Testing for Bivariate Extreme Dependence Using Kendall's Process

Abstract. New tests for the hypothesis of bivariate extreme‐value dependence are proposed. All test statistics that are investigated are continuous functionals of either Kendall's process or its version with estimated parameters. The procedures considered are based on linear combinations of moments and on Cramér–von Mises distances. A suitably adapted version of the multiplier central limit theorem for Kendall's process enables the computation of asymptotically valid p‐values. The power of the tests is evaluated for small, moderate and large sample sizes, as well as asymptotically, under local alternatives. An illustration with a real data set is presented.     

A two- sample partially sequential probability ratio test

A two-sample partially sequential probability ratio test (PSPRT) is considered for the two-sample location problem with one sample fixed and the other sequential. Observations are assumed to come from two normal poptilatlons with equal and known variances. Asymptotically in the fixed-sample size the PSPRT is a truncated Wald one sample sequential probability test. Brownian motion approximations for boundary-crossing probabilities and expected sequential sample size are obtained. These calculations are compared to values obtained by Monte Carlo simulation.     

Ordered Alternatives and the 1 1/2-Tail Test

Under proper conditions, two independent tests of the null hypothesis of homogeneity of means are provided by a set of sample averages. One test, with tail probability P ₁, relates to the variation between the sample averages, while the other, with tail probability P ₂, relates to the concordance of the rankings of the sample averages with the anticipated rankings under an alternative hypothesis. The quantity G = P ₁ P ₂ is considered as the combined test statistic and, except for the discreteness in the null distribution of P ₂, would correspond to the Fisher statistic for combining probabilities. Illustration is made, for the case of four means, on how to get critical values of G or critical values of P ₁ for each possible value of P ₂, taking discreteness into account. Alternative measures of concordance considered are Spearman's ρ and Kendall's τ. The concept results, in the case of two averages, in assigning two-thirds of the test size to the concordant tail, one-third to the discordant tail.     

Testing for equivalence of variances using Hartley's ratio

Hartley's test for homogeneity of k normal‐distribution variances is based on the ratio between the maximum sample variance and the minimum sample variance. In this paper, the author uses the same statistic to test for equivalence of k variances. Equivalence is defined in terms of the ratio between the maximum and minimum population variances, and one concludes equivalence when Hartley's ratio is small. Exact critical values for this test are obtained by using an integral expression for the power function and some theoretical results about the power function. These exact critical values are available both when sample sizes are equal and when sample sizes are unequal. One related result in the paper is that Hartley's test for homogeneity of variances is no longer unbiased when the sample sizes are unequal. The Canadian Journal of Statistics 38: 647–664; 2010 © 2010 Statistical Society of Canada     

Exact Tests for 2 × 2 Contingency Tables

Fisher's exact test, difference in proportions, log odds ratio, Pearson's chi-squared, and likelihood ratio are compared as test statistics for testing independence of two dichotomous factors when the associated p values are computed by using the conditional distribution given the marginals. The statistics listed above that can be used for a one-sided alternative give identical p values. For a two-sided alternative, many of the above statistics lead to different p values. The p values are shown to differ only by which tables in the opposite tail from the observed table are considered more extreme than the observed table.     

On testing homogeneity of t normal means against ordered alternatives in r groups

Given k=rt normal populations with a common but unknown variance consisting of t treatments applied to r different groups of units, and supposing that in each group the means are monoto-nically non-decreasing (or non-increasing), then the likelihood ratio test of homogeneity of the means in each group against the simple order alternative is considered. Critical values are provided when one observation is drawn from each of the k populations.     

In Memoriam: Jack Carl Kiefer 1924–1981

This note provides a new explanation for Tukey's definition of “(inner) fences” for box-and-whiskers plots. The starting point is explicit bounds for the sample mean based only on the box plot. Starting from these bounds we define a dataset to contain outside values if at least one of the latter bounds is outside of the box. This leads to a new, yet simple definition of fences. They are symmetric around the box if, and only if, the median is in the middle of the box. In that case, the new definition coincides with Tukey's rule of 1.5 times the inter quartile range. To avoid instabilities for small (sub-) samples we propose to complement the box-and-whiskers plot of the original data with a box-and-whiskers plot of Walsh means.     

