Abstract
We investigate the logarithmic quantile estimation (LQE) method using fully nonparametric rank statistics to test for known trend and umbrella patterns in the main effects of three widely used designs: a fixed-effect two-factor model, a mixed-effect repeated measures model, and a mixed-effect cross-classification model. We also test for patterned alternatives in the interaction between the main effect and time in the repeated measures model. We determine the level and power of the test statistics using LQE with simulated and real data. The LQE procedure uses only the data to estimate quantiles of test statistics and does not require the estimation of the asymptotic variance nor the Satterthwaite–Smith degrees of freedom estimation. Our results show that the LQE method commonly yields conservative tests with high power when testing for patterned alternatives.
Similar content being viewed by others
Availability of data and material
Data created by simulation is reproducible through the use of the set.seed() function in R and will be provided or archived as requested by the publisher.
References
Abrams DI, Goldman AI, Launer C, Korvick JA, Neaton JD, Crane LR et al (1994) A comparative trial of didanosine or zalcitabine after treatment with zidovudine in patients with human immunodeficiency virus infection. N Engl J Med 330(10):657–662
Akritas MG, Arnold SF (1994) Fully nonparametric hypotheses for factorial designs I: Multivariate repeated measures designs. J Am Stat Assoc 89(425):336–343
Akritas MG, Arnold SF, Brunner E (1997) Nonparametric hypotheses and rank statistics for unbalanced factorial designs. J Am Stat Assoc 92(437):258–265
Akritas MG, Brunner E (1996) Rank tests for patterned alternatives in factorial designs with interactions. Festschrift on the Occasion of the 65th Birthday of Madam L. Puri. VSP-International Science Publishers, Utrecht, pp 277–288
Akritas MG, Brunner E (1997) A unified approach to rank tests for mixed models. J Stat Plan Inference 61(2):249–277
Berkes I, Csáki E (2001) A universal result in almost sure central limit theory. Stoch Process Appl 94(1):105–134
Brosamler GA (1988) An almost everywhere central limit theorem. Math Proc Camb Philos Soc 104(3):561–574
Brunner E, Denker M (1994) Rank statistics under dependent observations and applications to factorial designs. J Stat Plan Inference 42:353–378
Brunner E, Domhof S, Langer F (2002) Nonparametric Anal Longitud Data Factorial Des. Wiley-Interscience, NewYork
Brunner E, Puri ML (1996) 19 Nonparametric methods in design and analysis of experiments. Handb Stat 13:631–703
Brunner E, Puri ML (2001) Nonparametric methods in factorial designs. Stat Pap 42(1):1–52
Callegari F, Akritas MG (2004) Rank tests for patterned alternatives in two-way non-parametric analysis of variance. J Stat Plan Inference 126(1):1–23
Denker M, Tabacu L (2014) Testing longitudinal data by logarithmic quantiles. Electron J Stat 8(2):2937–2952
Denker M, Tabacu L (2015) Logarithmic quantile estimation for rank statistics. J Stat Theory Pract 9(1):146–170
Fisher A (1987) Convex-invariant means and a pathwise central limit theorem. Adv Math 63(3):213–246
Fridline M (2010) Almost sure confidence intervals for the correlation coefficient. Dissertation, Case Western Reserve University, Cleveland
Hettmansperger TP, Norton RM (1987) Tests for patterned alternatives in k-sample problems. J Am Stat Assoc 82(397):292–299
Jonckheere AR (1954) A distribution-free k-sample test against ordered alternatives. Biometrika 41(1/2):133–145
Lifshits MA (2001) Lecture notes on almost sure limit theorems. Publ IRMA Lille 54(8):1–23
Montgomery DC (2013) Des Anal Exp. J Wiley and Sons, New York
Page ES (1954) Continuous inspection schemes. Biometrika 41(1/2):100–115
Rizopoulos D (2010) JM: an R package for the joint modelling of longitudinal and time-to-event data. J Stat Softw 35(9):1–33
Schatte P (1988) On strong versions of the central limit theorem. Math Nachr 137(1):249–256
Tabacu L (2014) Logarithmic Quantile Estimation and Its Applications to Nonparametric Factorial Designs. Dissertation, The Pennsylvania State University, Pennsylvania
Terpstra TJ (1952) The asymptotic normality and consistency of Kendall’s test against trend, when ties are present in one ranking. Indag Math 14:327–333
Thangavelu K (2005) Quantile estimation based on the almost sure central limit theorem. Dissertation, University of Göttingen, Germany
Funding
Not applicable.
Author information
Authors and Affiliations
Contributions
Both authors contributed to the study conception and design. Material preparation and data analysis were performed by Mark K. Ledbetter. The first draft of the manuscript was written by Mark K. Ledbetter and Lucia Tabacu reviewed and commented on previous versions of the manuscript. Both authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflicts of interests / Competing interests
The authors declare that they have no conflict of interest.
