‘Classical regression analysis’ assumes the normality (N), homoscedasticity (H) and serial independence (I) of regression residuals. Violation of the normality assumption may lead the investigator to inaccurate inferential statements. Recently, tests for normality have been derived for the case of homoscedastic serially independent (HZ) residuals [e.g., White and Macdonald (1980)]. Similarly, t...

Many statistical tests require data to be approximately normally distributed. Usually, the first step of data analysis is to test the normality. Also, we often test the normality of residuals after fitting a linear model to the data in order to ensure the normality assumption of the model is satisfied. SAS has offered four statistical tests that provide an easy way to test the normality. Howeve...

Many parametric statistical inferential procedures in finite samples depend crucially on the underlying normal distribution assumption. Dozens of normality tests are available in the literature to test the hypothesis of normality. Availability of such a large number of normality tests has generated a large number of simulation studies to find a best test but no one arrived at a definite answer ...

We consider estimation of the covariance matrix of a multivariate random vector under the constraint that certain covariances are zero. We first present an algorithm, which we call Iterative Conditional Fitting, for computing the maximum likelihood estimator of the constrained covariance matrix, under the assumption of multivariate normality. In contrast to previous approaches, this algorithm h...

Mapping quantitative trait loci (QTL) using ascertained sibships is discussed. It is shown that under the standard normality assumption of variance components analysis the efficient scores are unchanged by ascertainment, and two different schemes of ascertainment correction suggested in the literature are asymptotically equivalent. The use of conditional maximum likelihood estimators derived un...

Analysis of covariance (ANCOVA) is a powerful statistical tool for adjusting an analysis to acoount for the effects of concomitant variables. The technique may be applied to completely randomized designs (CRO) as well as repeated measures designs. In addition to normality assumptions, ANCOVA depends on assumptions about variances and slopes. Although not usually provided directly, most statisti...

Normality of random effects is a routine assumption for the linear mixed model, but it may be unrealistic, obscuring important features of among-individual variation. We relax this assumption by approximating the random effects density by the seminonparameteric (SNP) representation of Gallant and Nychka (1987, Econometrics 55, 363-390), which includes normality as a special case and provides fl...

The variance-components model is the method of choice for mapping quantitative trait loci in general human pedigrees. This model assumes normally distributed trait values and includes a major gene effect, random polygenic and environmental effects, and covariate effects. Violation of the normality assumption has detrimental effects on the type I error and power. One possible way of achieving no...

This article considers quasi-maximum likelihood estimations (QMLE) for two spatial panel data regression models: mixed effects model with spatial errors and transformed mixed effects model (where response and covariates are transformed) with spatial errors. One aim of transformation is to normalize the data, thus the transformed models are more robust with respect to the normality assumption co...

The setting of the control limits to utilize on a control chart supposes the assumption of the normality. However, in many situations, this condition does not hold. There are numerous studies on the control charts when the underlying distribution is non-normal. This paper examines the effects of non-normality as measured by skewness and provides an alternative method of designing individuals co...