Abstract
Multivariate analysis of variance (MANOVA) is a powerful and versatile method to infer and quantify main and interaction effects in metric multivariate multi-factor data. It is, however, neither robust against change in units nor meaningful for ordinal data. Thus, we propose a novel nonparametric MANOVA. Contrary to existing rank-based procedures, we infer hypotheses formulated in terms of meaningful Mann–Whitney-type effects in lieu of distribution functions. The tests are based on a quadratic form in multivariate rank effect estimators, and critical values are obtained by bootstrap techniques. The newly developed procedures provide asymptotically exact and consistent inference for general models such as the nonparametric Behrens–Fisher problem and multivariate one-, two-, and higher-way crossed layouts. Computer simulations in small samples confirm the reliability of the developed method for ordinal and metric data with covariance heterogeneity. Finally, an analysis of a real data example illustrates the applicability and correct interpretation of the results.
Similar content being viewed by others
References
Acion, L., Peterson, J. J., Temple, S., Arndt, S. (2006). Probabilistic index: An intuitive non-parametric approach to measuring the size of treatment effects. Statistics in Medicine, 25(4), 591–602.
Akritas, M. G. (1986). Bootstrapping the Kaplan–Meier estimator. Journal of the American Statistical Association, 81(396), 1032–1038.
Akritas, M. G., Arnold, S. F., Brunner, E. (1997). Nonparametric hypotheses and rank statistics for unbalanced factorial designs. Journal of the American Statistical Association, 92(437), 258–265.
Barbiero, A., Ferrari, P. A. (2015). GenOrd: Simulation of discrete random variables with given correlation matrix and marginal distributions. R package version 1.4.0.
Bathke, A. C., Harrar, S. W., Madden, L. V. (2008). How to compare small multivariate samples using nonparametric tests. Computational Statistics and Data Analysis, 52(11), 4951–4965.
Bathke, A. C., Friedrich, S., Pauly, M., Konietschke, F., Staffen, W., Strobl, N., Höller, Y. (2018). Testing mean differences among groups: Multivariate and repeated measures analysis with minimal assumptions. Multivariate Behavioral Research, 53(3), 348–359.
Brown, B. M., Hettmansperger, T. P. (2002). Kruskal–Wallis, multiple comparisons and Efron dice. Australian and New Zealand Journal of Statistics, 44(4), 427–438.
Brumback, L. C., Pepe, M. S., Alonzo, T. A. (2006). Using the ROC curve for gauging treatment effect in clinical trials. Statistics in Medicine, 25(4), 575–590.
Brunner, E., Puri, M. L. (2001). Nonparametric methods in factorial designs. Statistical Papers, 42(1), 1–52.
Brunner, E., Dette, H., Munk, A. (1997). Box-type approximations in nonparametric factorial designs. Journal of the American Statistical Association, 92(440), 1494–1502.
Brunner, E., Munzel, U., Puri, M. L. (2002). The multivariate nonparametric Behrens–Fisher problem. Journal of Statistical Planning and Inference, 108(1), 37–53.
Brunner, E., Konietschke, F., Pauly, M., Puri, M. L. (2017). Rank-based procedures in factorial designs: Hypotheses about non-parametric treatment effects. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 79(5), 1463–1485.
Brunner, E., Konietschke, F., Bathke, A. C., Pauly, M. (2018). Ranks and pseudo-ranks: Paradoxical results of rank tests. arXiv preprint arXiv:1802.05650.
Davidson, R., Flachaire, E. (2008). The wild bootstrap, tamed at last. Journal of Econometrics, 146(1), 162–169.
De Neve, J., Thas, O. (2015). A regression framework for rank tests based on the probabilistic index model. Journal of the American Statistical Association, 110(511), 1276–1283.
Dobler, D. (2017). A discontinuity adjustment for subdistribution function confidence bands applied to right-censored competing risks data. Electronic Journal of Statistics, 11(2), 3673–3702.
Dobler, D., Pauly, M. (2018). Inference for the Mann–Whitney effect for right-censored and tied data. TEST, 27(3), 639–658.
Efron, B. (1979). Bootstrap methods: Another look at the jackknife. The Annals of Statistics, 7(1), 1–26.
Efron, B. (1981). Censored data and the bootstrap. Journal of the American Statistical Association, 76(374), 312–319.
Ellis, A. R., Burchett, W. W., Harrar, S. W., Bathke, A. C. (2017). Nonparametric inference for multivariate data: The R package npmv. Journal of Statistical Software, 76(4), 1–18.
Ferrari, P. A., Barbiero, A. (2012). Simulating ordinal data. Multivariate Behavioral Research, 47(4), 566–589.
Friedrich, S., Pauly, M. (2018). Mats: Inference for potentially singular and heteroscedastic manova. Journal of Multivariate Analysis, 165, 166–179.
