A Very Quick Estimation of Random Variability of Data by a Portable Method

Hubert Žáček

Department of Pharmaceutical Technology, Charles University in Prague, Faculty of Pharmacy in Hradec Králové, Czech Republic

Summary

A very quick and simple method for assessing random variability of data on the basis of their standard deviation is described. The simplification consists in approximation of the standard deviation by the quotient of range and the square root of the number n of observations. The method can be successfully applied in treating samples of n = 3 to n = 12. The relative error in comparison with the standard deviation calculated traditionally is in general > 5 %. A pharmaceutical practical example of application of the suggested new method is described on the basis of quality control of volumes of filling injection ampoules. Of course, the new method has also other possibilities of use (e.g., it can also serve as bridge between statistics and cybernetics).