A Primer for the Use of Multilevel Models in Couple and Family Therapy Research

Bartle‐Haring, Suzanne; Washburn-Busk, Michelle; VanBergen, Alexandra

doi:10.1111/jmft.12433

J Marital Family Therapy

2020

DOI: 10.1111/jmft.12433

|View full text |Cite

A Primer for the Use of Multilevel Models in Couple and Family Therapy Research

Suzanne Bartle‐Haring

Michelle Washburn-Busk

Alexandra VanBergen

Abstract: This article serves as a primer for understanding how to use multilevel modeling (MLM) techniques in couple and family therapy outcome and process research. It outlines the use of HLM and Mplus-two of many software programs that can perform multilevel modelingand provides an applied example of using MLM to investigate the use of postsession feedback on couple satisfaction and change, as well as the influence of trauma on the use of postsession feedback. Two graduate students in COAMFTE accredited PhD programs … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2020

2024

Publication Types

Select...

Article2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Atkins was correct when he stated, “multilevel models are incredibly powerful and flexible tools to analyze couple and family treatment data” (2005, p. 109). The article by Bartle‐Haring, Washburn‐Busk, and VanBergen (2020) introduces readers to the methods used to conduct multilevel modeling, and the article by Wu, McWey, and Ledermann (2020) provides an excellent example of how it can be used in clinical research.…”

mentioning

confidence: 99%

An Introduction to a New Generation of Clinical Statistical Approaches

Miller

2020

J Marital Family Therapy

View full text Add to dashboard Cite

One of the most exciting, yet frustrating, aspects of being a clinical researcher is that as we therapists clinically morph and grow, so do the statistical analyses that we use. They have to change in order to account for the complexity of the work we are doing. Simple bi-variate correlations, once sufficient, paved the way for multiple regression where confounding phenomena could be controlled for. In clinical research, this allowed researchers to account for factors such as diagnosis or duration of pre-treatment impairment when examining clinical outcomes. Then, structural equation modeling (SEM) gained popularity as a tool beyond multiple regression, an improved approach for a number of reasons. SEM allowed researchers to account for measurement error, to incorporate multiple dependent variables into their research questions, to test how well a model fits the data, and to work with complex and difficult data (Wang & Wang, 2012). This allowed clinicians to account for complex change processes happening over the course of treatment. Nothing that we do clinically is simple, so why should the analyses we use to validate our approach be? Standards of practice for running and reporting statistical analyses continued to evolve. Testing and reporting of statistical power, effect sizes, and confidence intervals have increasingly become critical components of the research process to manage typical errors that arise from an overreliance on the p < .05 criterion (Cohen, 1994; Cumming, 2012). Other complex approaches emerged as means to manage the complexity of the researcher and the data. Meta-analysis became the new standard for reviewing clinical studies because of its ability to reduce researcher bias when synthesizing the results of studies. Dyadic analysis approaches such as the Actor-Partner Interdependence Model (APIM, Cook & Snyder, 2005) opened the door to more appropriate and valid analyses of data that included paired participants, such as romantic partners and parent-child dyads. These changes are exciting because they enable us to improve the precision and accuracy of our statistical analyses, thereby improving the validity of our findings (Johnson & Miller, 2014). Moreover, it is exciting to have new statistical approaches that can better model the multiple relationships and complex interactions that are inherent in couple and family therapy. However, they are also frustrating because the standard for doing state-of-the-art statistics seems to always be increasing. Learning a new statistical approach does not bring much satisfaction because, as soon as we learn it, we realize that there is something new that we need to learn. The frustration comes from feeling as if our statistical knowledge is perpetually outdated. And, make no mistake about it; newer statistical techniques seem to gravitate, like some law of physics, toward greater complexity and sophistication. Well, the evolution has continued, and there is a new generation of statistical approaches that are available to CFT researchers to enhance their ...

show abstract

mentioning

confidence: 99%

An Introduction to a New Generation of Clinical Statistical Approaches

Miller

2020

J Marital Family Therapy

View full text Add to dashboard Cite

show abstract

Perceived overlap and therapy outcomes among couple clients

Bartle‐Haring,

Whiting

2024

J Marital Family Therapy

View full text Add to dashboard Cite

This article explores couples' perceptions and expectations of closeness in a clinical setting, and how relationship perceptions and expectations are associated with treatment outcomes. Bowen's theory of differentiation suggests that healthy relationships require a balance of autonomy and connection. However, some research suggests that contemporary societal expectations are pushing couples to expect greater degrees of closeness and less autonomy. Utilizing a clinical sample of 185 couples from an on‐campus Couple and Family Therapy training clinic, this article explores couples' perceptions and expectations of relationship closeness utilizing graphics of overlapping circles. Latent profile analysis was conducted to identify three different profile groups based on perceptions and expectations. Wald tests for significant mean differences among the profiles were performed. Results identified significant differences between the three groups for satisfaction and separateness and connectedness variables, number of sessions and termination.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

A Primer for the Use of Multilevel Models in Couple and Family Therapy Research

Cited by 2 publications

References 12 publications

An Introduction to a New Generation of Clinical Statistical Approaches

An Introduction to a New Generation of Clinical Statistical Approaches

Perceived overlap and therapy outcomes among couple clients

Contact Info

Product

Resources

About