APPLICATION OF EXPERIMENTAL-DESIGN TO GENERATE RELEVANT INFORMATION AND REPRESENTATIVE CALIBRATION DATA

The basic requirements for a good calibration is representative data. This paper outlines techniques for selecting samples from an existing population. The concept of factorial designs is explained, and three w ays of applying experimental design to generate representative data ar e described. These are: to vary the experimental conditions; focus on some of the parameters of interest directly (reference values); to var y the underlying conditions which generate consistent variations in th e spectra,Sor example production factors. Finally the paper-gives an e xample of the the use of the concept of experimental design to pick ou t samples from a population.