Friedrich, S., Konietschke, F., Pauly, M. (2017). A wild bootstrap approach for nonparametric repeated measurements. Computational Statistics and Data Analysis, 113, 38–52.
Gao, X., Alvo, M. (2005). A unified nonparametric approach for unbalanced factorial designs. Journal of the American Statistical Association, 100(471), 926–941.
Gao, X., Alvo, M. (2008). Nonparametric multiple comparison procedures for unbalanced two-way layouts. Journal of Statistical Planning and Inference, 138(12), 3674–3686.
Gao, X., Alvo, M., Chen, J., Li, G. (2008). Nonparametric multiple comparison procedures for unbalanced one-way factorial designs. Journal of Statistical Planning and Inference, 138(8), 2574–2591.
Halvorsen, K. B. (2015). ElemStatLearn: Data sets, functions and examples from the book: The elements of statistical learning, data mining, inference, and prediction” by Trevor Hastie, Robert Tibshirani and Jerome Friedman. R package version 2015.6.26.
Harrar, S. W., Bathke, A. C. (2008). Nonparametric methods for unbalanced multivariate data and many factor levels. Journal of Multivariate Analysis, 99(8), 1635–1664.
Harrar, S. W., Bathke, A. C. (2012). A modified two-factor multivariate analysis of variance: Asymptotics and small sample approximations (and erratum). Annals of the Institute of Statistical Mathematics, 64(1), 135–165.
Kieser, M., Friede, T., Gondan, M. (2013). Assessment of statistical significance and clinical relevance. Statistics in Medicine, 32(10), 1707–1719.
Konietschke, F., Hothorn, L. A., Brunner, E. (2012). Rank-based multiple test procedures and simultaneous confidence intervals. Electronic Journal of Statistics, 6, 738–759.
Konietschke, F., Bathke, A. C., Harrar, S. W., Pauly, M. (2015). Parametric and nonparametric bootstrap methods for general MANOVA. Journal of Multivariate Analysis, 140, 291–301.
Kruskal, W. H. (1952). A nonparametric test for the several sample problem. The Annals of Mathematical Statistics, 23(4), 525–540.
Kruskal, W. H., Wallis, W. A. (1952). Use of ranks in one-criterion variance analysis. Journal of the American Statistical Association, 47(260), 583–621.
Lakens, D. (2013). Calculating and reporting effect sizes to facilitate cumulative science: A practical primer for t-tests and ANOVAs. Frontiers in Psychology, 4, 863.
Mann, H. B., Whitney, D. R. (1947). On a test of whether one of two random variables is stochastically larger than the other. The Annals of Mathematical Statistics, 18(1), 50–60.
Marcus, R., Eric, P., Gabriel, K. R. (1976). On closed testing procedures with special reference to ordered analysis of variance. Biometrika, 63(3), 655–660.
Munzel, U. (1999). Linear rank score statistics when ties are present. Statistics and Probability Letters, 41(4), 389–395.
Munzel, U., Brunner, E. (2000). Nonparametric methods in multivariate factorial designs. Journal of Statistical Planning and Inference, 88(1), 117–132.
Puri, M. L., Sen, P. K. (1971). Nonparametric methods in multivariate analysis. New York: Wiley.
R Core Team. (2016). R: A language and environment for statistical computing. Vienna: R Foundation for Statistical Computing.
Rust, S. W., Filgner, M. A. (1984). A modification of the Kruskal–Wallis statistic for the generalized Behrens–Fisher problem. Communications in Statistics-Theory and Methods, 13(16), 2013–2027.
Ruymgaart, F. H. (1980). A unified approach to the asymptotic distribution theory of certain midrank statistics. In J.-P. Raoult (Ed.), Statistique non Parametrique Asymptotique, pp. 1–18. Berlin: Springer.
Thangavelu, K., Brunner, E. (2007). Wilcoxon–Mann–Whitney test for stratified samples and Efron’s paradox dice. Journal of Statistical Planning and Inference, 137(3), 720–737. Special Issue on Nonparametric Statistics and Related Topics: In honor of M.L. Puri.
Thas, O., De Neve, J., Clement, L., Ottoy, J.-P. (2012). Probabilistic index models. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 74(4), 623–671.
Umlauft, M., Konietschke, F., Pauly, M. (2017). Rank-based permutation approaches for nonparametric factorial designs. British Journal of Mathematical and Statistical Psychology, 70, 368–390.
Umlauft, M., Placzek, M., Konietschke, F., Pauly, M. (2019). Wild bootstrapping rank-based procedures: Multiple testing in nonparametric factorial repeated measures designs. Journal of Multivariate Analysis, 171, 176–192.
van der Vaart, A. W., Wellner, J. A. (1996). Weak convergence and empirical processes. New York: Springer.
