Rank tests for the k-sample problem with restricted alternatives

An asymptotically maximin most powerful rank test among somewhere asymptotically most powerful linear rank tests with scores generating function cf> is derived for each of the simple order alternative, the simple loop alternative and the simple tree alternative in the k-sample problem. The comparisons of the tests obtained with the rank analogues of the Bartholomew's xv tests are made in terms of local asymptotic relative efficiency. It is found that our tests are better than the rank analogues of the xk tests. Furthermore, the asymptotic equivalence of the ranking by the pooled sample to the ranking in pairs are discuss¬ed and the tests which are asymptotically equivalent to ours are given.     

Approximate and exact distributions of rank tests for balanced incomplete block designs

Judges rank k out of t objects according to m replic ations of abasic balanced incomplete block design with bblocks. In Alvo and Cabilio(1991),it is shown that the Durbin test, which is the usual test in this situation, can be written in terms of Spearman correlations between the blocks, and using a Kendall correlation, they generated a new statistic for this situation.This Kendall tau based statistic has a richer support than the Durbin statistic, and is at least as efficient.In the present paper,exact and simulation based tables are generated for both statistics, and various approximations to these null distributions are considered and compared.     

The matched pair sign test using bivariate ranked set sampling for different ranking based schemes

Bivariate rank set sample (BVRSS) matched pair sign test is introduced and investigated for different ranking based schemes. We show that this test is asymptotically more efficient and more powerful than its counterpart sign test based on a bivariate simple random sample (BVSRS) for different ranking schemes. The asymptotic null distribution and the efficiency of the test are derived. Pitman’s asymptotic relative efficiency is used to compare the asymptotic performance of the matched pair sign test using BVRSS versus using BVSRS in all ranking cases. For small sample sizes, the bootstrap method is used to estimate P-values. Numerical comparisons are used to gain insight about the efficiency of the BVRSS sign test compared to the BVSRS sign test. Our numerical and theoretical results indicate that using any ranking scheme of BVRSS for the matched pair sign test is more efficient than using BVSRS.     

The Gaussian rank correlation estimator: robustness properties

The Gaussian rank correlation equals the usual correlation coefficient computed from the normal scores of the data. Although its influence function is unbounded, it still has attractive robustness properties. In particular, its breakdown point is above 12%. Moreover, the estimator is consistent and asymptotically efficient at the normal distribution. The correlation matrix obtained from pairwise Gaussian rank correlations is always positive semidefinite, and very easy to compute, also in high dimensions. We compare the properties of the Gaussian rank correlation with the popular Kendall and Spearman correlation measures. A simulation study confirms the good efficiency and robustness properties of the Gaussian rank correlation. In the empirical application, we show how it can be used for multivariate outlier detection based on robust principal component analysis.     

Deux méthodes d'estimation pour les paramètres de processus moyenne mobile spatiaux

We consider moving average processes, {X_s, s ∈ ??}, where ?? is a triangular lattice in the plane R^2. To estimate the parameters of such processes, Adjengue & Moore (1993) have considered likelihood and gaussian pseudo-likelihood methods. We consider here two other methods. The first one is based on the estimation of the correlations and the relation between these correlations and the parameters of the process. The second relies on a linear approximation of the process. The asymptotic properties of the proposed estimators are analyzed and compared. A simulation study allows us to compare the estimators for fixed sample sizes.     

The chernoff efficiency of the wilcoxon rank test

Exact limiting Chernoff efficiencies of the Wilcoxon rank test are derived using Hoadley's results. Efficiency curves are derived for the two-sample Wilcoxon rank test relative to the two-sample t test for normal shift alternatives when the null hypothesis is that of common normality. The comparisons with Bahadur efficiency and small sample Hodges-Lehmann efficiency-are also made.     

Asymptotic optimality of a class of rank tests for replicated latin-square designs

This paper is concerned with the class of conditionally distribution-free rank tests introduced by Monga and Tardif (1994) for replicated Latin-square designs. It is possible to proceed with an enlargement of this class by making use of the method of ranking after substitution. The unconditional asymptotic behaviour of any member of the enlarged class is derived under the null hypothesis of no treatment effects as well as under a sequence of contiguous alternatives. This enables the establishment of the asymptotic Pitman efficiency of any member relative to the asymptotically minimax test and to conclude that at least one member of the class is asymptotically as efficient as the latter.     

