The paper describes a non-parametric approach to the statistical analysis performed on data obtained during investigation on the airfoil blade traces. This approach releases us from limits of many conditions. Typical statistical analysis of data, with factorial (qualitative) control approach, bases on many theoretical assumptions, with the most important and the most influential one: the normality of random noises distributions (usually named ‘errors’). The solution is the bootstrap approach, originally proposed by Efron in 1979, later in 1995 described in details by Shao and Tu. The bootstrap is formally the method based on random resampling with replacement from the source dataset. It allows to identify the whole distribution shape of raw data and related confidence intervals without additional assumptions about particular distribution. The paper presents the practical case: the factorial approach performed for the fixed-effect analysis of the relation between secondary dendrite arm spacing and carbides for the airfoil blade traces. The paper contains notes on encountered difficulties and possible guidelines for similar analysis.Keywords: Uncertainty, non-parametric approach, SDAS, carbide, superalloy
© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.