Distribution-free tests in randomized blocks

Classes of distribution-free tests are proposed for testing homogeneity against order restricted as well as unrestricted alternatives in randomized block designs with multiple observations per cell. Allowing for different interblock scoring schemes, these tests are constructed based on the method of within block rankings. Asymptotic distributions (cell sizes tending to infinity) of these tests are derived under the assumption of homogeneity. The Pitman asymptotic relative efficiencies relative to the least squares statistics are studied. It is shown that when blocks are governed by different distributions, adaptive choice of scores within each block results in asymptotically more efficient tests as compared with methods that ignore such information. Monte Carlo simulations of selected designs indicate that the method of within block rankings is more power robust with respect to differing block distributions.     

A modification of the kruskal-wallis statistic for the generalized behrens-fisher problem

The problem of testing the equality of the medians of several populations is considered. Standard distribution-free procedures for this problem require that the populations have the same shape in order to maintain their nominal significance level, ever asymptotically, under the null hypothesis of equal medians , A modification of the Kruskal-Wallis test statistic is proposed which is exactly distribution-free under the usual nonparanetric asswnption that the continuous populations are identical with any shape. It is asymptotically distribution-free when the Continuous populations are asswned to be syrmnetric with equal medians.     

Modifications of the Mack-Wolfe umbrella tests for a generalized Behrens-Fisher problem

We are concerned with testing procedures for umbrella alternatives in the k-sample location problem without making the assumption that the underlying populations have the same shape. Modifications of the Mack-Wolfe tests are proposed for the cases when the peak of the umbrella is known or unknown. The proposed procedures are exactly distribution-free when the continuous populations have the same shape. The modified test for peak-known umbrella alternatives remains asymptotically distribution-free when the continuous populations are symmetric, but not necessarily with the same shape.     

Unbiased goodness-of-fit tests

Familiar distribution-free goodness-of-fit tests like the Kolmogorov–Smirnov test are all biased tests. In this paper, we show how to compute the bias of any distribution-free goodness-of-fit test that corresponds to a distribution-free confidence band for the cumulative distribution function (CDF). The bias of the Kolmogorov–Smirnov test turns out to be smaller than the biases of other distribution-free goodness-of-fit tests. We also develop a method for obtaining unbiased goodness-of-fit tests, which can then be inverted to obtain unbiased confidence bands for the CDF. Interestingly, only a discrete set of levels are available for the unbiased tests. Our power comparisons show that while removing bias improves the power of a test at some alternatives, it does not improve the overall power properties of the test.     

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.     

Use of the squared ranks test to test for the equality of the coefficients of variation

A distribution-free test for the equality of the coefficients of variation from k populations is obtained by using the squared ranks test for variances, as presented by Conover and Iman (1978) and Conover (1980), on the original observations divided by their respective expected values. Substitution of the sample mean in place of the expected value results in the test being only asymptotically distribution-free. Results of a simulation study evaluating the size of the test for various coefficient of variation values and probability distributions are presented.     

A distribution-free rank-like test for scale with unequal population locations

The properties of a distribution-free rank-like test proposed by Moses (1963) for the twosample scale problem is studied and a modification of the test using Savage scores is proposed. It is shown that this rank-like test is superior to commonly used rank tests for scale in that it:(1) does not require the estimation of any location or centrality parameter, (2) does not require equal or known location parameters, (3) is robust for skewed data, (4) is resolving and (5) has some significant power advantages. The test is shown to be asymptotically normal, and asymptotic relative efficiencies are calculated. Power properties, studied via simulation, indicate that the test is especially well suited for testing for equality of scale when the data are sampled from skewed populations with unequal medians. Extensions to the J-sample problem are indicated.     

Multivariate goodness-of-fit tests based on statistically equivalent blocks

Various nonparametric procedures are known for the goodness-of-fit test in the univariate case. The distribution-free nature of these procedures does not extend to the multivariate case. In this paper, we consider an application of the theory of statistically equivalent blocks(SEB)to obtain distribution-free procedures for the multivariate case. The sample values are transformed to random variables which are distributed as sample spacings from a uniform distribution on [0, 1], under the null hypothesis. Various test statistics are known, based on the spacings, which are used for testing uniformity in the univariate case. Any of these statistics can be used in the multivariate situation, based on the spacings generated from the SEB. This paper gives an expository development of the theory of SEB and a review of tests for goodness-of-fit, based on sample spacings. To show an application of the SEB, we consider a test of bivariate normality.     

