Abstract
This article addresses the problem of multiple contrast tests in the presence of heteroscedasticity. A procedure applying multiple degrees of freedom and a procedure based on sandwich estimation are described and compared concerning the familywise error type I. The former procedure seems to be most robust in this regard, especially for situations where high variances meet small sample sizes.
Similar content being viewed by others
References
Adler ID, Kliesch U (1990) Comparison of single and multiple treatment regiments in the mouse bone marrow micronucleus assay for hydroquinone and cyclophosphamide. Mutat Res 234:115–123
Bretz F (2006) An extension of the Williams trend test to general unbalanced linear models. Comput Stat Data Anal 50(7):1735–1748
Bretz F, Genz A, Hothorn LA (2001) On the numerical availability of multiple comparison procedures. Biom J 43:645–656
Brown MB, Forsythe AB (1974) Anova and multiple comparisons for data with heterogeneous variances. Biometrics 30(4):719–724
Demirhan H, Dolgun NA, Demirhan YP, Dolgun MO (2010) Performance of some multiple comparison tests under heteroscedasticity and dependency. J Stat Comput Simul 80(10):1083–1100
Djira GD, Hasler M, Gerhard D, Schaarschmidt F (2012) mratios: Inferences for ratios of coefficients in the general linear model. http://CRAN.R-project.org/package=mratios, R package version 1.3.17. Accessed 2 Nov 2012
Dunnett CW (1955) A multiple comparison procedure for comparing several treatments with a control. J Am Stat Assoc 50(272):1096–1121
Dunnett CW (1980) Pairwise multiple comparisons in the unequal variance case. J Am Stat Assoc 75(372):796–800
Freedman DA (2006) On the so-called “Huber Sandwich Estimator” and “Robust Standard Errors”. Am Stat 60(4):299–302
Games PA, Howell JF (1976) Pairwise multiple comparison procedures with unequal n’s and/or variances: a monte carlo study. J Educ Stat 1(2):113–125
Genz A, Bretz F (2002) Methods for the computation of multivariate \(t\)-probabilities. J Comput Graph Stat 11:950–971
Genz A, Bretz F (2009) Computation of multivariate normal and \(t\) probabilities, vol 195., Lecture notes in statisticsSpringer, Heidelberg
Genz A, Bretz F, Miwa T, Mi X, Leisch F, Scheipl F, Hothorn T (2014) mvtnorm: Multivariate normal and \(t\) distributions. http://CRAN.R-project.org/package=mvtnorm, R package version 1.0-0. Accessed 8 July 2014
Guilbaud O (2011) Note on simultaneous inferences about non-inferiority and superiority for a primary and a secondary endpoint. Biom J 53(6, SI):927–937
Hartung J, Argac D, Makambi KH (2002) Small sample properties of tests on homogeneity in one-way anova and meta-analysis. Stat Pap 43(2):197–235
Hasler M (2012) Multiple comparisons to both a negative and a positive control. Pharm Stat 11(1):74–81
Hasler M (2014) SimComp: simultaneous comparisons for multiple endpoints. http://CRAN.R-project.org/package=SimComp, R package version 2.2. Accessed 12 Sept 2014
Hasler M, Hothorn LA (2008) Multiple contrast tests in the presence of heteroscedasticity. Biom J 50(5):793–800
Hasler M, Hothorn LA (2012) A multivariate Williams-type trend procedure. Stat Biopharm Res 4:57–65
Hasler M, Vonk R, Hothorn LA (2008) Assessing non-inferiority of a new treatment in a three-arm trial in the presence of heteroscedasticity. Stat Med 27(4):490–503
Hayter AJ (1984) A proof of the conjecture that the Tukey–Kramer multiple comparisons procedure is conservative. Ann Stat 12(1):61–75
Herberich E, Sikorski J, Hothorn T (2010) A robust procedure for comparing multiple means under heteroscedasticity in unbalanced designs. PLoS One 5(3):e9788
Holm S (1979) A simple sequentially rejective multiple test procedure. Scand J Stat 6:65–70
Homma Y, Yamaguchi T, Yamaguchi O (2008) A randomized, double-blind, placebo-controlled phase ii dose-finding study of the novel anti-muscarinic agent imidafenacin in Japanese patients with overactive bladder. Int J Urol 15(9):809–815
Hommel G (1988) A stagewise rejective multiple test procedure based on a modified Bonferroni test. Biometrika 75(2):383–386
Hothorn T, Bretz F, Genz A (2001) On multivariate \(t\) and Gauss probabilities in R. R News 1(2):27–29
Hothorn T, Bretz F, Westfall PH, Heiberger RM, Schuetzenmeister A (2014) multcomp: Simultaneous inference in general parametric models. http://CRAN.R-project.org/package=multcomp, R package version 1.3-7. Accessed 2 Oct 2014
Huber PJ (1967) The behavior of maximum likelihood estimates under nonstandard conditions. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, vol 1. pp 221–233
Kromrey JD, LaRocca MA (2004) Power and type i error rates of new pairwise multiple comparison procedures under heterogeneous variances. J Exp Educ 63(4):343–362
Li H, Ning W (2012) Multiple comparisons with a control under heteroscedasticity. J Appl Stat 39(10):2275–2283
Lumley T, Zeileis A (2014) Sandwich: robust covariance matrix estimators. http://CRAN.R-project.org/package=sandwich, R package version 2.3-2. Accessed 24 Aug 2014
MacKinnon JG, White H (1985) Some heteroskedasticity-consistent covariance-matrix estimators with improved finite-sample properties. J Econom 29(3):305–325
Mehrotra DV (1997) Improving the Brown–Forsythe solution to the generalized Behrens–Fisher problem. Commun Stat Simul Comput 26(3):1139–1145
R Core Team (2013) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. http://www.R-project.org/
Ramsey PH, Ramsey PP (2009) Power and type I errors for pairwise comparisons of means in the unequal variances case. Br J Math Stat Psychol 62:263–281
Satterthwaite FE (1946) An approximate distribution of estimates of variance components. Biometrics 2:110–114
Strassburger K, Bretz F (2008) Compatible simultaneous lower confidence bounds for the Holm procedure and other Bonferroni-based closed tests. Stat Med 27(24):4914–4927
Sun WG, McLain AC (2012) Multiple testing of composite null hypotheses in heteroscedastic models. J Am Stat Assoc 107(498):673–687
Tamhane AC, Logan BR (2004) Finding the maximum safe dose level for heteroscedastic data. J Biopharm Stat 14(4):843–856
Tukey JW (1953) The problem of multiple comparisons, dittoed manuscript of 396 pages. Department of Statistics, Princeton University, New Jersey
Welch BL (1938) The significance of the difference between two means when the population variances are unequal. Biometrika 29:350–362
Welch BL (1951) On the comparison of several mean values—an alternative approach. Biometrika 38(3–4):330–336
Westfall PH, Young SS (1993) Resampling-based multiple testing, Examples and methods for p-value adjustment. Wiley-Interscience, Berlin
Williams DA (1971) A test for differences between treatment means when several dose levels are compared with a zero dose control. Biometrics 27:103–117
Zeileis A (2004) Econometric computing with HC and HAC covariance matrix estimators. J Stat Softw 11(10):1–17
Zeileis A (2006) Object-oriented computation of sandwich estimators. J Stat Softw 16(9):1–16
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hasler, M. Heteroscedasticity: multiple degrees of freedom vs. sandwich estimation. Stat Papers 57, 55–68 (2016). https://doi.org/10.1007/s00362-014-0640-4
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00362-014-0640-4