Inference under covariate-adaptive randomization: A simulation study

In clinical trials, several covariate-adaptive designs have been proposed to balance treatment arms with respect to key covariates. Although some argue that conventional asymptotic tests are still appropriate when covariate-adaptive randomization is used, others think that re-randomization tests should be used. In this manuscript, we compare by simulation the performance of asymptotic and re-randomization tests under covariate-adaptive randomization. Our simulation study confirms results expected by the existing theory (e.g. asymptotic tests do not control type I error when the model is miss-specified). Furthermore, it shows that (i) re-randomization tests are as powerful as the asymptotic tests if the model is correct; (ii) re-randomization tests are more powerful when adjusting for covariates; (iii) minimization and permuted blocks provide similar results.

Approximations of the power functions for Wald, likelihood ratio, and score tests and their applications to linear and logistic regressions

Traditionally, asymptotic tests are studied and applied under local alternative. There exists a widespread opinion that the Wald, likelihood ratio, and score tests are asymptotically equivalent. We dispel this myth by showing that These tests have different statistical power in the presence of nuisance parameters. The local properties of the tests are described in terms of the first and second derivative evaluated at the null hypothesis. The comparison of the tests are illustrated with two popular regression models: linear regression with random predictor and logistic regression with binary covariate. We study the aberrant behavior of the tests when the distance between the null and alternative does not vanish with the sample size. We demonstrate that these tests have different asymptotic power. In particular, the score test is generally asymptotically biased but slightly superior for linear regression in a close neighborhood of the null. The power approximations are confirmed through simulations.

An Asymptotic Test for Bimodality Using The Kullback–Leibler Divergence

Detecting bimodality of a frequency distribution is of considerable interest in several fields. Classical inferential methods for detecting bimodality focused in third and fourth moments through the kurtosis measure. Nonparametric approach-based asymptotic tests (DIPtest) for comparing the empirical distribution function with a unimodal one are also available. The latter point drives this paper, by considering a parametric approach using the bimodal skew-symmetric normal distribution. This general class captures bimodality, asymmetry and excess of kurtosis in data sets. The Kullback–Leibler divergence is considered to obtain the statistic’s test. Some comparisons with DIPtest, simulations, and the study of sea surface temperature data illustrate the usefulness of proposed methodology.

Tests for paired count outcomes

For moderate to large sample sizes, all tests yielded pvalues close to the nominal, except when models were misspecified. The signed-rank test generally had the lowest power. Within the current context of count outcomes, the signed-rank test shows subpar power when compared with tests that are contrasted based on full data, such as the GEE. Parametric models for count outcomes such as the GLMM with a Poisson for marginal count outcomes are quite sensitive to departures from assumed parametric models. There is some small bias for all the asymptotic tests, that is,the signed-ranktest, GLMM and GEE, especially for small sample sizes. Resampling methods such as permutation can help alleviate this.

Left‑Censored Samples from Skewed Distributions: Statistical Inference and Applications

Left‑censored data occur frequently in many areas. At present, researchers pay attention to skewed censored distributions more frequently. This paper deals with statistical inference of type I multiply left‑censored Weibull and exponential distributions. It suggests a computational procedure for calculation of maximum likelihood estimates of the parameters. The expected Fisher information matrix for estimation of variances of estimated parameters is introduced. The estimates are then used for construction of confidence intervals for the expectation using the maximum likelihood method. Asymptotic tests for comparison of distributions (expectations respectively) of two independent left‑censored Weibull samples are proposed. Furthermore, asymptotic tests for assessing suitability of reduction of the Weibull distribution to the exponential distribution are introduced. Finally, the left‑censored exponential distribution is briefly described. Methods derived in this paper are illustrated on elemental carbon measurements, and can be applied in analysis of real environmental and/or chemical data.