Preserving consensus hierarchies

In numerical taxonomy we often have the task of finding a consensus hierarchy for a given set of hierarchies. This consensus hierarchy should reflect the substructures which are common to all hierarchies of the set. Because there are several kinds of substructures in a hierarchy, the general axiom to preserve common substructures leads to different axioms for each kind of substructure. In this paper we consider the three substructurescluster, separation, andnesting, and we give several characterizations of hierarchies preserving these substructures. These characterizations facilitate interpretation of axioms for preserving substructures and the examination of properties of consensus methods. Finally some extensions concerning the preserving of qualified substructures are discussed.The author is grateful to the editor and the referees for their helpful suggestions and to H. J. Bandelt for his comments on an earlier version of this paper.     

N-trees as nestings: Complexity,similarity, and consensus

Interpreting a taxonomic tree as a set of objects leads to natural measures of complexity and similarity, and sets natural lower bounds on a consensus tree Interpretations differing as to the kind of objects constituting a tree lead to different measures and consensus Subset nesting is preferred over the clusters (strict consensus) and even the triads interpretations because of its superior expression of shared structure Algorithms for computing the complexity and similarity of trees, as well as a consensus index onto [0,1], are presented for this interpretation The full consensus is defined as the only tree which includes all the nestings shared in a profile of rival trees and whose clusters reflect only nestings shared in the profile The full consensus is proved to exist uniquely for each profile, and to equal the Adams consensusThe author is grateful for the many helpful comments on presentation from Frances McA Adams, William H E Day, and Christopher A Meacham     

Comparison of classifications using measures intermediate between metric dissimilarity and consensus similarity

Two fundamental approaches to the comparison of classifications (e g, partitions on the same finite set of objects) can be distinguished One approach is based upon measures of metric dissimilarity while the other is based upon measures of similarity, or consensus These approaches are not necessarily simple complements of each other Instead, each captures different, limited views of comparison of two classifications The properties of these measures are clarified by their relationships to Day's complexity models and to association measures of numerical taxonomy The two approaches to comparison are equated with the use of separation and minimum value sensitive measures, suggesting the potential application of an intermediate sensitive measure to the problem of comparison of classifications Such a measure is a linear combination of separation sensitive and minimum value sensitive components The application of these intermediate measures is contrasted with the two extremes The intermediate measure for the comparison of classifications is applied to a problem of character weighting arising in the analysis of Australian stream basinsWe thank Bill Day, Mike Austin, Peter Minchin and two anonymous referees for many helpful comments We also thank P Arabie for useful discussion of consensus methods and character weighting     

One-Mode Classification of a Three-Way Data Matrix

X is the automatic hierarchical classification of one mode (units or variables or occasions) of X on the basis of the other two. In this paper the case of OMC of units according to variables and occasions is discussed. OMC is the synthesis of a set of hierarchical classifications Delta obtained from X; e.g., the OMC of units is the consensus (synthesis) among the set of dendograms individually defined by clustering units on the basis of variables, separately for each given occasion of X. However, because Delta is often formed by a large number of classifications, it may be unrealistic that a single synthesis is representative of the entire set. In this case, subsets of similar (homegeneous) dendograms may be found in Delta so that a consensus representative of each subset may be identified. This paper proposes, PARtition and Least Squares Consensus cLassifications Analysis (PARLSCLA) of a set of r hierarchical classifications Delta. PARLSCLA identifies the best least-squares partition of Delta into m (1 <= m <= r) subsets of homogeneous dendograms and simultaneously detects the closest consensus classification (a median classification called Least Squares Consensus Dendogram (LSCD) for each subset. PARLSCLA is a generalization of the problem to find a least-squares consensus dendogram for Delta. PARLSCLA is formalized as a mixed-integer programming problem and solved with an iterative, two-step algorithm. The method proposed is applied to an empirical data set.     