Selection and Ranking Procedures for Type I Extreme Value Populations and a Related Homogeneity Test

Consider k (≥2) independent Type I extreme value populations with unknown location parameters and common known scale parameter. With samples of same size, we study procedures based on the sample means for (1) selecting the population having the largest location parameter, (2) selecting the population having the smallest location parameter, and (3) testing for equality of all the location parameters. We use Bechhofer's indifference-zone and Gupta's subset selection formulations. Tables of constants for implemention are provided based on approximation for the distribution of the standardized sample mean by a generalized Tukey's lambda distribution. Examples are provided for all procedures.     

Power studies of tests for uniformity,II

Results from a power study of six statistics for testing that a sample is from a uniform distribution on the unit interval (0,1) are reported. The test statistics are all well-known and each of them was originally proposed because they should have high power against some alternative distributions. The tests considered are the Pearson probability product test, the Neyman smooth test, the Sukhatme test, the Durbin-Kolmogorov test, the Kuiper test, and the Sherman test. Results are given for each of these tests against each of four classes of alternatives. Also, the most powerful test against each member of the first three alternatives is obtained, and the powers of these tests are given for the same sample sizes as for the six general "omnibus" test statistics. These values constitute a "power envelope" against which all tests can be compared. The Neyman smooth tests with 2nd and 4th degree polynomials are found to have good power and are recommended as general tests for uniformity.     

A revision of the tukey multiple comparisons procedure to control the probability of committing at most one type i error

Halperin et al. (1988) suggested an approach which allows for k Type I errors while using Scheffe's method of multiple comparisons for linear combinations of p means. In this paper we apply the same type of error control to Tukey's method of multiple pairwise comparisons. In fact, the variant of the Tukey (1953) approach discussed here defines the error control objective as assuring with a specified probability that at most one out of the p(p-l)/2 comparisons between all pairs of the treatment means is significant in two-sided tests when an overall null hypothesis (all p means are equal) is true or, from a confidence interval point of view, that at most one of a set of simultaneous confidence intervals for all of the pairwise differences of the treatment means is incorrect. The formulae which yield the critical values needed to carry out this new procedure are derived and the critical values are tabulated. A Monte Carlo study was conducted and several tables are presented to demonstrate the experimentwise Type I error rates and the gains in power furnished by the proposed procedure     

A multiple test for comparing two treatments with control: Interval hypotheses approach

In biological experiments, multiple comparison test procedures may lead to a statistically significant difference in means. However, sometimes the difference is not worthy of attention considering the inherent variation in the characteristic. This may be due to the fact that the magnitude of the change in the characteristic under study after receiving the treatment is small, less than the natural biological variation. It then becomes the job of the statistician to design a test that will remove this paradox, such that the statistical significance will coincide with the biological one. The present paper develops a multiple comparison test for comparing two treatments with control by incorporating within-person variation in forming interval hypotheses. Assuming common variance (unknown) for the three groups (control and two treatments) and the width of the interval as intra-individual variation (known), the distribution of the test statistic is obtained as bivariate non-central t . A level f test procedure is designed. A table of critical values for carrying out the test is constructed for f = 0.05. The exact powers are computed for various values of small sample sizes and parameters. The test is powerful for all values of the parameters. The test was used to detect differences in zinc absorption for two cereal diets compared with a control diet. After application of our test, we arrived at the conclusion of homogeneity of diets with the control diet. Dunnett's procedure, when applied to the same data, concluded otherwise. The new test can also be applied to other data situations in biology, medicine and agriculture.     

