ABSTRACT
Per ICH guidelines, the robustness of an analytical method (assay) is defined as a measure of its capacity to remain unaffected by small but deliberate variations in procedural parameters and provide an indication of its reliability during normal usage. Various statistical methods and measures have been developed to evaluate the robustness of analytical methods. Statistical significance of an assay method indicates that the mean differences of the assay responses by varying a procedural parameter is not likely due to sampling error. The statistical significance may be simply caused by a large sample size or by a consistent yet negligible effect of a factor although the effect size is not practically meaningful. The chapter reviews several common methods for assessing robustness of analytical methods and illustrates the subtle difference of statistical and practical significance with a case study of A280 method for protein concentration.