MCS: A Method for Finding the Number of Clusters

This paper proposes a maximum clustering similarity (MCS) method for determining the number of clusters in a data set by studying the behavior of similarity indices comparing two (of several) clustering methods. The similarity between the two clusterings is calculated at the same number of clusters, using the indices of Rand (R), Fowlkes and Mallows (FM), and Kulczynski (K) each corrected for chance agreement. The number of clusters at which the index attains its maximum is a candidate for the optimal number of clusters. The proposed method is applied to simulated bivariate normal data, and further extended for use in circular data. Its performance is compared to the criteria discussed in Tibshirani, Walther, and Hastie (2001). The proposed method is not based on any distributional or data assumption which makes it widely applicable to any type of data that can be clustered using at least two clustering algorithms.     

On the use of ordered sets in problems of comparison and consensus of classifications

Ordered set theory provides efficient tools for the problems of comparison and consensus of classifications Here, an overview of results obtained by the ordinal approach is presented Latticial or semilatticial structures of the main sets of classification models are described Many results on partitions are adaptable to dendrograms; many results on n-trees hold in any median semilattice and thus have counterparts on ordered trees and Buneman (phylogenetic) trees For the comparison of classifications, the semimodularity of the ordinal structures involved yields computable least-move metrics based on weighted or unweighted elementary transformations In the unweighted case, these metrics have simple characteristic properties For the consensus of classifications, the constructive, axiomatic, and optimization approaches are considered Natural consensus rules (majoritary, oligarchic, ) have adequate ordinal formalizations A unified presentation of Arrow-like characterization results is given In the cases of n-trees, ordered trees and Buneman trees, the majority rule is a significant example where the three approaches convergeThe authors would like to thank the anonymous referees for helpful suggestions on the first draft of this paper, and W H E Day for his comments and his significant improvements of style     

Structural Classification Analysis of Three-Way Dissimilarity Data

The paper presents a methodology for classifying three-way dissimilarity data, which are reconstructed by a small number of consensus classifications of the objects each defined by a sum of two order constrained distance matrices, so as to identify both a partition and an indexed hierarchy. Specifically, the dissimilarity matrices are partitioned in homogeneous classes and, within each class, a partition and an indexed hierarchy are simultaneously fitted. The model proposed is mathematically formalized as a constrained mixed-integer quadratic problem to be fitted in the least-squares sense and an alternating least-squares algorithm is proposed which is computationally efficient. Two applications of the methodology are also described together with an extensive simulation to investigate the performance of the algorithm.     

Character and OTU stability in five taxonomic groups

The character and OTU stability of classifications based on UPGMA clustering and maximum parsimony (MP) trees were compared for 5 datasets (families of angiosperms, families of orthopteroid insects, species of the fish genusIctalurus, genera of the salamander family Salamandridae, and genera of the frog family Myobatrachidae). Stability was investigated by taking different sized random subsamples of OTUs or characters, computing UPGMA clusters and an MP tree, and then comparing the resulting trees with those based on the entire dataset. Agreement was measured by two consensus indices, that of Colless, computed from strict consensus trees, and Stinebrickner's 0.5-consensus index. Tests of character stability generally showed a monotone decrease in agreement with the standard as smaller sets of characters are considered. The relative success of the two methods depended upon the dataset. Tests of OTU stability showed a monotone decrease in agreement for UPGMA as smaller sets of OTUs are considered. But for MP, agreement decreased and then increased again on the same scale. The apparent superiority of UPGMA relative to MP with respect to OTU stability depended upon the dataset. Considerations other than stability, such as computer efficiency or accuracy, will also determine the method of choice for classifications.     

TreeOfTrees Method to Evaluate the Congruence Between Gene Trees

A new method, TreeOfTrees, is proposed to compare X-tree structures obtained from several sets of aligned gene sequences of the same taxa. Its aim is to detect genes or sets of genes having different evolutionary histories. The comparison between sets of trees is based on several tree metrics, leading to a unique tree labelled by the gene trees. The robustness values of its edges are estimated by bootstrapping and consensus procedures that allow detecting subsets of genes having differently evolved. Simulations are performed under various evolutionary conditions to test the efficiency of the method and an application on real data is described. Tests of arboricity and various consensus algorithms are also discussed. A corresponding software package is available.     

