Abstract
Background: Researchers often use conventional parametric procedures to test hypotheses of health-related quality of life (HRQL) mean equality across patient groups. However, these techniques are sensitive to the presence of skewed distributions and unequal group variances, which may characterize many HRQL measures. Purpose: To conduct a sensitivity analysis of conventional and robust approaches to test hypotheses of mean equality on HRQL measures for hematopoietic stem cell transplantation survivors and a healthy comparison group. Methods: The methods applied were the conventional parametric procedure of least-squares analysis of variance applied to the raw scores, the conventional parametric procedure applied to transformed data, and a robust approximate degrees of freedom parametric procedure utilizing trimmed means and Winsorized variances. Results: The choice of analysis method affected the conclusions about the null hypothesis of mean equality. More commonly observed, however, was a substantial difference in the value of the F-statistic and standard errors which was particularly evident in the measures with greater degrees of skewness and heterogeneity of variances. Conclusions: Robust statistical tests should be incorporated into sensitivity analyses when analyzing HRQL data.
Similar content being viewed by others
Abbreviations
- ANOVA:
-
analysis of variance
- ADF:
-
approximate degrees of freedom
- CES-D:
-
Center for Epidemiologic Studies Depression Scale
- Duke-SS:
-
Duke-UNC Social Support
- ES:
-
effect size
- HC:
-
healthy comparison
- FACIT-Fatigue:
-
Functional Assessment of Chronic Illness Therapy-Fatigue
- FACIT-Sp:
-
Functional Assessment of Chronic Illness Therapy-Spiritual Well-Being
- FACT-PWB:
-
Functional Assessment of Cancer Therapy-Physical Well-Being
- HRQL:
-
health-related quality of life
- HSCT:
-
hematopoietic stem cell transplantation
- LS:
-
least squares
- MOS-Family:
-
Medical Outcomes Study-Family Functioning
- MOS-Sleep:
-
Medical Outcomes Study-Sleep Problems
- PHQ:
-
Perceived Health Questionnaire
- PTGI:
-
Posttraumatic Growth Inventory
- SD:
-
standard deviation
- SE:
-
standard error
- SF-36:
-
Medical Outcomes Study 36-item Short Form
- SF-36-GH:
-
SF-36 General Health Perceptions
- SF-36-MH:
-
SF-36 Mental Health Index
- SF-36-PF:
-
SF-36 Physical Functioning
- SF-36-SF:
-
SF-36 Social Functioning
- SIP-AB:
-
Sickness Impact Profile-Alertness Behavior
- STAI:
-
State-Trait Anxiety Inventory-Trait Anxiety
- UCLA-L:
-
UCLA Loneliness
References
SA Julious S George D Machin RJ Stephens (1997) ArticleTitleSample sizes for randomized trials measuring quality of life in cancer patients Qual Life Res 6 109–117 Occurrence Handle10.1023/A:1026481815304 Occurrence Handle1:STN:280:ByiA3cvotVI%3D Occurrence Handle9161110
MS Rose ML Koshman S Spreng R Sheldon (1999) ArticleTitleStatistical issues encountered in the comparison of health-related quality of life in diseased patients to published general population norms: Problems and solutions J Clin Epidemiol 52 405–412 Occurrence Handle10.1016/S0895-4356(99)00014-1 Occurrence Handle1:STN:280:DyaK1M3oslSrsg%3D%3D Occurrence Handle10360335
SD Ramsey K Berry C Moinpour A Giedzinska MR Andersen (2002) ArticleTitleQuality of life in long term survivors of colorectal cancer Am J Gastroenterol 97 1228–1234 Occurrence Handle12017152
LM Lix JC Keselman HJ Keselman (1996) ArticleTitleConsequences of assumption violations revisited: A quantitative review of alternatives to the one-way analysis of variance F test Rev Educ Res 66 579–619
JL Rasmussen (1986) ArticleTitleAn evaluation of parametric and non-parametric tests on modified and non-modified data Brit J Math Stat Psychol 39 213–220
RC Blair SS Sawilowsky JJ Higgins (1987) ArticleTitleLimitations of the rank transform statistic in tests for interactions Commun Stat Simul Comput 16 1133–1145
SS Sawilowsky RC Blair JJ Higgins (1989) ArticleTitleAn investigation of the type I error and power properties of the rank transform procedure in factorial ANOVA J Educ Stat 14 255–267
RR Wilcox (1995) ArticleTitleANOVA: The practical importance of heteroscedastic methods, using trimmed means versus means, and designing simulation studies Brit J Math Stat Psychol 48 99–114
HJ Keselman RR Wilcox LM Lix (2003) ArticleTitleA generally robust approach to hypothesis testing in independent and correlated groups designs Psychophysiology 40 586–596 Occurrence Handle10.1111/1469-8986.00060 Occurrence Handle1:STN:280:DC%2BD3svpt1yitA%3D%3D Occurrence Handle14570166
GS Mudholkar DK Srivastava (2000) ArticleTitleA class of robust stepwise alternatives to Hotelling’s T2 tests J Appl Stat 27 299–619
JF Reed SuffixIII (2003) ArticleTitleSolutions to the Behrens–Fisher problem Comput Meth Progr Biomed 70 259–263 Occurrence Handle10.1016/S0169-2607(02)00021-4
KK Yuen (1974) ArticleTitleThe two-sample trimmed t for unequal population variances Biometrika 61 165–170
LM Lix HJ Keselman (1998) ArticleTitleTo trim or not to trim: Tests of location equality under heteroscedasticity and nonnormality Educ Psychol Meas 58 409–429
MA Andrykowski M Bishop EA Hahn et al. (2005) ArticleTitleLong-term health-related quality of life, growth, and spiritual well-being after hematopoietic stem-cell transplantation J Clin Oncol 23 599–608 Occurrence Handle15659507
InstitutionalAuthorNameSAS Institute Inc (2002) SAS/STAT, Version 8.2 SAS Institute, Inc. Cary, NC
InstitutionalAuthorNameSAS Institute Inc (2002) SAS/IML User’s Guide, Version 8.2 SAS Institute, Inc. Cary, NC
PH Westfall SS Young (1993) Resampling-Based Multiple Testing Wiley New York
RR Wilcox HJ Keselman (2001) ArticleTitleUsing trimmed means to compare k measures corresponding to k independent groups Multivar Behav Res 36 421–444
GEP Box (1954) ArticleTitleTheorems on quadratic forms applied in the study of analysis of variance problems, I. Effect of inequality of variance in the one way classification Ann Math Stat 25 290–302
F Pesarin (2001) Multivariate Permutation Tests Wiley New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Beaumont, J.L., Lix, L.M., Yost, K.J. et al. Application of Robust Statistical Methods for Sensitivity Analysis of Health-Related Quality of Life Outcomes. Qual Life Res 15, 349–356 (2006). https://doi.org/10.1007/s11136-005-2293-1
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s11136-005-2293-1