of our research questions. It will be argued that to move forward, we need to look beyond the narrow focus on how to model our correlational panel data. Progress will involve theorizing more deliberately about the timescale that a process operates on, being more explicit about our research questions, considering alternative designs and models, and familiarizing ourselves with relevant discussions in other disciplines. (PsycInfo Database Record (c) 2026 APA, all rights reserved).

Researchers often combine longitudinal panel data analysis with tests of interactions (i.e., moderation). A popular example is the cross-lagged panel model (CLPM). However, interaction tests in CLPMs and related models require caution because stable (i.e., between-level, B) and dynamic (i.e., within-level, W) sources of variation are present in longitudinal data, which can conflate estimates of interaction effects. We address this by integrating literature on CLPMs, multilevel moderation, and latent interactions. Distinguishing stable B and dynamic W parts, we describe three types of interactions that are of interest to researchers: 1) purely dynamic or WxW; 2) cross-level or BxW; and 3) purely stable or BxB. We demonstrate estimating latent interaction effects in a CLPM using a Bayesian SEM in Mplus to apply relationships among work-family conflict and job satisfaction, using gender as a stable B variable. We support our approach via simulations, demonstrating that our proposed CLPM approach is superior to a traditional CLPMs that conflate B and W sources of variation. We describe higher-order nonlinearities as a possible extension, and we discuss limitations and future research directions.

Cross-lagged models are by far the most commonly used method to test the prospective effect of one construct on another, yet there are no guidelines for interpreting the size of cross-lagged effects. This research aims to establish empirical benchmarks for cross-lagged effects, focusing on the cross-lagged panel model (CLPM) and the random intercept cross-lagged panel model (RI-CLPM). We drew a quasirepresentative sample of studies published in four subfields of psychology (i.e., developmental, social-personality, clinical, and industrial-organizational). The dataset included 1,028 effect sizes for the CLPM and 302 effect sizes for the RI-CLPM, based on data from 174 samples. For the CLPM, the 25th, 50th, and 75th percentiles of the distribution corresponded to cross-lagged effect sizes of .03, .07, and .12, respectively. For the RI-CLPM, the corresponding values were .02, .05, and .11. Effect sizes did not differ significantly between the CLPM and RI-CLPM. Moreover, effect sizes did not differ significantly across subfields and were not moderated by design characteristics. However, effect sizes were moderated by the concurrent correlation between the constructs and the stability of the predictor. Based on the findings, we propose to use .03 (small effect), .07 (medium effect), and .12 (large effect) as benchmark values when interpreting the size of cross-lagged effects, for both the CLPM and RI-CLPM. In addition to aiding in the interpretation of results, the present findings will help researchers plan studies by providing information needed to conduct power analyses and estimate minimally required sample sizes. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

In virtually all areas of psychology, the question of whether a particular construct has a prospective effect on another is of fundamental importance. For decades, the cross-lagged panel model (CLPM) has been the model of choice for addressing this question. However, CLPMs have recently been critiqued, and numerous alternative models have been proposed. Using the association between low self-esteem and depression as a case study, we examined the behavior of seven competing longitudinal models in 10 samples, each with at least four waves of data and sample sizes ranging from 326 to 8,259. The models were compared in terms of convergence, fit statistics, and consistency of parameter estimates. The traditional CLPM and the random intercepts cross-lagged panel model (RI-CLPM) converged in every sample, whereas the other models frequently failed to converge or did not converge properly. The RI-CLPM exhibited better model fit than the CLPM, whereas the CLPM produced more consistent cross-lagged effects (both across and within samples) than the RI-CLPM. We discuss the models from a conceptual perspective, emphasizing that the models test conceptually distinct psychological and developmental processes, and we address the implications of the empirical findings with regard to model selection. Moreover, we provide practical recommendations for researchers interested in testing prospective associations between constructs and suggest using the CLPM when focused on between-person effects and the RI-CLPM when focused on within-person effects. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

