A program for the weighted linear least-squares regression of unbalanced response arrays

A program is described to establish calibration diagrams by weighted, linea r, least-squares regression of unbalanced response arrays. Whatever the con fidence level, the number of analysed standard solutions and of their avail able replicates, the program allows (i) testing for scedasticity, linearity , outliers and normality, (ii) evaluation of slope and intercept of the cal ibration function and their confidence interval and (iii) evaluation of an unknown concentration and its confidence interval by interpolation/extrapol ation. For negative results of the linearity test, the program structure al lows a rapid evaluation of data to be discarded to attempt entering the lin ear range. The program was validated by analysing response arrays obtained by adding a Gaussian noise to known response/concentration functional relat ionships. The results of validation tests led to the implementation of an e mpirical but efficient way to correct regression results when certain exper imental situations lead to unjustified over-weighting of some responses. Th e analysis of some real calibration data sets allows the versatility of the software to be evaluated.