An analytic method for randomized trials with informative censoring: Part II

Consider a randomized trial in which time to the occurrence of a particular disease, say pneumocystic pneumonia in an AIDS trial or breast cancer in a mammographic screening trial, is the failure time of primary interest. Suppose that time to disease is subject to informative censoring by the minimum of time to death, loss to and end of follow-up. In such a trial, the potential censoring time is observed for all study subjects, including failures. In the presence of informative censoring, it is not possible to consistently estimate the effect of treatment on time to disease without imposing additional non-identifiable assumptions. Robins (1995) specified two non-identifiable assumptions that allow one to test for and estimate an effect of treatment on time to disease in the presence of informative censoring. The goal of this paper is to provide a class of consistent and reasonably efficient semiparametric tests and estimators for the treatment effect under these assumptions. The tests in our class, like standard weighted-log-rank tests, are asymptotically distribution-free -level tests under the null hypothesis of no causal effect of treatment on time to disease whenever the censoring and failure distributions are conditionally independent given treatment arm. However, our tests remain asymptotically distribution-free -level tests in the presence of informative censoring provided either of our assumptions are true. In contrast, a weighted log-rank test will be an -level test in the presence of informative censoring only if (1) one of our two non-identifiable assumptions hold, and (2) the distribution of time to censoring is the same in the two treatment arms. We also study the estimation, in the presence of informative censoring, of the effect of treatment on the evolution over time of the mean of repeated measures outcome such as CD4 count.     

A One-Sided Rank Test for Multivariate Censored Data

An asymptotically distribution-free test is proposed for testing the equality of two multivariate failure distributions against a particular one-sided alternative based on censored observations. This test may be interpreted as a multivariate one-sided Gehan test. The consistency of the test is established. An illustrative example is given.     

An analytic method for randomized trials with informative censoring: Part 1

Consider a randomized trial in which time to the occurrence of a particular disease, say pneumocystis pneumonia in an AIDS trial or breast cancer in a mammographic screening trial, is the failure time of primary interest. Suppose that time to disease is subject to informative censoring by the minimum of time to death, loss to and end of follow-up. In such a trial, the censoring time is observed for all study subjects, including failures. In the presence of informative censoring, it is not possible to consistently estimate the effect of treatment on time to disease without imposing additional non-identifiable assumptions. The goals of this paper are to specify two non-identifiable assumptions that allow one to test for and estimate an effect of treatment on time to disease in the presence of informative censoring. In a companion paper (Robins, 1995), we provide consistent and reasonably efficient semiparametric estimators for the treatment effect under these assumptions. In this paper we largely restrict attention to testing. We propose tests that, like standard weighted-log-rank tests, are asymptotically distribution-free -level tests under the null hypothesis of no causal effect of treatment on time to disease whenever the censoring and failure distributions are conditionally independent given treatment arm. However, our tests remain asymptotically distribution-free -level tests in the presence of informative censoring provided either of our assumptions are true. In contrast, a weighted log-rank test will be an -level test in the presence of informative censoring only if (1) one of our two non-identifiable assumptions hold, and (2) the distribution of time to censoring is the same in the two treatment arms. We also extend our methods to studies of the effect of a treatment on the evolution over time of the mean of a repeated measures outcome, such as CD-4 count.     

Comparison of tests for bivariate symmetry versus location and/or scale alternatives

This paper studies the performance of tests which use a null hypothesis of bivariate symmetry and detect the broad class of location and/or scale alternatives . The conditionally distribution-free tests of Sen (1967) and Hollander (1971) and parametric tests related to those of Bell and Haller (1969) are compared in a Monte Carlo study which also includes a new conditionally distribution-free test.     

