I am just starting to experiment with the party package and I am getting
strange results. In the examples, the "statistic" and
"criterion" seem
related, i.e. criterion is a 1-p.value and statistic is the test
statistic. Higher statistics are associated with higher criteria
values. When I run these models on my own dataset, the highest
statistic ends up getting a 0.00 criterion value and I get a "no valid
split" message. Here are the results for my test run.
$statistic
consbanner ShopSpecifically4Toys ShopAlone
0.695049632 3.994070949 0.323828003
PlannedVisit HolidayGift ShoppingForInfants
5.959390531 1.215781494 0.008348165
ShoppingForToddlers Shopping5To8 Shopping9To12
1.514564166 1.272472976 2.916720663
ShoppingForBoys ShoppingForGirls
1.176195270 2.931369192
$criterion
consbanner ShopSpecifically4Toys ShopAlone
0.234652500 0.999935052 0.253931746
PlannedVisit HolidayGift ShoppingForInfants
0.000000000 0.775931830 0.006660795
ShoppingForToddlers Shopping5To8 Shopping9To12
0.870117187 0.796794880 0.996462676
ShoppingForBoys ShoppingForGirls
0.760483146 0.996625285
$maxcriterion
[1] 0.999935
PlannedVisit has the highest statistic but it's criterion is zeroed out.
If I run this model utilizing only the ShopSpecifically4Toys variable I
get the same statistic but it's criterion value is also zero. Does
anyone know what might be causing this? My dataset has 2250 cases.
I am using R version 2.4.0 (2006-10-03)
Copyright (C) 2006 The R Foundation for Statistical Computing
ISBN 3-900051-07-0
Platform - Windows XP sp2
Michael Conklin
Chief Methodologist - Advanced Analytics
MarketTools, Inc.
6465 Wayzata Blvd. Suite 170
Minneapolis, MN 55426
Tel: 952.417.4719 | Mobile:612.201.8978
Michael.Conklin@markettools.com <mailto:Michael.Conklin@markettools.com>
MarketTools(r) http://www.markettools.com
<http://www.markettools.com/>
This e-mail and any attachments may contain privileged, confidential or
proprietary information. If you are not the intended recipient, be aware
that any review, copying, or distribution of this e-mail or any
attachment is strictly prohibited. If you have received this e-mail in
error, please return it to the sender immediately, and permanently
delete the original and any copies from your system. Thank you for your
cooperation.
[[alternative HTML version deleted]]