The article critiques the cross-lagged panel model (CLPM) for its inability to adequately account for trait-like, time-invariant stability in longitudinal data. It argues that the CLPM's autoregressive parameters fail to capture this stability, leading to biased estimates of cross-lagged regression coefficients and potentially erroneous conclusions about causal relationships. The authors propose an alternative model, the random intercepts cross-lagged panel model (RI-CLPM), which includes random intercepts to account for stable, trait-like differences between individuals. This model separates within-person dynamics from between-person differences and provides more accurate estimates of cross-lagged relationships. The RI-CLPM is shown to yield different results than the traditional CLPM when considering the three major objectives of cross-lagged panel research: determining whether variables influence each other, identifying which variable is causally dominant, and determining the sign of the influence. The article also discusses the relationship between the RI-CLPM and other existing structural equation models, such as the Stable Trait Autoregressive Trait and State (STARTS) model, the Autoregressive Latent Trajectory (ALT) model, the Latent Change Score (LCS) model, and the Latent State-Trait (LST) model. The authors conclude that the RI-CLPM is more closely related to the CLPM and requires only three waves of data, making it a more feasible alternative for researchers in cross-lagged panel research. The article also presents simulations showing that the CLPM can lead to spurious results when analyzing data with stable, trait-like individual differences. The RI-CLPM is shown to provide more accurate estimates of cross-lagged relationships and to better account for the complex dynamics of longitudinal data.The article critiques the cross-lagged panel model (CLPM) for its inability to adequately account for trait-like, time-invariant stability in longitudinal data. It argues that the CLPM's autoregressive parameters fail to capture this stability, leading to biased estimates of cross-lagged regression coefficients and potentially erroneous conclusions about causal relationships. The authors propose an alternative model, the random intercepts cross-lagged panel model (RI-CLPM), which includes random intercepts to account for stable, trait-like differences between individuals. This model separates within-person dynamics from between-person differences and provides more accurate estimates of cross-lagged relationships. The RI-CLPM is shown to yield different results than the traditional CLPM when considering the three major objectives of cross-lagged panel research: determining whether variables influence each other, identifying which variable is causally dominant, and determining the sign of the influence. The article also discusses the relationship between the RI-CLPM and other existing structural equation models, such as the Stable Trait Autoregressive Trait and State (STARTS) model, the Autoregressive Latent Trajectory (ALT) model, the Latent Change Score (LCS) model, and the Latent State-Trait (LST) model. The authors conclude that the RI-CLPM is more closely related to the CLPM and requires only three waves of data, making it a more feasible alternative for researchers in cross-lagged panel research. The article also presents simulations showing that the CLPM can lead to spurious results when analyzing data with stable, trait-like individual differences. The RI-CLPM is shown to provide more accurate estimates of cross-lagged relationships and to better account for the complex dynamics of longitudinal data.