Optimizing the wald-wolfowitz runs statistic using a linkage tolerance: guidelines based on computer simulation

When performing the Wald-Wolfowitz runs test, observations from two samples are combined and ordered, and the test statistic is the number of sequences of observations from the same sample. This test statistic is equivalent to the number of links between observations from different samples, if we consider each observation to be linked to the next higher and next lower observations. While it is known that the Wald-Wolfowitz runs test is not very powerful, what would be the effect on the power of the Wald-Wolfowitz runs test if all observations within a specified Euclidean distance or “tolerance” were linked instead? This question is motivated by the simulation results of Whaley and Quade (1985), who found that for normal data, the power of the multi-dimensional runs test using a linkage tolerance compared favorably to Hotelling's T² in some instances. The results of a similar simulation procedure show that the power of the Wald-Wolfowitz runs test does indeed improve when observations are linked using a tolerance. The results also suggest that a better large sample approximation to the distribution of the test statistic needs to be found.     

The simultaneous confidence intervals for all distances from the extreme populations for two-parameter exponential populations based on the multiply type II censored samples

Among k independent two-parameter exponential distributions which have the common scale parameter, the lower extreme population (LEP) is the one with the smallest location parameter and the upper extreme population (UEP) is the one with the largest location parameter. Given a multiply type II censored sample from each of these k independent two-parameter exponential distributions, 14 estimators for the unknown location parameters and the common unknown scale parameter are considered. Fourteen simultaneous confidence intervals (SCIs) for all distances from the extreme populations (UEP and LEP) and from the UEP from these k independent exponential distributions under the multiply type II censoring are proposed. The critical values are obtained by the Monte Carlo method. The optimal SCIs among 14 methods are identified based on the criteria of minimum confidence length for various censoring schemes. The subset selection procedures of extreme populations are also proposed and two numerical examples are given for illustration.     

Statistical analysis of non-inferiority via non-zero risk difference in stratified matched-pair studies

A stratified study is often designed for adjusting several independent trials in modern medical research. We consider the problem of non-inferiority tests and sample size determinations for a nonzero risk difference in stratified matched-pair studies, and develop the likelihood ratio and Wald-type weighted statistics for testing a null hypothesis of non-zero risk difference for each stratum in stratified matched-pair studies on the basis of (1) the sample-based method and (2) the constrained maximum likelihood estimation (CMLE) method. Sample size formulae for the above proposed statistics are derived, and several choices of weights for Wald-type weighted statistics are considered. We evaluate the performance of the proposed tests according to type I error rates and empirical powers via simulation studies. Empirical results show that (1) the likelihood ratio and the Wald-type CMLE test based on harmonic means of the stratum-specific sample size (SSIZE) weight (the Cochran's test) behave satisfactorily in the sense that their significance levels are much closer to the prespecified nominal level; (2) the likelihood ratio test is better than Nam's [2006. Non-inferiority of new procedure to standard procedure in stratified matched-pair design. Biometrical J. 48, 966–977] score test; (3) the sample sizes obtained by using SSIZE weight are smaller than other weighted statistics in general; (4) the Cochran's test statistic is generally much better than other weighted statistics with CMLE method. A real example from a clinical laboratory study is used to illustrate the proposed methodologies.     

Sequential procedures in identification

In this paper we study the problem of identifying a popula-tion with one of the two populations, with an aim to control both types of errors. We assume that the populations are normal with unknown means, but with unit variance. We have cited examples from anthropological studies where our formulation of the problem fits in quite nicely. We observe that SPRT’s based on the maximal invariant may not terminate with probability one. Simulation studies reported here show a substantial saving in the average number of samples compared to the best invariant fixed sample test.     

