Online Program Home
My Program

Abstract Details

Activity Number: 430 - Contributed Poster Presentations: Section on Statistical Consulting
Type: Contributed
Date/Time: Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Consulting
Abstract #329096
Title: Using Actor-Partner Interdependence Model (APIM) to Analyze Patient-Sibling Paired Data
Author(s): Ke Yan* and Liyun Zhang and Craig Erker and Julie Panepinto and Pippa Simpson
Companies: Medical College of Wisconsin and Medical College of Wisconsin and Cincinnati Children's Hospital Medical Center and Medical College of Wisconsin and Medical College of Wisconsin
Keywords: Clustered data; Actor-partner interdependence model
Abstract:

Introduction: 73 pairs of patient-sibling data were collected from children with cancer and their siblings aged 8 - 17 years old. Both patients and siblings completed the Patient-Reported Outcomes Measurement Information System (PROMIS) short forms for family relationships and for depressive symptoms and peer relationships. Age and gender of all children, along with diagnoses types of patients were also collected. Of interest was which variables predict family relationships scores. Methods: The actor-partner interdependence model (APIM) for measuring bidirectional effects in interpersonal relationships was used. Two components of the APIM, the actor and the partner effects, were estimated by a "two-intercept" multilevel modelling (MLM) approach. Results: Depressive symptoms were the most significant predictor for family relationships scores. Patients' family relationships scores were affected by both their own and their siblings' depressive symptoms. However, siblings' family relationships scores were more affected by their own, but not much by patients' depressive symptoms. Conclusion: The APIM can be very useful in analyzing data with distinguishable repeats within clusters.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program