Stochastic equivalence of ranking methods

The asymptotic behavior of linear rank statistics for comparing the locations of two populations, where the observations are ranked jointly with other populations, is considered. Under certain conditions, the asymptotic behavior of these statistics does not depend on which other populations are included in the ranking. In particular, the difference of a pair of these statistics, with the same score function, but based on two different rankings, converges to zero in probability under Pitman alternatives and Chernoff-Savage conditions on the scores and underlying distributions.     

A comparison of approximations to the distribution of average kendall tau

The average Kendall tau test for the null hypothesis of compLete randomness in n judges' rankings of r objects was introduced by Ehrenberg (1952). The superior efficiency of this test. as measured by approximate Bahadur slope has been established by Alva, Cabilio, and Feigin (1982).

The purpose of this paper is first to provide further justification for the use of this test, and second to compare the accuracy of the asymptotic distribution to other app roxtmations to the null distribution for small values of r and n. In the process we generate tables for this exact dis tribution for r=3 and n=3(1)19, r=4 and n=3(1)9, r=5 and n=3(1)5.     

Linear rank tests for homogeneity against ordered alternatives in anova and anocova

A unified method of constructing rank tests for homogeneity against ordered alternatives in unbalanced analysis of variance and analysis of covariance is considered. The relationship between these tests with some of the existing methods are studied. The normal theory likelihood ratio tests are also derived and the asymptotic relative efficiency comparisons, in Pitman sense, of the rank tests with respect to the likelihood ratio tests are carried out.     

Influence functions of the Spearman and Kendall correlation measures

Nonparametric correlation estimators as the Kendall and Spearman correlation are widely used in the applied sciences. They are often said to be robust, in the sense of being resistant to outlying observations. In this paper we formally study their robustness by means of their influence functions and gross-error sensitivities. Since robustness of an estimator often comes at the price of an increased variance, we also compute statistical efficiencies at the normal model. We conclude that both the Spearman and Kendall correlation estimators combine a bounded and smooth influence function with a high efficiency. In a simulation experiment we compare these nonparametric estimators with correlations based on a robust covariance matrix estimator.     

Rank-order choice-based conjoint experiments: Efficiency and design

In a rank-order choice-based conjoint experiment, the respondent is asked to rank a number of alternatives of a number of choice sets. In this paper, we study the efficiency of those experiments and propose a D-optimality criterion for rank-order experiments to find designs yielding the most precise parameter estimators. For that purpose, an expression of the Fisher information matrix for the rank-ordered conditional logit model is derived which clearly shows how much additional information is provided by each extra ranking step. A simulation study shows that, besides the Bayesian D-optimal ranking design, the Bayesian D-optimal choice design is also an appropriate design for this type of experiments. Finally, it is shown that considerable improvements in estimation and prediction accuracy are obtained by including extra ranking steps in an experiment.     

A 2-dimensional extension of the Bradley–Terry model for paired comparisons

The Bradley–Terry model is widely and often beneficially used to rank objects from paired comparisons. The underlying assumption that makes ranking possible is the existence of a latent linear scale of merit or equivalently of a kind of transitiveness of the preference. However, in some situations such as sensory comparisons of products, this assumption can be unrealistic. In these contexts, although the Bradley–Terry model appears to be significantly interesting, the linear ranking does not make sense. Our aim is to propose a 2-dimensional extension of the Bradley–Terry model that accounts for interactions between the compared objects. From a methodological point of view, this proposition can be seen as a multidimensional scaling approach in the context of a logistic model for binomial data. Maximum likelihood is investigated and asymptotic properties are derived in order to construct confidence ellipses on the diagram of the 2-dimensional scores. It is shown by an illustrative example based on real sensory data on how to use the 2-dimensional model to inspect the lack-of-fit of the Bradley–Terry model.     

THE OPTIMAL CRITICAL VALUE OF A PRE-TEST FOR AN INEQUALITY RESTRICTION IN A MIS-SPECIFIED REGRESSION MODEL

Optimal critical values are derived for a pre-test of an inequality restriction in a model where relevant regressors are unwittingly omitted. The criterion adopted is either that of the minimum average relative risk, or that of the mini-max regret. The latter approach yields an optimal critical value which is sensitive to the degree of model mis-specification, while the former criterion always leads to the choice of the unrestricted estimator.     