Code availability
R code files are available and will be provided or archived as requested by the publisher.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
We sketch the proofs of Propositions 1 and 2 following the ideas from [13, 14]. For convenience, we present here the formulas from [13] that we use in our derivations (see Appendix, page 2948). [13] showed that a simple linear rank statistic based on n independent random vectors of possibly unequal lengths satisfies the almost sure central limit theorem. In our case, we use n independent random vectors of equal length \({{{\mathbf{X_1}}}},\dots ,{{{\mathbf{X_n}}}}\), having components \({{{\mathbf{X_u}}}}=(X_{u1},\) \(\dots ,\) \(X_{um})\) (\(u=1,\dots ,n\)) and \(N(n)=nm\) total number of observations. We now define the simple linear rank statistic (see [14], formulas (6)-(10))
which has the following term that appears in its Taylor decomposition
\(R_{uv}(n)\) denotes the rank of observation \(X_{uv}\backsim F_{uv}\) among all N(n) random variables, and \(\lambda _{uv}^{(n)}\) are known regression constants with maximum absolute value of one. We define the distribution function weighted by the regression constants for the n independent random vectors
and its empirical form
In the proofs equations (31) through (35) are specified for each model and used to prove the almost sure central limit theorems. The almost sure weak convergence of the linear rank statistic \(T_n\) in equation (31) can be obtained by showing the almost sure weak convergence of \(B_n\) in equation (32). By verifying the conditions in Theorem 3.1 in [19], we obtain the almost sure weak convergence of \(B_n\) in (32) (see Appendix in [13]).
Proof of Proposition 1
In the two-way fixed-effects model introduced in Section 2.1, \(X_{ijk} \backsim F_{ij}\) are independent random variables, and \(N= abn\) is the total number of subjects. We define independent random vectors \({{{\mathbf{X}}}_{{{\mathbf{ik}}}}}= (X_{i1k}, \dots , X_{ibk})'\), \(1\le i\le a\), \(1\le k \le n\). Let \(1\le l\le a\) denote the \(l^{th}\) level of factor A and define
Equations (34) and (35) become
which are the average distribution function across the levels of factor B (groups) for a fixed time (\(i=l\)) of factor A, and its empirical analog, respectively. The linear rank statistic is
where H(x) is defined in (1), and
We note that under \(H_0^F(A)\) in (10) the test statistic \(P_N^{(\text {fix})}(A)\) in (13) can be expressed as
The almost sure weak convergence of the vector
can be obtained by showing the almost sure weak convergence of the vector
As in [13], we can express \({{\tilde{{\mathbf{B}}}}_{{\mathbf{n}}}}\) as a sum of a dimensional independent random vectors \({{{\mathbf{Z_k}}}}\), which are bounded with \(E{{{\mathbf{Z_k}}}}={{{\mathbf{0}}}}\)
where \({\mathbf{Z_k}}\) has components
By the multivariate central limit theorem (MVCLT) and under Assumption 1, the vector
It can be verified using Theorem 3.1 of [19] that
where \(G_X\) is the distribution function of \({{{\mathbf{X}}}}\backsim {\mathscr {N}}({{{\mathbf{0}}}},{\varvec{{\varSigma }}})\). Lemma 2.2 of [16] implies
For the continuous function \(f:{\mathbb {R}}^a\longrightarrow {\mathbb {R}}\), \(f(x_1,\dots ,x_a)=\sum _{i=1}^{a}x_i\), and by [19] and the techniques in [24] equation (43) is equivalent to
Hence, the almost sure weak convergence of the test statistic (37) follows. \(\square\)
Proof of Proposition 2
Recall that each of the bn subjects in the partial hierarchical model of Section 2.2 can be expressed as independent random vectors \({{{\mathbf{X}}}_{{{\mathbf{jk}}}}}\) \(=\) \(\left( X_{1jk},\dots ,X_{ajk}\right) '\), \(1\le j\le 2, 1\le k\le n\), where \(X_{ijk}\backsim F_{ij}\). For fixed l,v such that \(1\le l \le a\), \(1 \le v \le b\) let
Then, the linear rank statistic has the form
and
The test statistic in (16) can be written
Consider the vectors
and
\({{\tilde{{{\mathbf{B}}}}}_{{\mathbf{n}}}}\) can be expressed as a sum of a dimensional independent random vectors
where components of the vector \({{{\mathbf{Z_k}}}}\) are
for \(1\le i \le a\). By the multivariate central limit theorem (MVCLT) and under Assumption 1, the vector
and hence,
The proof follows as in Proposition 1 by taking the function \(f:{\mathbb {R}}^{ab}\rightarrow {\mathbb {R}}\), \(f(x_1,\dots ,x_{ab})=\sum _{i=1}^{ab}x_i\). \(\square\)
Rights and permissions
About this article
Cite this article
Ledbetter, M.K., Tabacu, L. Tests for Patterned Alternatives Using Logarithmic Quantile Estimation. J Stat Theory Pract 15, 57 (2021). https://doi.org/10.1007/s42519-021-00194-z
Accepted:
Published:
DOI: https://doi.org/10.1007/s42519-021-00194-z
Keywords
- Patterned alternatives
- Almost sure central limit theorem
- Logarithmic quantile estimation
- Rank tests
- Nonparametric factorial designs