Wu, C.-F. J. (1986). Jackknife, bootstrap and other resampling methods in regression analysis. The Annals of Statistics, 14(4), 1261–1295.
Acknowledgements
This work was supported by the German Research Foundation (Grant No. PA-2409 4-1).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Authors are in alphabetical order.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Appendices
Appendix
A Proofs
Throughout, let \(\mathbb P_{1, n_1}, \ldots , \mathbb P_{a, n_a}\) be the empirical processes based on the samples \(\mathcal X_1, \ldots , \mathcal X_a\), respectively, which are indexed by the class of functions \(\mathcal G = \mathcal F \circ \Pi \), where
and \(\Pi = \{\pi _j : j=1,\ldots , d \}\) is the class of all canonical coordinate projections \(\pi _j : \mathbb {R}^d \rightarrow \mathbb {R}, (x_1, \ldots , x_d) \mapsto x_j\). Using this indexation, it is easily possible to derive the normalized empirical distribution functions \(\widehat{F}_{ij}\) from \(\mathbb P_{i, n_i}\). In particular, \(\widehat{F}_{ij}(x)= \mathbb P_{i, n_i} [\frac{1}{2} ({\mathbb {1}}_{(-\infty , x]}(\cdot ) + {\mathbb {1}}_{(-\infty , x)})\circ \pi _j]\), where we used the definition \(Pf = \int f \mathrm dP\) for a suitable function \(f \in \mathcal G\) and a probability measure P. We also see that every group-specific empirical process \(\mathbb P_{i, n_i}\) can be considered as an element of \(\ell ^\infty (\mathcal G)\) which contains all bounded sequences with indices in \(\mathcal G\): Based on the definition \(\mathbb P_{i, n_i} \in \ell ^\infty (\mathcal G)\) if \(\sup _{f \in \mathcal G} |Pf| < \infty \).
It is important to note that the class \(\mathcal G\) is obtained from the Vapnik–C̆ervonenkis subgraph class \(\mathcal F\) concatenated with the class of all canonical coordinate projections \(\Pi \). This conserves the Vapnik–C̆ervonenkis subgraph property as argued in Lemma 2.6.17(iii) and 2.6.18(vii) of van der Vaart and Wellner (1996). Hence, \(\mathcal G\) is a Donsker class.
Proof of Theorem 1
Clearly, \(\widehat{\mathbf{p}}\) is a multivariate version \(\phi \) of the Wilcoxon functional \(\tilde{\phi }(f,g) = \int f(u) \mathrm dg(u)\) which is applied to all of the normalized empirical distribution functions \({\widehat{F}_{ij}(x)=}\)\(\frac{1}{n_i} \sum _{k=1}^{n_i} {c(x-X_{ijk})}\). The Hadamard differentiability of the Wilcoxon functional \(\tilde{\phi }\) for normalized distribution functions has been argued in the proof of Theorem 2.1 in Dobler and Pauly (2018), and a similar result for the multivariate \(\phi \) follows immediately. Hence, asymptotic normality follows from an application of the functional delta-method (Theorem 3.9.4 in van der Vaart and Wellner, 1996): it follows that \(\sqrt{N}(\widehat{\mathbf{p}} - \mathbf{p})\) is asymptotically equal to \(\phi '_{F_{11}, \ldots , F_{ad}}( \sqrt{N}(\widehat{F}_{ij} - F_{ij})_{i,j} ) \), where \(\phi '_{F_{11}, \ldots , F_{ad}}\) is a continuous and linear functional. Hence, the Donsker theorem yields that \(\sqrt{N}(\widehat{F}_{ij} - F_{ij})_{i,j}\) converges in distribution to a Gaussian process as \(N \rightarrow \infty \) and the application of \(\phi '_{F_{11}, \ldots , F_{ad}}\) proves the asymptotic multivariate normality of \(\sqrt{N}(\widehat{\mathbf{p}} - \mathbf{p})\).