A computational bootstrap procedure to compare two dependent time series

It is an important problem to compare two time series in many applications. In this paper, a computational bootstrap procedure is proposed to test if two dependent stationary time series have the same autocovariance structures. The blocks of blocks bootstrap on bivariate time series is employed to estimate the covariance matrix which is necessary in order to construct the proposed test statistic. Without much additional effort, the bootstrap critical values can also be computed as a byproduct from the same bootstrap procedure. The asymptotic distribution of the test statistic under the null hypothesis is obtained. A simulation study is conducted to examine the finite sample performance of the test. The simulation results show that the proposed procedure with the bootstrap critical values performs well empirically and is especially useful when time series are short and non-normal. The proposed test is applied to an analysis of a real data set to understand the relationship between the input and output signals of a chemical process.     

Joint distribution of simultaneous exposures to several carcinogens in a case–control study: sample size determination

Consider a population of individuals who are free of a disease under study, and who are exposed simultaneously at random exposure levels, say X,Y,Z,… to several risk factors which are suspected to cause the disease in the populationm. At any specified levels X=x, Y=y, Z=z, …, the incidence rate of the disease in the population ot risk is given by the exposure–response relationship r(x,y,z,…) = P(disease|x,y,z,…). The present paper examines the relationship between the joint distribution of the exposure variables X,Y,Z, … in the population at risk and the joint distribution of the exposure variables U,V,W,… among cases under the linear and the exponential risk models. It is proven that under the exponential risk model, these two joint distributions belong to the same family of multivariate probability distributions, possibly with different parameters values. For example, if the exposure variables in the population at risk have jointly a multivariate normal distribution, so do the exposure variables among cases; if the former variables have jointly a multinomial distribution, so do the latter. More generally, it is demonstrated that if the joint distribution of the exposure variables in the population at risk belongs to the exponential family of multivariate probability distributions, so does the joint distribution of exposure variables among cases. If the epidemiologist can specify the differnce among the mean exposure levels in the case and control groups which are considered to be clinically or etiologically important in the study, the results of the present paper may be used to make sample size determinations for the case–control study, corresponding to specified protection levels, i.e., size α and 1–β of a statistical test. The multivariate normal, the multinomial, the negative multinomial and Fisher's multivariate logarithmic series exposure distributions are used to illustrate our results.     

Editor's Report

There are two common methods for statistical inference on 2 × 2 contingency tables. One is the widely taught Pearson chi-square test, which uses the well-known χ²statistic. The chi-square test is appropriate for large sample inference, and it is equivalent to the Z-test that uses the difference between the two sample proportions for the 2 × 2 case. Another method is Fisher’s exact test, which evaluates the likelihood of each table with the same marginal totals. This article mathematically justifies that these two methods for determining extreme do not completely agree with each other. Our analysis obtains one-sided and two-sided conditions under which a disagreement in determining extreme between the two tests could occur. We also address the question whether or not their discrepancy in determining extreme would make them draw different conclusions when testing homogeneity or independence. Our examination of the two tests casts light on which test should be trusted when the two tests draw different conclusions.     

Estimating the population median by nomination sampling

In nomination sampling, the largest values from several independent random samples (nominees) are rank ordered, and an estimate of the population median is formed by interpolating between 2 of these order statistics. The resulting estimate compares favorably to the sample median of a simple random sample from the same population. When historical data sets retain only extreme values, nomination sampling may offer the only practical way to estimate the population median. The approach may also be useful when potential survey respondents will only participate if they can actively influence the selection of cases for analysis.     

An empirical power study of multi-sample tests for exponentiality

Results are given of an empirical power study of three statistical procedures for testing for exponentiality of several independent samples. The test procedures are the Tiku (1974) test, a multi-sample Durbin (1975) test, and a multi-sample Shapiro–Wilk (1972) test. The alternative distributions considered in the study were selected from the gamma, Weibull, Lomax, lognormal, inverse Gaussian, and Burr families of positively skewed distributions. The general behavior of the conditional mean exceedance function is used to classify each alternative distribution. It is shown that Tiku's test generally exhibits overall greater power than either of the other two test procedures. For certain alternative distributions, Shapiro–Wilk's test is superior when the sample sizes are small.