Relative importance measures for reprioritization response shift
- 496 Downloads
Response shift (RS), a change in the meaning of an individual’s self-evaluation of a target construct, such as health-related quality of life (HRQOL), can affect the interpretation of change in measures of the construct collected over time. This study proposes new statistical methods to test for reprioritization RS, in which the relative importance of HRQOL domains changes over time.
The methods use descriptive discriminant analysis or logistic regression models and bootstrap inference to test for change in relative importance weights (Method 1) or ranks (Method 2) for discriminating between patient groups at two occasions. The methods are demonstrated using data from the Manitoba Inflammatory Bowel Disease (IBD) Cohort Study (n = 388). Reprioritization of domains from the IBD Questionnaire (IBDQ) and SF-36 was investigated for groups with active and inactive disease symptoms.
The IBDQ bowel symptoms and SF-36 bodily pain domains had the highest ranks for group discrimination. Using Method 1, there was evidence of reprioritization RS in the IBDQ social functioning domain and the SF-36 bodily pain and social functioning domains. Method 2 did not detect change for any of the domains.
Compared to IBD patients without active disease symptoms, those with active symptoms were likely to change the meaning of their self-evaluations of pain and social interactions. Further research is needed to compare these new RS detection methods under a variety of data analytic conditions before recommendations about the optimal method can be made.
KeywordsDiscriminant analysis Inflammatory bowel disease Logistic regression Longitudinal Relative importance Response shift
Descriptive discriminant analysis
Discriminant ratio coefficient
Health-related quality of life
Inflammatory bowel disease
Inflammatory Bowel Disease Questionnaire
Logistic Pratt’s index
Standardized discriminant function coefficient
Structural equation modeling
36-item Short-Form Questionnaire
Standardized logistic regression coefficient
This research was supported by a Canadian Institutes of Health Research (CIHR) New Investigator award and University of Saskatchewan Centennial Chair to the first author, a CIHR Vanier Graduate Scholarship to the second author, and a CIHR Operating Grant to the research team.
- 14.Draper, N. H., & Smith, H. (1998). Applied regression analysis (3rd ed.). New York: Wiley.Google Scholar
- 17.Agresti, A. (1996). An introduction to categorical data analysis. New York: Wiley.Google Scholar
- 19.Kruskal, W., & Majors, R. (1989). Concepts of relative importance in recent scientific literature. The American Statistician, 43, 2–6.Google Scholar
- 24.Thomas, D. R., Zumbo, B. D., Zhu, P., & Dutta, S. (2008). On measuring the relative importance of explanatory variables in a logistic regression. Journal of Modern Applied Statistical Methods, 7, 21–38.Google Scholar
- 32.Chernick, M. R. (2008). Bootstrap methods: A guide for practitioners and researchers. New Jersey: Wiley.Google Scholar
- 38.Lix, L. M., Graff, L. A., Walker, J. R., Clara, I., Rawsthorne, P., Rogala, L., et al. (2008). Longitudinal study of quality of life and psychological functioning for active, fluctuating, and inactive disease patterns in inflammatory bowel disease. Inflammatory Bowel Disease, 14, 1575–1584.CrossRefGoogle Scholar
- 39.Clara, I., Lix, L. M., Walker, J. R., Graff, L. A., Miller, N., Rogala, L., et al. (2009). The Manitoba IBD index: Evidence for a new and simple indicator of IBD activity over time. Gastroenterology, 104, 1754–1763.Google Scholar
- 43.Ware, J. E., Snow, K. K., Kosinski, M., & Gandek, B. (1993). SF-36 health survey: Manual and interpretation guide. Boston, MA: New England Medical Center, The Health Institute.Google Scholar
- 44.Little, R. J. A., & Rubin, D. B. (2002). Statistical analysis with missing data (2nd ed.). New Jersey: Wiley.Google Scholar
- 45.SAS Institute Inc. (2008). SAS/STAT user’s guide, version 9.2. Cary, NC: SAS Institute Inc.Google Scholar
- 46.Westfall, P. H., & Young, S. S. (1993). Resampling-based multiple testing: Examples and methods for p-value adjustment. New York: Wiley.Google Scholar
- 49.Jennrich, R. I. (1977). Stepwise discriminant analysis. In K. Enslein, A. Ralston, & H. S. Wilf (Eds.), Mathematical methods for digital computers (Vol. 3). New York: Wiley.Google Scholar
- 50.Thomas, D. R., & Zumbo, B. D. (1996). Using a measure of variable importance to investigate the standardization of discriminant coefficients. Journal of Educational and Behavioral Statistics, 21, 110–130.Google Scholar