MPO 581 Class number 15/27  Mar 9, 2011

1. Last words on Line fitting by least squares

(applet from wikipedia page on Least absolute deviations (LAD) )
Correlation and dependence (wikipedia)
Pearson correlation

More than you wanted to know about line fitting (but only 10 pages) -- 

Cantrell 2008 pdf in ACP

Abstract. The representation of data, whether geophysical observations, numerical model output or laboratory results, by a best fit straight line is a routine practice in the geosciences and other fields. While the literature is full of detailed analyses of procedures for fitting straight lines to values with uncertainties, a surprising number of scientists blindly use the standard least-squares method, such as found on calculators and in spreadsheet programs, that assumes no uncertainties in the x values. Here, the available procedures for estimating the best fit straight line to data, including those applicable to situations for uncertainties present in both the x and y variables, are reviewed. Representative methods that are presented in the literature for bivariate weighted fits are compared using several sample data sets, and guidance is presented as to when the somewhat more involved iterative methods are required, or when the standard least-squares pro- cedure would be expected to be satisfactory. A spreadsheet- based template is made available that employs one method for bivariate fitting.

Hsieh Ch. 1-2 -- regression, correlation, principal components

Open questions, assignments, and loose ends for next class:

Testable questions about today's material:s