<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content="text/html; charset=koi8-r" http-equiv=Content-Type>
<META content="MSHTML 5.00.3103.1000" name=GENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=#ffffff>
<DIV><FONT color=#0000ff face=Arial size=2>
<DIV><FONT color=#0000ff face=Arial size=2>
<DIV><FONT color=#0000ff face=Arial size=2>I apologize if you receive multiple
copies of this letter.</FONT><FONT color=#0000ff face="Arial CYR" size=2><FONT
color=#0000ff face="Arial CYR" size=2> This is the first time I've written to
this mailing list, so please be kind:-)</FONT></FONT></DIV>
<DIV><FONT color=#0000ff face="Arial CYR" size=2> </DIV>
<DIV>
<DIV><FONT face=Arial><FONT color=#0000ff face=Arial size=2>Hello
everyone!</FONT></FONT></DIV>
<DIV>I'm trying to make a programme which grows a classification tree. I use APL
programming language and I use R to compare and test results.</DIV>
<DIV><FONT color=#0000ff face="Arial CYR" size=2>I have a classification tree
and I have a sequence of cost-comlexity parameters(alphas): 0,A1,A2...An. Now I
want to choose a right-sized tree or, in other words, the optimal complexity
parameter Ak. I understand that I should use a V-fold cross validation. The
problem is that I don't quite understand how to prune trees in
CV:</FONT></DIV>
<DIV><FONT color=#0000ff face=Arial size=2>1. If I use the initial sequence of
alphas: </FONT><FONT color=#0000ff face=Arial size=2></FONT></DIV>
<DIV><FONT color=#0000ff face=Arial size=2>To test A1 I snip off all rooted
nodes with cost-complexity parameters in a range [0, A1]; to test A2 I prune all
nodes with cost-complexity parameters in a range [A1, A2]; ...etc.
Is this correct?</FONT></DIV>
<DIV> </DIV>
<DIV><FONT color=#0000ff face="Arial CYR" size=2>2. If I use a new sequence of
complexity parameters 0,B1,B2,...,Bm, where Bi is the geometric mean of A[i] and
A[i+1], Bi=SQRT( A[i] * A[i+1] ):</FONT><FONT color=#0000ff face="Arial CYR"
size=2> </FONT></DIV>
<DIV><FONT color=#0000ff face="Arial CYR" size=2>Suppose, I select Bk as an
optimal parameter. Which Ai does this optimal Bk correspond to? </FONT></DIV>
<DIV> </DIV>
<DIV><FONT color=#0000ff face="Arial CYR" size=2>Which of the two ways
should I follow? Are there any other ways of choosing a right-sized tree?
Does anybody have any ideas?</FONT></DIV>
<DIV><FONT color=#0000ff face="Arial CYR" size=2>Thank you</FONT></DIV>
<DIV> </DIV>
<DIV><FONT color=#0000ff face="Arial CYR" size=2>Kutinsky
Vladimir</FONT></DIV></FONT></DIV></FONT></DIV></FONT></DIV></BODY></HTML>