Re: Selection of explanatory variables in a model

Cat wrote:
Dear colisters,

I have to build a logistic regression model and I've got a couple of
questions:


- I heard / read (on the Internet) that the number of variables to put
as explanatory characters must not be greater than n/10 or n/ 20 (n is
the sample size). Does someone can provide me with a serious
bibliographic reference about this ?

I think it is better to choose a subset using an information criterion
such as AIC than to rely on such a rule of thumb. Two books on variable
selection are

Subset Selection in Regression
Alan J. Miller

Regression and Time Series Model Selection
by Allan D. R. McQuarrie, Chih-Ling Tsai

.

Relevant Pages

  • Re: Underestimating r
    ... > the population, due to natural selection". ... > own relative fitness, holding fixed the actions of her social partners. ... > fundamentally a regression measure. ... random variables will be something similar. ...
    (sci.bio.evolution)
  • Re: Underestimating r
    ... >> natural selection, is the product of the selection differential ... >> fundamentally a regression measure. ... >> IBD actor-actor. ... I suppose dzbar is the average amount ...
    (sci.bio.evolution)
  • Re: Cumulative Security Update for Outlook Express 6 Service Pack 1 (KB837009)
    ... Robert: ... talking about as to finding the regression or expanding what ever. ... > one is selected and then copy the combined selection. ...
    (microsoft.public.windowsupdate)
  • Different R^2 values with same variables
    ... If I run linear regression with R^2 selection (in SAS) and get some ...
    (sci.stat.math)
  • Re: A StepWise Regression Subroutine
    ... I already have one version of that subroutine, ... I recommend looking at the Fortran codes of statistician Alan Miller in ... the "Subset Selection in Regression" section of the site ... Miller wrote the book "Subset Selection in Regression", 2nd edition, ...
    (comp.lang.fortran)