TICKETED SESSIONS | Advanced Methodology and Statistics Seminars

Clinical psychology is undergoing a revolution where hypotheses, data, materials, and papers are shared more openly than ever before, improving the credibility, accessibility, and transparency of the science we produce. Additionally, an increasing list of top-tier outlets for clinical trials now require (e.g., Journal of Consulting and Clinical Psychology, Archives of General Psychiatry/JAMA Psychiatry) or strongly encourage (e.g., Clinical Psychological Science) primary hypotheses to be preregistered in order to be considered for publication.

Secondary analyses are also being subjected to ever-increasing scrutiny, with credibility of research findings becoming an integral part of the review process. However, clinical psychology has lagged behind other areas in adopting credibility-enhancing research practices. This may be at least partially because adopting such practices are often framed as a communal good, but a personal sacrifice of time and effort. The landscape is evolving such that open science practices are no longer optional and policies at leading clinical journals suggest that this will only increase over the near term (e.g., Davila, 2019;). This AMASS will teach easy-to-adopt strategies for enhancing the transparency, accessibility, and credibility of your research-and ways in which these practices actually save both personal time and effort. We will highlight: (a) using preregistration tools to boost odds of publication acceptance, regardless of your study results; (b) tools for staying even more up to date in your field; (c) earning credit, and disseminating your work, earlier in the paper-writing process; (d) creating easy-to-reproduce analyses that meet current publication standards for data transparency. This session will include hands-on practice with free, credibility increasing tools such as preprint servers, open data repositories, open source analysis tools (R & JAMOVI), and the Open Science Framework. This AMASS will also focus on immediate translation of at least one open science practice into each participant's workflow by the following day, no matter the type of research you conduct-from work on basic mechanisms of psychopathology to clinical trials to dissemination and implementation science.

At the end of this session, the learner will be able to:

• Learn how and why various credibility-enhancing practices can support and strengthen your (and your lab's) research.
• Establish a quicker ideas-to-paper pipeline (using preprint servers to disseminate research earlier).
• Download and apply at least one tool (including a point and click interface) that helps ensure your analyses are easy for others to reproduce.
• Explain how preregistration and registered reports can facilitate publication regardless of results.
• Discover at least one way you can apply open science practices in your research starting the next day, regardless of your research area within clinical psychology.

Recommended Readings:

JAMOVI User Manual to Create Reproducible R Code Using a Point and Click Interface

Nelson, L. D., Simmons, J., & Simonsohn, U. (2018). Psychology's renaissance. Annual Review of Psychology, 69(1), 511-534.

Nosek, B. A., Ebersole, C. R., DeHaven, A. C., & Mellor, D. T. (2018). The preregistration revolution. Proceedings of the National Academy of Sciences of the United States of America, 115(11), 2600-2606.

Srivastava, S. (2018). Sound Inference in Complicated Research: A Multi-Strategy Approach. https://doi.org/10.31234/osf.io/bwr48

Tackett, J. L., Brandes, C. M., King, K. M., & Markon, K. E. (2019). Psychology's replication crisis and clinical psychological science. Annual Review of Clinical Psychology, 15, 579-604.

Intensive data collection methods and their analytic counterparts have become commonplace in basic psychological science. Despite their tremendous value for application to clinical trials, these methods have yet to be widely adopted in efficacy or effectiveness studies of psychological interventions. For example, these methods can be used to ask questions about not only whether clients have improved to subclinical levels but also about the stability of that pattern of improvement. Being able to differentiate patients who have stably improved from those who have improved but are not yet stable has promise in preventing relapse and increasing the longevity of treatment gains (e.g., Hayes & Strauss, 1998). Other applications include the study of complex change processes (e.g., Hayes et al., 2015; Hawe et al., 2009) and contextual factors associated with less prolonged/less severe symptomatology (e.g., Masten, 2004). This AMASS will (a) introduce attendees to a conceptual perspective for thinking about clinically meaningful, distinct patterns of change that psychotherapy can create (dynamical systems theory; DST), (b) compare and contrast this way of conceptualizing change with current standard practices (e.g., repeated measures ANOVA and growth curve modeling), (c) describe how ideas from DST can be integrated into common research designs, and (d) build on knowledge of descriptive statistics and ordinary least squares regression to estimate single case dynamic systems models. Depending on the statistical background of attendees, single case estimation methods will be expanded to modeling entire data sets using either multilevel modeling (MLM) or structural equation modeling (SEM). Basic familiarity with MLM or SEM is recommended for attendees. Participants are encouraged to bring their own data, and we will work through annotated examples. Simulated data and code for annotated examples will be provided.

At the end of this session, the learner will be able to:

• Develop a conceptual framework for distinguishing types of clinically meaningful patterns of change.
• Apply and interpret statistical methods that parallel the conceptual framework thereby enhancing the clinical implications drawn.
• Compare current statistical approaches indicating what translates and what is not known given the DST conceptual framework.
• Create a protocol for how these models change to parallel various research designs
• Explore how the ideas expand, with practical examples, with other advanced statistical considerations including MLM and SEM.

Recommended Readings:

Butner, J. E., Gagnon, K. T., Geuss, M. N., Lessard, D. A., & Story, T. N. (2015). Utilizing topology to generate and test theories of change. Psychological Methods, 20, 1.

Perry, N. S., Baucom, K. J., Bourne, S., Butner, J., Crenshaw, A. O., Hogan, J. N., ... Baucom, B. R. (2017). Graphic methods for interpreting longitudinal dyadic patterns from repeated-measures actor-partner interdependence models. Journal of Family Psychology, 31, 592.

Thelen, E., & Smith, L. B. (2007). Dynamic systems theories. In W. Damon & R.M. Lerner (Eds.), Handbook of child psychology, Sixth Edition. Vol 1, pp. 258-308. https://doi.org/10.1002/9780470147658.chpsy0106