Skip to main content

Statistical Methods for Response Shift Detection

1 Presentation 0 Sections

Organized By: The Response Shift SIG
Description
The current webinar will focus specifically on important and cutting-edge statistical methods for RS detection and adjustment for true change estimation, including latent variable modelling and relative importance analysis. Specifically, leading RS researchers will discuss the use of structural equation modelling (SEM), Item Response/Rasch Measurement Theory (IRT/RMT), and importance measures based on logistic regression and discriminant analysis. The strengths, limitations, and assumptions of the methods will be reviewed, as will the types of RS that can be detected with each method. An overview of available software to implement these methods will be provided. Future directions of research in the field will be discussed.

Background
Response shift (RS) refers to a change in an individual’s perceptions of his/her quality of life (QOL) or health status over time. According to Sprangers and Schwartz (1999), RS can result from three different processes: recalibration (changes in the individual’s internal standards of measurements), reprioritization (changes in the individual’s values and in the relative importance given to the questions or dimensions constituting the target construct), and reconceptualization (changes in the individual’s definition of the target construct). A literature review of RS presented at a previous ISOQOL webinar revealed that RS can occur for many different acute and chronic medical conditions and procedures, including surgeries and stroke. RS can impact the ability to detect change in QOL over time, which could ultimately impact on patient care.

Learning Outcomes/Objectives
After the webinar, the learner will be able to:
  • Participants will learn about different statistical methods that can be used for RS detection and adjustment for true change estimation
  • Participants will be able to critically compare the leading statistical methods for RS analysis and interpretation based on latent variable modelling and relative importance analysis
  • Participants will be able to assess the potential influence that RS has on the assessment of changes in patients’ health status and quality of life over time in longitudinal studies
Presenters
  • Lisa Lix, Professor & Manitoba Research Chair, BSHEc, MSc, PhD, P.Stat, University of Manitoba
  • Bellinda King-Kallimanis, Sr Scientist, Psychometrics ＆ Biostatistics, BSc, MSc, PhD, Pharmerit International
  • Myriam Blanchin, Research Engineer in Biostatistics, BSc, MSc, PhD, EA 4275 SPHERE “methodS in Patient-centered outcomes and HEalth ResEarch”, University of Nantes

    • Moderator
  • Véronique Sébille , Professor of Biostatistics, BSc, MSc, PhD, ScD, EA 4275 SPHERE “methodS in Patient-centered outcomes and HEalth ResEarch”, University of Nantes
    • Recording Policy
    Photography, video or audio recording (including screen capture) of ISOQOL courses, sessions, digital materials, or ISOQOL graphics without written permission from ISOQOL is strictly prohibited.

    Note that photographs and video recordings taken by or on behalf of ISOQOL is the property of ISOQOL.


    ISOQOL members receive a discounted rate. To view membership rates, click  here.