The asymptotic covariance structure of the resulting multivariate normal distribution is derived in detail in Section 10 of in the supplement, where the asymptotic linear expansion of \(\widehat{\mathbf{p}}\) in all empirical distribution functions is utilized. \(\square \)
Proof of Theorem 2
Similarly, as argued in the proof of Theorem 1, \(\mathbf{p}^*\) is obtained as a Hadamard-differentiable functional of all bootstrapped (normalized) empirical distribution functions \(F_{ij}^*(t) = \frac{1}{n_i} \sum _{k=1}^{n_i} c(t - X^*_{ijk})\), \(j=1, \ldots , d\), \(i=1, \ldots , a\). As the conditional central limit theorem holds in outer probability for each bootstrapped empirical distribution function, i.e. for each
cf. Theorem 3.6.1 in van der Vaart and Wellner (1996), the convergence is transferred to \(\sqrt{N}(\mathbf{p}^* - \widehat{\mathbf{p}})\) by means of the functional delta-method for the bootstrap; cf. Theorem 3.9.11 in van der Vaart and Wellner (1996). \(\square \)
Proof of Theorem 3
First note that, given \(\mathcal X\), we have conditional convergence in distribution of \(\mathbf{F}_N^\star = \sqrt{N} (F_{11}^\star , F_{12}^\star , \ldots , F_{ad}^\star )'\) to an (ad)-variate Brownian bridge process \((\mathbf{U}_t)_{t \in \mathbb {R}}\) in outer probability: indeed, each \(F_{ij}^\star \) can be written as
which is due to \(\sum _{k=1}^{n_i} [c(x - X_{ijk}) - \widehat{F}_{ij}(x)] = 0\). Here we let \(\bar{D}_{i\cdot } = \frac{1}{n_i} \sum _{k=1}^{n_i} D_{ik}\). If we further define \(\delta _{\mathbf{X}_{ik}}\) to be the Dirac measure in \(\mathbf{X}_{ik}\) and \(f_{j,x} = \frac{1}{2} ({\mathbb {1}}_{(-\infty , x]}(\cdot ) + {\mathbb {1}}_{(-\infty , x)})\circ \pi _j\), we see that \(c(x - X_{ijk}) = \delta _{\mathbf{X}_{ik}} f_{j,x} \). Consequently, \(F_{ij}^\star (x)\) is a marginal distribution of \(\frac{1}{n_i} \sum _{k=1}^{n_i} (D_{ik} - \bar{D}_{i \cdot }) \cdot \delta _{\mathbf{X}_{ik}} \). This proves that \(F_{ij}^\star (x)\) has the required structure for an application of the conditional Donsker Theorem 3.6.13 in van der Vaart and Wellner (1996). Finally, Example 3.6.12 shows that this Donsker theorem still holds for our choice of wild bootstrap multipliers \(D_{ik}\).
Next, recall the asymptotic linear representation (8) of
which followed from the functional delta-method and which motivated the wild bootstrap version (9). That presentation motivates that the Hadamard-derivative of the multivariate Wilcoxon-type functional \(\phi \) which depends on unknown quantities should be estimated by
Here each \(\text {P}_\ell \in \ell ^\infty (\mathcal G), \ell =1,\ldots , a,\) is a distribution on \(\mathbb {R}^d\) with marginal normalized distribution functions \(\text {F}_{\ell j}\).
We apply the extended continuous mapping theorem (Theorem 1.11.1 in van der Vaart and Wellner, 1996) to the (random) functional \(\phi '_{\widehat{F}} = (\phi _{11; \widehat{F}}', \phi _{12; \widehat{F}}', \ldots , \phi _{ad; \widehat{F}}') : \ell ^\infty (\mathcal G) \rightarrow \mathbb {R}^{ad}\). Due to the subsequence principle (Lemma 1.9.2 in van der Vaart and Wellner, 1996) convergence in outer probability is equivalent to outer almost sure convergence along subsequences given a realization of \(\mathcal X\).
The actual requirement for an application of the extended continuous mapping theorem is satisfied as well: note that \(\phi '_{\widehat{F}}\) basically consists of integral mappings of the form
where \(D(\mathbb {R})\) is the space of right- (or left-)continuous functions on \(\mathbb {R}\) with existing left- (or right-)sided limits and \(BV_1(\mathbb {R})\) is the subspace of functions with total variation bounded by 1. Lemma 3.9.17 in van der Vaart and Wellner (1996) states that \(\psi \) is Hadamard-differentiable, hence continuous. We conclude that for all sequences of functions \((f_n)_{n \in \mathbb {N}}\) and \((g_n)_{n \in \mathbb {N}}\), which converge to \(f_0\) in \(D(\mathbb {R})\) and to \(g_0\) in \(BV_1(\mathbb {R})\), respectively, the sequence of functionals \(\psi _n : f \mapsto \int f \mathrm dg_n\) satisfies \(\psi _n(f_n) \rightarrow \int f_0 \mathrm dg_0\) as \(n \rightarrow \infty \).
All in all, the extended continuous mapping theorem, combined with the conditional central limit theorem for the wild bootstrapped empirical distribution functions as stated at the beginning of this proof, concludes this proof: \(\phi '_{\widehat{F}}(\mathbf{F}_N^\star )\) converges in distribution to \(\phi (\mathbf{U})\) for almost every sample \(\mathcal X\) which is the same limit in distribution as in Theorem 1. Another application of the subsequence principle yields the desired convergence result in outer probability. \(\square \)
About this article
Cite this article
Dobler, D., Friedrich, S. & Pauly, M. Nonparametric MANOVA in meaningful effects. Ann Inst Stat Math 72, 997–1022 (2020). https://doi.org/10.1007/s10463-019-00717-3
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-019-00717-3