You could be reading the full-text of this article now if you...

If you have access to this article through your institution,
you can view this article in

Using Latent Transition Analysis in Nursing Research to Explore Change Over Time

Roberts, Tonya J.; Ward, Sandra E.

Nursing Research:
doi: 10.1097/NNR.0b013e3182001c63
Methods
Abstract

Background: Latent transition analysis is a method of modeling change over time in categorical variables. It has been used in the social sciences for many years, but not in nursing research.

Objective: The purposes of this study were to illustrate the utility of latent transition analysis for nursing research by presenting a case example (a secondary analysis of data from a previously conducted randomized control trial testing the effectiveness of a tailored psychoeducational intervention to decrease patient-related attitudinal barriers to cancer pain management) and to understand for whom and in what direction the tailored intervention resulted in change with respect to attitudinal barriers and pain symptoms.

Methods: The model was developed by (a) defining a class structure on the basis of individuals' barrier patterns, (b) adding demographic predictors and distal pain outcomes, and (c) modeling and testing transitions across classes.

Results: There were two classes of individuals: Low Barriers and High Barriers. Older, less educated individuals were more likely to be in the High Barriers class at Time 1. Individuals in either class did not have different pain outcomes at the end of the study. Of those individuals that transitioned across classes, those who received the intervention were statistically more likely to move in a favorable direction (to the Low Barriers class). Furthermore, there is evidence that some individuals in the control group had unfavorable outcomes.

Discussion: The results from the example provide useful information about for whom and in what direction the intervention resulted in change. Latent transition analysis is a valuable procedure for nurse researchers because it collapses large arrays of categorical data into meaningful patterns. It is a flexible modeling procedure with extensions allowing further understanding of a change process.

Author Information

Tonya J. Roberts, MS, RN, is Research Assistant; and Sandra E. Ward, PhD, RN, is Helen Denne Schulte Professor, Director Center for Patient-Centered Interventions, School of Nursing, University of Wisconsin-Madison.

Editor's Note Materials documenting the review process for this article are posted at http://journals.lww.com/nursingresearchonline/pages/default.aspx.

Supplemental digital content is available for this article. Direct URL citations appear in the printed text and are provided in the HTML and PDF versions of this article on the journal's Web site (www.nursingresearchonline.com).

Accepted for publication October 4, 2010.

The first author's training during a portion of this project was supported by the National Institute of Nursing Research (award no. T32NR007102). The data used in this analysis were from a parent study that was supported by the National Cancer Institute (award no. CA101907). The content is solely that of the authors and does not necessarily represent the official views of the National Institutes of Health.

Thank you to David Kaplan for valuable suggestions on developing and interpreting Mplus syntax and insightful comments on an earlier draft of this manuscript.

Corresponding author: Tonya J. Roberts, MS, RN, H6/292 CSC, 600 Highland Avenue, Madison, WI 53792-2455 (e-mail: tjbeal@wisc.edu).

© 2011 Lippincott Williams & Wilkins, Inc.