A STATISTICAL VIEW OF SOME CHEMOMETRICS REGRESSION TOOLS

Chemometrics is a field of chemistry that studies the application of s tatistical methods to chemical data analysis. In addition to borrowing many techniques from the statistics and engineering literatures, chem ometrics itself has given rise to several new data-analytical methods. This article examines two methods commonly used in chemometrics for p redictive modeling-partial least squares and principal components regr ession-from a statistical perspective. The goal is to try to understan d their apparent successes and in what situations they can be expected to work well and to compare them with other statistical methods inten ded for those situations. These methods include ordinary least squares , variable subset selection, and ridge regression.