The present study examines the directionality of links between romantic relationship conflict and psychological distress in premarital relationships of emerging adults. A total of 182 participants (Mage = 21.23; SDage = 1.62; 85.16% female) provided data at both Time 1 (T1) and Time 2 (T2). Participants responded to a battery of questions related to romantic relationship conflict and psychological distress. The data for the present study were collected at two time points during spring semester of 2018: First week (Time 1) and the last week of the semester, Week 14 (Time 2). A two-wave two variable cross-lagged autoregressive panel model was conducted to examine the links between relationship conflict and psychological distress over time in emerging adults. Using a latent cross-lagged panel model, we found that romantic relationship conflict at T1 significantly predicted psychological distress at T2, but psychological distress at T1 was not associated with subsequent romantic relationship conflict at T2, after controlling for autoregressive effects. The results highlighted the key role of romantic relationship conflict in predicting later psychological distress. Limitations and implications are discussed and future directions are suggested.

This study simplifies the seven different cross-lagged panel models (CLPMs) by using the RSEM model for both inter-individual and intra-individual structures. In addition, the study incorporates the newly developed dynamic panel model (DPM), general cross-lagged model (GCLM) and the random intercept auto-regressive moving average (RI-ARMA) model. Then, using a longitudinal study of self-esteem and depression, ten different CLPMs are analyzed using robust maximum likelihood estimation. In addition, the Mplus syntax is provided as a reference for researcher. This study aims to enhance empirical researcher understanding and exploration of different CLPMs by providing simplified explanations and analyses of the ten different CLPMs, thereby promoting the development of empirical constructs and topics in the context of various cross-lagged panel models.

Burnout and exhaustion has been extensively studied in organizational, work, and health psychology. Studies using the cross-lagged panel models have tended to conclude, explicitly or implicitly (e.g., in the form of policy recommendations), causal prospective effects of, for example, organizational demands, job insecurity, and depression on burnout and exhaustion. However, it is well established that effects in the cross-lagged panel model may be artifactual, e.g., due to correlations with residuals and regression to the mean. Here, we scrutinized 23 previously reported prospective effects on burnout/exhaustion by fitting complementary models to data that were simulated to resemble data in the evaluated studies. With one possible exception, the previously reported prospective effects did not withstand scrutiny, i.e., they appeared to be artifactual. It is important for researchers to bear in mind that correlations, including effects in cross-lagged panel models, do not prove causality in order not to overinterpret findings. We recommend researchers to scrutinize findings from cross-lagged panel models by fitting complementary models to their data. If findings from complementary models converge, conclusions are corroborated. If, on the other hand, findings diverge, caution is advised and claims of causality, explicit or implicit, should probably be avoided.

In longitudinal studies involving multiple latent variables, researchers often seek to predict how iterations of latent variables measured at early time points predict iterations measured at later time points. Cross-lagged panel modeling, a form of structural equation modeling, is a useful way to conceptualize and test these relationships. However, prior to making causal claims, researchers must first ensure that the measured constructs are equivalent between time points. To do this, they test for measurement invariance, constructing and comparing a series of increasingly strict and parsimonious models, each making more constraints across time than the last. This comparison process, though challenging, is an important prerequisite to interpretation of results. Fortunately, testing for measurement invariance in cross-lagged panel models has become easier, thanks to the wide availability of R and its packages. This paper serves as a tutorial in testing for measurement invariance and cross-lagged panel models using the lavaan package. Using real data from an openly available study on perfectionism and drinking problems, we provide a step-by-step guide of how to test for longitudinal measurement invariance, conduct cross-lagged panel models, and interpret the results. Original data source with materials: https://osf.io/gduy4/. Project website with data/syntax for the tutorial: https://osf.io/hwkem/.

