Model-based nonlinear data fitting is an invaluable instrument in the hand of any scientist, who is interested in the quantitative analysis of measured data. The range of analyses is wide and includes simple straight line fits to the global analysis of series of measurements of complex chemical processes. Data fitting comprises three main aspects. The first and central component of any data analysis is the collection of measured data that wait to be analysed. The second component of data fitting is a model that is used to quantitatively describe the data. The third aspect is the actual fitting routine, which determines the most likely values for the parameters of the model.
Comprehensive Chemometrics: Chemical and Biochemical Data Analysis, Volume 3 p. 413-436