物理学基本定律的独立性之争及其反思

理论公理化的一个重要问题是公理的独立性问题.考察公理化最为发达的物理学中关于独立性问题的争论,可以看出,自然科学的公理独立性问题不同于逻辑学和数学,有自身独特的方法论价值.     

Comparing the Long-Term Evolution of ``Cognitive Invariances' in Physics with a Dynamics in States of Consciousness

It is shown that the evolution of physics canin several regards be described by elements of``regression', i.e., that within a certaintradition of ideas one begins with theconstruction of most ``plausible' statements(axioms) at hand, and then ``works onselfbackwards' with respect to developmental terms.As a consequence of this strategy, the furtherwork proceeds along such a ``regressive' path,the more one arrives at concepts andrelationships which are unexpected or evencounter-intuitive in terms of our everydayexperiences. However, a comparable phenomenology is wellknown from studies on states of consciousness.In particular, the evolutionary logic of theconstructions of major ``cognitive invariances'in physics, which is in part due to everincreasing rates of data processing, ismirrored in a logic of states of consciousnesswhich deviate from a ``normal' state of dailyroutine along increasing levels of centralnervous arousal. Examples are given from the evolution ofphysics, and future perspectives are brieflyoutlined on the basis thereof.     

Obtaining common pruned trees

Given two or more dendrograms (rooted tree diagrams) based on the same set of objects, ways are presented of defining and obtaining common pruned trees. Bounds on the size of a largest common pruned tree are introduced, as is a categorization of objects according to whether they belong to all, some, or no largest common pruned trees. Also described is a procedure for regrafting pruned branches, yielding trees for which one can assess the reliability of the depicted relationships. The tree obtained by regrafting branches on to a largest common pruned tree is shown to contain all the classes present in the strict consensus tree. The theory is illustrated by application to two classifications of a set of forty-nine stratigraphical pollen spectra.This work was supported by the Science and Engineering Research Council. The authors are grateful to the referees for constructive criticisms of an earlier version of the paper, and to Dr. J.T. Henderson for advice on PASCAL.     

The Generalised Liar Paradox: A Quantum Model and Interpretation

The formalism of abstracted quantum mechanics is applied in a model of the generalized Liar Paradox. Here, the Liar Paradox, a consistently testable configuration of logical truth properties, is considered a dynamic conceptual entity in the cognitive sphere (Aerts, Broekaert, &; Smets, [Foundations of Science 1999, 4, 115–132; International Journal of Theoretical Physics, 2000, 38, 3231–3239]; Aerts and colleagues[Dialogue in Psychology, 1999, 10; Proceedings of Fundamental Approachs to Consciousness, Tokyo ’99; Mind in Interaction]. Basically, the intrinsic contextuality of the truth-value of the Liar Paradox is appropriately covered by the abstracted quantum mechanical approach. The formal details of the model are explicited here for the generalized case. We prove the possibility of constructing a quantum model of the m-sentence generalizations of the Liar Paradox. This includes (i) the truth–falsehood state of the m-Liar Paradox can be represented by an embedded 2m-dimensional quantum vector in a (2m) ^m -dimensional complex Hilbert space, with cognitive interactions corresponding to projections, (ii) the construction of a continuous ‘time’ dynamics is possible: typical truth and falsehood value oscillations are described by Schrödinger evolution, (iii) Kirchoff and von Neumann axioms are satisfied by introduction of ‘truth-value by inference’ projectors, (iv) time invariance of unmeasured state.     

