Measures of relative importance for health-related quality of life
- 353 Downloads
In health-related quality of life (HRQOL) studies, data are often collected on multiple domains for two or more groups of study participants. Quantitative measures of relative importance, which are used to rank order the domains based on their ability to discriminate between groups, are an alternative to multiple tests of significance on the group differences. This study describes relative importance measures based on logistic regression (LR) and multivariate analysis of variance (MANOVA) models.
Relative importance measures are illustrated using data from the Manitoba Inflammatory Bowel Disease (IBD) Cohort Study. Study participants with self-reported active (n = 244) and inactive (n = 105) disease were compared on 12 HRQOL domains from the Inflammatory Bowel Disease Questionnaire (IBDQ) and Medical Outcomes Study 36-item Short-Form (SF-36) Questionnaire.
All but two relative importance measures ranked the IBDQ bowel symptoms and emotional health domains as most important.
MANOVA-based importance measures are recommended for multivariate normal data and when group covariances are equal, while LR measures are recommended for non-normal data and when the correlations among the domains are small. Relative importance measures can be used in exploratory studies to identify a small set of domains for further research.
KeywordsDiscriminant analysis Health-related quality of life Inflammatory bowel disease Logistic model Multivariate analysis Relative importance
Adjusted discriminant ratio coefficient
Adjusted Pratt’s Index
Descriptive discriminant analysis
Discriminant ratio coefficient
Health-related quality of life
Inflammatory bowel disease
Inflammatory Bowel Disease Questionnaire
Multivariate analysis of variance
Ordinary least squares
Rescaled relative weight
Standardized discriminant function coefficient
36-Item Short Form Questionnaire
Standardized logistic regression coefficient
This research was supported by a Canadian Institutes of Health Research (CIHR) Vanier Graduate Scholarship to the first author, funding from the Manitoba Health Research Council and a CIHR New Investigator Award to the second author, funding from a Crohn’s and Colitis Foundation of Canada Research Investigator Award and the Bingham Chair in Gastroenterology to the last author and funding from a CIHR Operating Grant to the research team.
Conflict of interest
Dr. Lix has received funding from Amgen in the form of an unrestricted research grant. In the past year, Dr. Bernstein has received consulting fees from Abbott Canada and an unrestricted educational grant from Axcan Pharma.
- 1.Fairclough, D. L. (2002). Design and analysis of quality of life studies in clinical trials. New York: Chapman & Hall.Google Scholar
- 11.Menard, S. (1995). Applied logistic regression analysis. Thousand Oaks, CA: Sage.Google Scholar
- 12.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
- 13.Traxel, N. M., & Azen, R. (2006). Predictor importance in logistic regression: An extension of dominance analysis. Poster presented at the 114th annual convention of the American psychological association, New Orleans, LA.Google Scholar
- 18.Olejnik, S., & Algina, J. (2000). Measures of effect size for comparative studies: Applications, interpretations, and limitations. Educational Psychology, 25, 241–286.Google Scholar
- 19.Agresti, A. (1996). An introduction to categorical data analysis. New York: Wiley.Google Scholar
- 21.Agresti, A., & Finlay, B. (1986). Statistical methods for the social sciences (2nd ed.). San Francisco: Dellen/Macmillan.Google Scholar
- 22.Kaufman, R. L. (1996). Comparing effects in dichotomous logistic regression: A variety of standardized coefficients. Social Science Quarterly, 77, 90–110.Google Scholar
- 24.Cox, D. R., & Snell, E. J. (1989). The analysis of binary data (2nd ed.). London: Chapman and Hall.Google Scholar
- 26.Pratt, J. W. (1987). Dividing the indivisible: Using simple symmetry to partition variance explained. In T. Pukkila & S. Puntanen (Eds.), Proceedings of the second international conference in statistics (pp. 245–260). Tampere, Finland: University of Tampere.Google Scholar
- 27.Thomas, D. R., Hughes, E., & Zumbo, B. D. (1998). On variable importance in linear regression. Social Indicators Research: An International and Interdisciplinary Journal for Quality-of-Life Measurement, 45, 253–275.Google Scholar
- 28.Ochieng, C. O., & Zumbo, B. D. (2001). Examination of a variable ordering index in linear regression models: An assessment of the relative Pratt index in Likert data. Paper presented at the Bob Conry conference on measurement evaluation and research and methodology, Vancouver, Canada.Google Scholar
- 29.Witherill, G. G. (1986). Regression analysis with applications. London: Chapman & Hall.Google Scholar
- 32.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
- 34.Pohar, M., Blas, M., & Turk, S. (2004). Comparison of logistic regression and linear discriminant analysis: A simulation study. Metodoloski zveski, 1, 143–161.Google Scholar
- 35.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
- 37.Finch, W. H., & Laking, T. (2008). Evaluation of the use of standardized weights for interpreting results from a descriptive discriminant analysis. Multiple Linear Regression Viewpoints, 34, 19–34.Google Scholar
- 38.Gibbons, L. B., & Hosmer, D. W. (1991). Conditional logistic regression with missing data. Communications in Statistics, Part B, 20, 109–120.Google Scholar
- 39.Little, R. J. A., & Rubin, D. B. (2002). Statistical analysis with missing data (2nd ed.). New Jersey: Wiley.Google Scholar
- 40.SAS Institute Inc. (2008). SAS/STAT user’s guide, version 9.2. Cary, NC: SAS Institute Inc.Google Scholar
- 46.Irvine, E. J. (1996). Effects of budesonide therapy on quality of life in active Crohn′s disease. Respiratory Clinical Forums, 18, 81–89.Google Scholar
- 47.Shapiro, S. S., & Wilk, M. B. (1965). An analysis of variance test for normality (complete samples). Biometrika, 52, 591–611.Google Scholar
- 53.Mardia, K. V. (1980). Tests of univariate and multivariate normality. In P. R. Krishnaiah (Ed.), Handbook of statistics (Vol. 1, pp. 279–320). Amsterdam: North-Holland.Google Scholar
- 55.Huberty, C. J. (1975). The stability of three indices of relative variable contribution in discriminant analysis. Journal of Experimental Education, 44, 59–64.Google Scholar
- 59.Kim, K., & Timm, N. (2007). Univariate and multivariate general linear models: Theory and applications with SAS (2nd ed.). New York: Chapman & Hall/CRC.Google Scholar
- 61.Maurer, W., Hothorn, L. A., & Lechmacher, W. (1995). Multiple comparisons in drug clinical trials and preclinical assays: A priori ordered hypotheses. In J. Vollman (Ed.), Biometrie in der chemische-pharmazeutichen Industrie (Vol. 6). Stuttgart: Fischer Verlag.Google Scholar