You are working with the text-only light edition of "H.Lohninger: Teach/Me Data Analysis, Springer-Verlag, Berlin-New York-Tokyo, 1999. ISBN 3-540-14743-8". Click here for further information.

Index
See also: variable selection 

Mallows Cp Statistic

C.L. Mallows [1] developed a method to find adequate models by plotting a special statistic against the number of variables+1.

Cp = SSres/MSres - N + 2p,

where
  SSres is the residual sum of squares for the model with p-1 variables,
  MSres is the residual mean square when using all available variables,
  N is the number of observations, and
  p is the number of variables used for the model plus one.

The general procedure to find an adequate model by means of the Cp statistic is to calculate Cp for all possible combinations of variables and the Cp values against p. The model with the lowest Cp value approximately equal to p is the most "adequate" model.

[1] C.L. Mallows
Some comments on Cp
Technometrics 15 (1973) 661

 

Last Update: 2004-Jul-03