Rational Beliefs as Produced by Computational Processes

Intelligent problem-solving depends on consciously applied methods of thinking as well as inborn or trained skills. The latter are like resident programs which control processes of the kind called (in Unix) daemons. Such a computational process is a fitting reaction to situations (defined in the program in question) which is executed without any command of a computer user (or without any intention of the conscious subject). The study of intelligence should involve methods of recognizing those beliefs whose existence is due to daemons. Once having been aware of so produced belief, one can assess it critically and, if possible and necessary, make it more rational. Eg, beliefs concerning properties of time are produced by a daemon-like intuition, likewise the Euclidean properties of space. The merit of getting aware of such daemon's activities, and so transforming implicit beliefs into explicit ones, lies mainly in the axiomatic characterization of the properties involved. That makes possible to improve a daemon-like conceptual equipment (producing beliefs) by suitable modifications of the axioms, or postulates. Such postulate sets can also define artificial daemons to either emulate or improve natural intelligence.     

Comparing partitions

The problem of comparing two different partitions of a finite set of objects reappears continually in the clustering literature. We begin by reviewing a well-known measure of partition correspondence often attributed to Rand (1971), discuss the issue of correcting this index for chance, and note that a recent normalization strategy developed by Morey and Agresti (1984) and adopted by others (e.g., Miligan and Cooper 1985) is based on an incorrect assumption. Then, the general problem of comparing partitions is approached indirectly by assessing the congruence of two proximity matrices using a simple cross-product measure. They are generated from corresponding partitions using various scoring rules. Special cases derivable include traditionally familiar statistics and/or ones tailored to weight certain object pairs differentially. Finally, we propose a measure based on the comparison of object triples having the advantage of a probabilistic interpretation in addition to being corrected for chance (i.e., assuming a constant value under a reasonable null hypothesis) and bounded between ±1.William H.E. Day was Acting Editor for the reviewing of this paper. We are grateful to him, Ove Frank, Charles Lewis, Glenn W. Milligan, Ivo Molenaar, Stanley S. Wasserman, and anonymous referees for helpful suggestions. Lynn Bilger and Tom Sharpe provided competent technical assistance. Partial support of Phipps Arabie's participation in this research was provided by NSF Grant SES 8310866 and ONR Contract N00014-83-K-0733.     

OCLUS: An Analytic Method for Generating Clusters with Known Overlap

The primary method for validating cluster analysis techniques is throughMonte Carlo simulations that rely on generating data with known cluster structure (e.g., Milligan 1996). This paper defines two kinds of data generation mechanisms with cluster overlap, marginal and joint; current cluster generation methods are framed within these definitions. An algorithm generating overlapping clusters based on shared densities from several different multivariate distributions is proposed and shown to lead to an easily understandable notion of cluster overlap. Besides outlining the advantages of generating clusters within this framework, a discussion is given of how the proposed data generation technique can be used to augment research into current classification techniques such as finite mixture modeling, classification algorithm robustness, and latent profile analysis.     

On the Properties of <Emphasis Type="Italic">α</Emphasis>-Unchaining Single Linkage Hierarchical Clustering

In the election of a hierarchical clustering method, theoretic properties may give some insight to determine which method is the most suitable to treat a clustering problem. Herein, we study some basic properties of two hierarchical clustering methods: α-unchaining single linkage or SL(α) and a modified version of this one, SL?(α). We compare the results with the properties satisfied by the classical linkage-based hierarchical clustering methods.     

兰伯特的几何学思想探析

德国数学家兰伯特在《平行线理论》中通过类比球面提出锐角假设在虚半径球面上成立,这一思想成为后来数学家建立和发展非欧几何的关键.兰伯特在对公理和定义的讨论中体现的几何哲学,使得他证明平行公设时回避了困扰前人的几何直观.他在同时期的数学工作中将圆函数和双曲函数类比,反映出其虚半径球面类比思想的来源和应用.     

Consensus supertrees: The synthesis of rooted trees containing overlapping sets of labeled leaves

Given two dendrograms (rooted tree diagrams) which have some but not all of their base points in common, a supertree is a dendrogram from which each of the original trees can be regarded as samples The distinction is made between inconsistent and consistent sample trees, defined by whether or not the samples provide contradictory information about the supertree An algorithm for obtaining the strict consensus supertree of two consistent sample trees is presented, as are procedures for merging two inconsistent sample trees Some suggestions for future work are made