Nonparametric tests of independence of two autoregressive time series based on autoregression rank scores

We propose a nonparametric test of independence of two autoregressive time series. The test statistic is based on lagged cross-correlation coefficients computed from autoregression rank scores, and extends the traditional correlogram-based method of Haugh (1976). It is easily computable, asymptotically distribution-free, and, contrary to its traditional parametric competitor, it does not require any estimation of the unknown autoregression parameters. The test is applied in a study of the relations between outdoor temperature and the daily mortality related to cardio-vascular problems in Brussels, during the period 1980–1989.     

On nonparametric profile analysis of several multivariate samples

A unified development is offered for asymptotically distribution-free profile analysis of several multivariate samples. This includes as special cases procedures based on generalized U-statistics and also those based on linear rank statistics. Furthermore, it includes as special cases analysis of location profiles and also scalar profiles. Finally, asymptotic power and consistency properties are discussed for tests of hypotheses and subhypotheses of interest.     

Generalized Supremum Tests for the Equality of Cause Specific Hazard Rates

In this paper we propose two new classes of asymptotically distribution-free Renyi-type tests for testing the equality of two risks in a competing risk model with possible censoring. This work extends the work of Aly, Kochar and McKeague [1994, Journal of American Statistical Association, 89, 994–999] and many of the existing tests for this problem belong to these newly proposed classes. The asymptotic properties of the proposed tests are investigated. Simulation studies are done to compare the performance with existing tests. A competing risks data set is analyzed to demonstrate the usefulness of the procedure.     

Testing for ordered alternatives by combining independent distribution-free block statistics

A class of distribution-free tests for ordered alternatives in a block design is presented. On each block a distribution-free statistic is selected, and a weighted sum of these statistics is then formed. A procedure for selecting the weighting constants which maximize the asymptotic relative efficiency is presented. The improvement in the efficiency of the weighted sum of block statistics over the unweighted sum is considered and proves interesting. Some attention is also given to the idea of using different types of statistics on different blocks.     

An adjusted friedman test for the nested design

As far as is known, no distribution-free test for treatment effects in the presence of nested column effects, is available, Therefore anadjusted Friedman-type test is derived, which is asymptotically the same as the Friedman-type test of Mack and Skillings (1980). If the assumption of commensurability holds, the adjustment is made by means of the renumbering of the cells within rows.     

Tests for Comparing Mark-Specific Hazards and Cumulative Incidence Functions

It is of interest in some applications to determine whether there is a relationship between a hazard rate function (or a cumulative incidence function) and a mark variable which is only observed at uncensored failure times. We develop nonparametric tests for this problem when the mark variable is continuous. Tests are developed for the null hypothesis that the mark-specific hazard rate is independent of the mark versus ordered and two-sided alternatives expressed in terms of mark-specific hazard functions and mark-specific cumulative incidence functions. The test statistics are based on functionals of a bivariate test process equal to a weighted average of differences between a Nelson-Aalen-type estimator of the mark-specific cumulative hazard function and a nonparametric estimator of this function under the null hypothesis. The weight function in the test process can be chosen so that the test statistics are asymptotically distribution-free. Asymptotically correct critical values are obtained through a simple simulation procedure. The testing procedures are shown to perform well in numerical studies, and are illustrated with an AIDS clinical trial example. Specifically, the tests are used to assess if the instantaneous or absolute risk of treatment failure depends on the amount of accumulation of drug resistance mutations in a subject's HIV virus. This assessment helps guide development of anti-HIV therapies that surmount the problem of drug resistance.     

Model Checks for Generalized Linear Models

In this paper we propose and study non-parametric tests for the validity of (composite) Generalized Linear Models with a given parametric link structure, which are based on certain empirical processes marked by the residuals. When properly transformed to their innovation part the resulting test statistics are distribution-free. The method perfectly adapts to a situation, when also the input vector follows a dimension reducing model.     

DISTRIBUTION-FREE TESTS BASED ON SUB-SAMPLE EXTREMA FOR TESTING AGAINST POSITIVE DEPENDENCE

A class of distribution-free tests based on U-statistics has been proposed for testing the null hypothesis of independence against positive quadrant dependence. The tests are based on U-statistics and the Kendall's-tau test belongs to this class.