The extended two-sample problem: nonparametric case

The classical two-sample problem is extended here to the case where the distribution functions of the observable random variables are specified functions of unknown distribution functions and the null hypotheses to be tested or the parameters to be estimated relate to these unknown distributions. Various properties of the proposed rank tests and derived estimates are studied.     

Comparison of Confidence Intervals on Between Group Variance in Unbalanced Heteroscedastic One-Way Random Models

A computer algorithm for computing the alternative distributions of the Wilcoxon signed rank statistic under shift alternatives is discussed. An explicit error bound is derived for the numeric integration approximation to these distributions.

A nonparametric process control procedure in which the standard CUSUM procedure is applied to the Wilcoxon signed rank statistic is discussed. In order to implement this procedure, the distribution of the Wilcoxon statistic under shift of the underlying distribution from its point of symmetry needs to be computed. The average run length of the nonparametric and parametric CUSUM are compared.     

A weighted dispersion function for estimation in linear models

Robust estimates for the parameters in the general linear model are proposed which are based on weighted rank statistics. The method is based on the minimization of a dispersion function defined by a weighted Gini's mean difference. The asymptotic distribution of the estimate is derived with an asymptotic linearity result. An influence function is determined to measure how the weights can reduce the influence of high-leverage points. The weights can also be used to base the ranking on a restricted set of comparisons. This is illustrated in several examples with stratified samples, treatment vs control groups and ordered alternatives.     

Asymptotic power efficiency for a location and scale problem

The asymptotic power efficiency of the class of linear rank tests relative to the asymptotically most powerful rank test is derived for a two sample location and scale problem and numerical evaluations are presented for two special tests.     

Asymptotic efficiency of majority rule relative to rank-sum method for selecting the best population

The ranking and selection problem has been well-studied in the case of continuous responses. In this paper, we address the situation in which continuous responses are replaced by discrete orderings. When individuals in the population provide exhaustive rank-orderings of the alternatives, two common decision rules are the majority rule and the rank-sum method. In the former case, the alternative receiving the most first-place votes is declared superior, while in the latter, the alternative with the smallest rank-sum is deemed the best. Both the Pitman efficiencies and the lower bounds on Bahadur efficiencies of the majority rule relative to the rank-sum method are derived, assuming that the rank data are generated from either the Plackett–Luce or the translative strengths models. In addition, finite sample properties of the two methods are compared with the maximum likelihood approach through simulation studies. Our results suggest two things. First, when it is substantially more difficult to obtain a complete rank-ordering than simply the top choice, the majority rule performs adequately and efforts would be better spent asking many voters to provide top choice rather than fewer voters to provide complete orderings. Second, the rank-sum rule compares favorably to, and is substantially more robust than, the maximum likelihood approach.     

Estimators based on trimmed Kendall’s tau in multivariate copula models

A common method of estimating the parameters of dependency in multivariate copula models is by maximum likelihood principle, termed as Inference From Marginals (IFM); see Joe (1997)  [13]. To avoid possible misspecification of the marginal distributions, some authors suggest rank-based procedures for estimating the parameters of dependency in a multivariate copula model. A standard approach for this problem is through maximization of the pseudolikelihood, as discussed in Genest et al. (1995)  [9] and Shih and Louis (1995)  [23]. Alternative estimators based on the inversion of two multivariate extensions of Kendall’s tau, due to Kendall and Babington Smith (1940)  [14] and Joe (1990)  [12], were used in Genest et al. (2011)  [10]. In the literature, dependency of data was considered in the whole data space. However, it may be better to divide the data set into two distinct sets, lower and higher than a threshold, and then evaluate the dependency parameters in these sets. In this way, we may have different dependency parameters in these sets which may shed additional light. For example, in drought analysis, precipitation and minimum temperature may be modeled using copulas in which case we can infer that dependency between precipitation and minimum temperature are severe when they are less than a certain threshold. In this paper, after introducing trimmed Kendall’s tau when such a threshold is imposed, we consider modeling dependency using it as a measure. Asymptotic distribution of trimmed Kendall’s tau is also investigated, and a test for the null hypothesis of equality between Kendall’s tau and trimmed Kendall’s tau is constructed. We can use this hypothesis testing procedure for testing the hypothesis that data are dependent before a threshold value and are independent after the threshold. An explicit form of the asymptotic distribution of trimmed Kendall’s tau and of the mentioned test statistic are also derived for some special families of copulas. Finally, the results of a simulation study and an illustrative example are provided.