Test of Homogeneity of Scale Parameters Based on Function of Sample Quasi Ranges

A multi-sample test for homogeneity of scale parameters against simple ordered alternative based on function of sample quasi ranges is proposed for censored data, as well as for data contaminated with outliers. These problems find a number of applications in different fields, such as agriculture, competitive markets, engineering and quality control. The critical points have been computed through simulation for the given test in case of standard exponential, standard logistic and standard uniform distributions. Nonetheless, the proposed test also finds applications in distributions such as Laplace, Pareto, Weibull, etc. Herein construction is proposed for simultaneous one-sided confidence intervals (SOCIs) along with an illustration. Besides computing the power of the proposed test, some power comparisons have also been undertaken.