Based on previous papers and a recent book published by the author, we
propose the term ''sampling'' to characterize all steps that relate t
he sample to the process of analysis. The analyst has to understand th
at no analysis is better than the sample itself, and is thus obliged t
o give more importance to the sampling process. The paper discusses th
e correlation ''Method-Sample-Instrument,'' the relationship of the hi
story of the sample to the development of the analytical process, and
the influence of the sampling process on the reliability of the analyt
ical information. We conclude that sampling must include all the separ
ation techniques. The main field of chemical analysis in the future, t
he hyphenated techniques, and the connection between sampling and patt
ern recognition are also discussed. (C) 1996 Academic Press, Inc.