Editorial Type:
Article
Article Type:
Research Article

Estimating the Probability of a Future Event from Dichotomously Classified Predictors

Iver A. Lund Air Force Cambridge Research Center, Cambridge 39, Mass.

Search for other papers by Iver A. Lund in
Current site
Google Scholar
PubMed Close
Print Publication:
01 Sep 1955
DOI:
https://doi.org/10.1175/1520-0477-36.7.325
Page(s):
325–328
Full access

The familiar multiple-regression equations are adapted to the problem of determining the probability of a future event from dichotomously classified predictors. The probability of an event can be computed rapidly by this method and can be used as a first approximation of what the subsequent weather will be. An example is included to illustrate how the method is used and to show a comparison between the computed probability values and the observed values.

The familiar multiple-regression equations are adapted to the problem of determining the probability of a future event from dichotomously classified predictors. The probability of an event can be computed rapidly by this method and can be used as a first approximation of what the subsequent weather will be. An example is included to illustrate how the method is used and to show a comparison between the computed probability values and the observed values.

Save
Cover Bulletin of the American Meteorological Society
Bulletin of the American Meteorological Society
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 154 31 2
PDF Downloads 60 13 4