RESUMO
This paper proposes two new Mantel-Haenszel test statistics for correlated binary data in 2 x 2 tables that are asymptotically valid in both sparse data (many strata) and large-strata limiting models. Monte Carlo experiments show that the statistics compare favorably to previously proposed test statistics, especially for 5-25 small to moderate-sized strata. Confidence intervals are also obtained and compared to those from the test of Liang (1985, Biometrika 72, 678-682).
Assuntos
Biometria/métodos , Intervalos de Confiança , Ensaios Clínicos Controlados como Assunto/métodos , Azia/tratamento farmacológico , Humanos , Método de Monte Carlo , Estudos Multicêntricos como Assunto/métodos , Razão de Chances , Placebos , Psoríase/tratamento farmacológico , Ensaios Clínicos Controlados Aleatórios como Assunto/métodos , Reprodutibilidade dos TestesRESUMO
Agricultural screening trials often involve a large number (t) of treatments in a complete block design with limited replication (b = 3 or 4 blocks). The null hypothesis of interest is that of no differences between treatments. For the commonly used analysis of variance (ANOVA) procedure, most texts do not discuss agreement between actual and nominal Type I error rates in the presence of nonnormality, in this small b, large t, situation. Similarly, for the Friedman and the increasingly popular "ANOVA on ranks" procedures, it is not easy to find results concerning null performance given b small and t large. In this article, we therefore present results, from two different bodies of theory, that provide useful insight concerning null performance of these ANOVA and rank procedures when t is large. The two types of theory are (i) the classical approach based on moment approximations to the permutation distribution, and (ii) central-limit-theory-based asymptotics in the nonstandard t--> infinity situation. Both approaches demonstrate the validity of standard ANOVA and of ANOVA on within-block ranks, under nonnormality when t is large. Choice of the procedure to be used on a given data set should therefore be based on consideration of power properties. In general, ANOVA on ranks will be superior to standard ANOVA for data with frequent extreme values.
Assuntos
Análise de Variância , Modelos Estatísticos , Animais , Afídeos , Lagerstroemia/parasitologiaRESUMO
New rank-based methods for analyzing data from multisite clinical trials are presented in the context of "mixed" linear models. In contrast to current rank methods, the new procedures test for a drug main effect in the presence of a random drug by site interaction (or drug by investigator interaction when there is only one investigator per site). Analogous procedures are also provided for the "fixed-effects" situation, and comparisons are made with current methods. The rationale for an analysis that assumes random investigator effects is described.
Assuntos
Modelos Estatísticos , Estudos Multicêntricos como Assunto/estatística & dados numéricos , Análise de Variância , Biometria , HumanosRESUMO
A statistical test for detecting genetic differentiation of subpopulations is described that uses molecular variation in samples of DNA sequences from two or more localities. The statistical significance of the test is determined with Monte Carlo simulations. The power of the test to detect genetic differentiation in a selectively neutral Wright-Fisher island model depends on both sample size and the rates of migration, mutation, and recombination. It is found that the power of the test is substantial with samples of size 50, when 4Nm less than 10, where N is the subpopulation size and m is the fraction of migrants in each subpopulation each generation. More powerful tests are obtained with genes with recombination than with genes without recombination.
Assuntos
Evolução Biológica , Variação Genética , Modelos Genéticos , Álcool Desidrogenase/genética , Animais , Drosophila melanogaster/genética , Genética Populacional , Geografia , Método de Monte Carlo , Mutação , Recombinação Genética , Cromossomo XRESUMO
A mixture model is described for dose-response studies where measurements on a continuous variable suggest that some animals are not affected by treatment. The model combines a logistic regression on dose for the probability an animal will "respond" to treatment with a linear regression on dose for the mean of the responders. Maximum likelihood estimation via the EM algorithm is described and likelihood ratio tests are used to distinguish between the full model and meaningful reduced-parameter versions. Use of the model is illustrated with three real-data examples.
Assuntos
Relação Dose-Resposta a Droga , Modelos Biológicos , Algoritmos , Análise de Variância , Animais , Biometria , Funções Verossimilhança , Modelos Logísticos , Modelos Estatísticos , Método de Monte Carlo , Análise de RegressãoRESUMO
The mean residual life function of a population gives an intuitive and interesting perspective on the aging process. Here we present new nonparametric methods for comparing mean residual life functions based on two independent samples. These methods have the flexibility to handle crossings of the functions and result in a new type of confidence set. We also discuss similar methods for comparison of median residual life functions.
Assuntos
Expectativa de Vida , Probabilidade , Animais , Cobaias , Humanos , Tuberculose/mortalidadeRESUMO
Good (1979, Biometrics 35, 483-489) introduced a new randomization test for the two-sample problem where a proportion 1 - p of the treatment group does not respond to the treatment, and suggested that the Wilcoxon test is not effective for this situation. We show to the contrary that the Wilcoxon test is quite useful when p greater than or equal to .6 and point out an error in his definition of a one-tailed randomization test.