Loading ...
Sorry, an error occurred while loading the content.

[ai-geostats] logistic regression in polychotomous case

Expand Messages
  • MARTINEZ VARGAS Adrian
    estimate mail list I have a data with multiple categories variable and I m interesting in classification and relation description with continuous variables,
    Message 1 of 1 , Apr 7, 2005
    • 0 Attachment
      estimate mail list

      I have a data with multiple categories variable and I'm interesting in
      classification and relation description with continuous variables, for
      problem of normality and heterosedasticity I have use logistic
      regression, but my software do not work with multiples categories
      (polychotomous case). to solve this problem i have work with marginal
      categories (logistic regression for each category by separate), to
      classify was assigned the category with largest probability, but for
      some categories where the number of 1 is low (each category {0,1}) the
      error in classification is to low, and for those case specific
      discriminat analysis give best results. In general, the result with
      logistic regression has give a little bit better results.

      how to perform logit regression in polychotomous case using a software
      that work only with one binary variable (dichotomy case) ?????

      regards

      Adrian Martinez Vargas
      CFSG student
      *Centre de Geostatistique* de l'Ecole des Mines de Paris
      35 Rue St Honore, 77300 Fontainebleau, FRANCE
    Your message has been successfully submitted and would be delivered to recipients shortly.