How to get wrong results from good experimental data: a survey of incorrect applications of regression

Examples are given from older and more recent literature (kinetics, ionization equilibria, complex formation in solution, dipole moment determination, thermochemistry, resonance energies, NMR shifts, photoelectron spectroscopy) where experimental data were processed in an incorrect way from the point of view of statistics. The results were more or less biased, sometimes completely wrong. Corrected procedures, based entirely on the least-squares method, are reported; in several cases methods are proposed. Some hints are given as to how these mistakes can be avoided, how they can be revealed in the literature and how the literature data can be recalculated: the last task is the most difficult.