If you need an accessible version of this item please contact JSTOR User Support

A Comparison of Detransformed Logarithmic Regressions and Power Function Regressions

Margareta Jansson
Geografiska Annaler. Series A, Physical Geography
Vol. 67, No. 1/2 (1985), pp. 61-70
Published by: Wiley on behalf of the Swedish Society for Anthropology and Geography
DOI: 10.2307/520466
Stable URL: http://www.jstor.org/stable/520466
Page Count: 10
  • Download PDF
  • Cite this Item

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If you need an accessible version of this item please contact JSTOR User Support
A Comparison of Detransformed Logarithmic Regressions and Power Function Regressions
Preview not available

Abstract

A comparison of detransformed logarithmic regressions and power function regressions is illustrated with regressions of sediment concentration in a Swedish river. Quite different parameters were obtained when power function equations were developed from log-transformed data compared with development from the original data. This is a consequence of different model assumptions. Power function regressions are calculated from an additive model. While detransformed logarithmic regressions represent a multiplicative model. Detransformed logarithmic regression equations are biased with respect to the original data. Some of the bias can be reduced by a correction factor.

Page Thumbnails

  • Thumbnail: Page 
61
    61
  • Thumbnail: Page 
62
    62
  • Thumbnail: Page 
63
    63
  • Thumbnail: Page 
64
    64
  • Thumbnail: Page 
65
    65
  • Thumbnail: Page 
66
    66
  • Thumbnail: Page 
67
    67
  • Thumbnail: Page 
68
    68
  • Thumbnail: Page 
69
    69
  • Thumbnail: Page 
70
    70