The cross-lagged panel model (CLPM) is a widely used technique for examining reciprocal causal effects using longitudinal data. Critics of the CLPM have noted that by failing to account for certain person-level associations, estimates of these causal effects can be biased. Because of this, models that incorporate stable-trait components (e.g., the random-intercept CLPM) have become popular alternatives. Debates about the merits of the CLPM have continued, however, with some researchers arguing that the CLPM is more appropriate than modern alternatives for examining common psychological questions. In this article, I discuss the ways that these defenses of the CLPM fail to acknowledge well-known limitations of the model. I propose some possible sources of confusion regarding these models and provide alternative ways of thinking about the problems with the CLPM. I then show in simulated data that with realistic assumptions, the CLPM is very likely to find spurious cross-lagged effects when they do not exist and can sometimes underestimate these effects when they do exist.

Family caregivers play a crucial caregiving role for colorectal cancer patients undergoing chemotherapy, and the emotional states of both patients and caregivers can influence each other. A high prevalence of depression and anxiety exists among both patients and caregivers, with their emotional states mutually influencing each other. This significantly impacts the quality of life for both parties. However, there is limited research on the bidirectional relationship between depression and anxiety in both groups. This study aims to investigate the longitudinal bidirectional relationship between depression and anxiety in colorectal cancer patients and their family caregivers using a cross-lagged panel model. A total of 244 pairs of colorectal cancer patients undergoing chemotherapy and their family caregivers were assessed using the Hospital Anxiety and Depression Scale. Data collection was conducted at four time points: the initial chemotherapy session and 1-, 3-, and 6- months post-chemotherapy. A cross-lagged panel model was employed to analyze the longitudinal interrelationship between depression and anxiety within and between the two groups. The study found high prevalence rates of depression and anxiety in both colorectal cancer patients and their caregivers. The cross-lagged model revealed a dynamic, bidirectional relationship between depression and anxiety in patients and caregivers from the second wave onwards (P < 0.05). The emotional states of depression and anxiety in colorectal cancer patients and their caregivers show dynamic changes and are longitudinally interrelated. These findings underscore the importance of early psychological assessment and interventions targeting both patients and caregivers.

Cross-lagged panel models (CLPMs) are widely used to test mediation with longitudinal panel data. One major limitation of the CLPMs is that the model effects are assumed to be fixed across individuals. This assumption is likely to be violated (i.e., the model effects are random across individuals) in practice. When this happens, the CLPMs can potentially yield biased parameter estimates and misleading statistical inferences. This article proposes a model named a random-effects cross-lagged panel model (RE-CLPM) to account for random effects in CLPMs. Simulation studies show that the RE-CLPM outperforms the CLPM in recovering the mean indirect and direct effects in a longitudinal mediation analysis when random effects exist in the population. The performance of the RE-CLPM is robust to a certain degree, even when the random effects are not normally distributed. In addition, the RE-CLPM does not produce harmful results when the model effects are in fact fixed in the population. Implications of the simulation studies and potential directions for future research are discussed.

The awareness of words’ morphological structure has been thought to allow generalizing meaning to other, similarly constructed words. Conversely, a large vocabulary is thought to facilitate the recognition of words’ morphological regularities, thereby contributing to morphological awareness. For this reason, morphological awareness and vocabulary have been suggested to be reciprocally associated across development. We followed 242 (girls = 119) Norwegian preschoolers (Mage = 5.5 years) from preschool through Grade 2 and examined the cross-lagged relations between morphological awareness (inflections and derivations) and vocabulary (receptive and expressive). Our results confirm that the traditional cross-lagged panel model shows significant cross-lagged relations between morphological awareness and vocabulary, as previous studies have shown. However, no cross-lagged relations were found when we accounted for longitudinal measured stability through a cross-lagged panel model with lag-2 paths or unmeasured stability through the random intercept cross-lagged panel model. We found that approximately 50% of the variation in morphology and vocabulary was due to highly stable and invariant factors across grades. We discuss how the significant cross-lagged relations found in previous studies could have been due to their not accounting for the right type of stability when using longitudinal panel data.