Book Chapter10.1007/978-3-662-26811-7_26
A Two-Stage Predictive Splitting Algorithm in Binary Segmentation
Francesco Mola,Roberta Siciliano +1 more
- 01 Jan 1992
- pp 179-184
31
TL;DR: In the framework of binary segmentation, a two-stage splitting algorithm which optimizes a defined predictability function to find a binary tree whose nodes are internally most homogeneous and externally most heterogeneous with respect to the predictability of their cases is proposed.
read more
Abstract: In the framework of binary segmentation, we propose a two-stage splitting algorithm which optimizes a defined predictability function. The idea is to find a binary tree whose nodes are internally most homogeneous and externally most heterogeneous with respect to the predictability of their cases. The main steps of the algorithm will be described. Some relations with the CART splitting procedure will be discussed and an example will be shown.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Multivariate data analysis and modeling through classification and regression trees
Roberta Siciliano,Francesco Mola +1 more
TL;DR: A multivariate approach to binary segmentation in order to deal with more response variables and to explore dependency in multivariate data is provided.
76
A fast splitting procedure for classification trees
Francesco Mola,Roberta Siciliano +1 more
TL;DR: The predictability index τ is proposed as a splitting rule for growing the same classification tree as CART does when using the Gini index of heterogeneity as an impurity measure to make a substantial saving in the time required to generate a classification tree.
63
A statistical approach to growing a reliable honest tree
TL;DR: Testing procedures for both classification and regression trees are introduced and these procedures guide the search for those parts in tree structures which are statistically significant.
41
Stability and scalability in decision trees
Tomàs Aluja-Banet,Eduard Nafria +1 more
TL;DR: This work proposes a series of data diagnostics to prevent internal instability in the tree-growing process before a particular split is made, and presents an algorithm that can cope with such problems, with linear cost upon the individuals, which can use a robust impurity measure as a splitting criterion.
22
Regression trees for multivalued numerical response variables
TL;DR: A definition of the impurity measure and of the splitting criterion allowing for building the regression tree for multivalued numerical response variable and the performance of this proposal is evaluated.
18
References
A new look at the statistical model identification
TL;DR: In this article, a new estimate minimum information theoretical criterion estimate (MAICE) is introduced for the purpose of statistical identification, which is free from the ambiguities inherent in the application of conventional hypothesis testing procedure.
•Book
Measures of association for cross classifications
Leo A. Goodman,William Kruskal +1 more
- 01 Jan 1979
TL;DR: In this article, a number of alternative measures are considered, almost all based upon a probabilistic model for activity to which the cross-classification may typically lead, and only the case in which the population is completely known is considered, so no question of sampling or measurement error appears.
2.8K
Problems in the Analysis of Survey Data, and a Proposal
James N. Morgan,John A. Sonquist +1 more
TL;DR: In this article, an approach to survey data is proposed which imposes no restrictions on interaction effects, focuses on Importance in reducing predictive error, operates sequentially, and is independent of the extent of linearity in the classifications or the order in which the explanatory factors are introduced.
1.3K
On Grouping for Maximum Homogeneity
TL;DR: In this article, the authors present a practical procedure for grouping arbitrary numbers so that the variance within groups is minimized, including a description of an automatic computer program, given for problems up to the size where 200 numbers are to be placed in 10 groups.
860
Related Papers (5)
[...]
Leo Breiman
- 01 Aug 1996
Trevor Hastie,Robert Tibshirani,Jerome H. Friedman +2 more
- 01 Jan 2001