Local regression: Difference between revisions

Revision as of 09:31, 14 July 2009

Revision as of 09:31, 14 July 2009

Line 30:

==Disadvantages of LOESS==

LOESS is makes less efficient use of data than other least squares methods. It requires fairly large, densely sampled data sets in order to produce good models. This is not really surprising, however, since LOESS needs good empirical information on the local structure of the process in order to perform the local fitting. In fact, given the results it provides, LOESS could arguably be more efficient overall than other methods like nonlinear least squares. It may simply frontload the costs of an experiment in data collection but then reduce analysis costs.

Another disadvantage of LOESS is the fact that it does not produce a regression function that is easily represented by a mathematical formula. This can make it difficult to transfer the results of an analysis to other people. In order to transfer the regression function to another person, they would need the data set and software for LOESS calculations. In [[nonlinear regression]], on the other hand, it is only necessary to write down a functional form in order to provide estimates of the unknown parameters and the estimated uncertainty. Depending on the application, this could be either a major or a minor drawback to using LOESS.