Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2015 Mar 2:6:27516.
doi: 10.3402/ejpt.v6.27516. eCollection 2015.

Using Bayesian statistics for modeling PTSD through Latent Growth Mixture Modeling: implementation and discussion

Sarah Depaoli  1 , Rens van de Schoot  2   3 , Nancy van Loey  4   5 , Marit Sijbrandij  6   7
Affiliations

Using Bayesian statistics for modeling PTSD through Latent Growth Mixture Modeling: implementation and discussion

Sarah Depaoli et al. Eur J Psychotraumatol. .

Abstract

Background: After traumatic events, such as disaster, war trauma, and injuries including burns (which is the focus here), the risk to develop posttraumatic stress disorder (PTSD) is approximately 10% (Breslau & Davis, 1992). Latent Growth Mixture Modeling can be used to classify individuals into distinct groups exhibiting different patterns of PTSD (Galatzer-Levy, 2015). Currently, empirical evidence points to four distinct trajectories of PTSD patterns in those who have experienced burn trauma. These trajectories are labeled as: resilient, recovery, chronic, and delayed onset trajectories (e.g., Bonanno, 2004; Bonanno, Brewin, Kaniasty, & Greca, 2010; Maercker, Gäbler, O'Neil, Schützwohl, & Müller, 2013; Pietrzak et al., 2013). The delayed onset trajectory affects only a small group of individuals, that is, about 4-5% (O'Donnell, Elliott, Lau, & Creamer, 2007). In addition to its low frequency, the later onset of this trajectory may contribute to the fact that these individuals can be easily overlooked by professionals. In this special symposium on Estimating PTSD trajectories (Van de Schoot, 2015a), we illustrate how to properly identify this small group of individuals through the Bayesian estimation framework using previous knowledge through priors (see, e.g., Depaoli & Boyajian, 2014; Van de Schoot, Broere, Perryck, Zondervan-Zwijnenburg, & Van Loey, 2015).

Method: We used latent growth mixture modeling (LGMM) (Van de Schoot, 2015b) to estimate PTSD trajectories across 4 years that followed a traumatic burn. We demonstrate and compare results from traditional (maximum likelihood) and Bayesian estimation using priors (see, Depaoli, 2012, 2013). Further, we discuss where priors come from and how to define them in the estimation process.

Results: We demonstrate that only the Bayesian approach results in the desired theory-driven solution of PTSD trajectories. Since the priors are chosen subjectively, we also present a sensitivity analysis of the Bayesian results to illustrate how to check the impact of the prior knowledge integrated into the model.

Conclusions: We conclude with recommendations and guidelines for researchers looking to implement theory-driven LGMM, and we tailor this discussion to the context of PTSD research.

Keywords: Bayesian estimation; Latent Growth Mixture Modeling; PTSD; delayed onset; sensitivity analysis.

PubMed Disclaimer

References

    1. Bonanno G. A. Loss, trauma, and human resilience: Have we underestimated the human capacity to thrive after extremely adverse events? American Psychologist. 2004;59:20–28. - PubMed
    1. Bonanno G. A, Brewin C. R, Kaniasty K, Greca A. M. L. Weighing the costs of disaster consequences, risks, and resilience in individuals, families, and communities. Psychological Science in the Public Interest. 2010;11:1–49. - PubMed
    1. Breslau N, Davis G. C. Posttraumatic stress disorder in an urban population of young adults: Risk factors for chronicity. The American Journal of Psychiatry. 1992;149:671–675. - PubMed
    1. Depaoli S. Measurement and structural model class separation in mixture CFA: ML/EM versus MCMC. Structural Equation Modeling: A Multidisciplinary Journal. 2012;19(2):178–203.
    1. Depaoli S. Mixture class recovery in GMM under varying degrees of class separation: Frequentist versus Bayesian estimation. Psychological Methods. 2013;18(2):186–219. - PubMed