 |
| Titel |
Technical Note: Review of methods for linear least-squares fitting of data and application to atmospheric chemistry problems |
| VerfasserIn |
C. A. Cantrell |
| Medientyp |
Artikel
|
| Sprache |
Englisch
|
| ISSN |
1680-7316
|
| Digitales Dokument |
URL |
| Erschienen |
In: Atmospheric Chemistry and Physics ; 8, no. 17 ; Nr. 8, no. 17 (2008-09-12), S.5477-5487 |
| Datensatznummer |
250006377
|
| Publikation (Nr.) |
 copernicus.org/acp-8-5477-2008.pdf |
|
|
|
|
|
| Zusammenfassung |
| 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 procedure
would be expected to be satisfactory. A spreadsheet-based template is made
available that employs one method for bivariate fitting. |
| |
|
| Teil von |
|
|
|
|
|
|
|
|