Improvements to resampling measures of group support

被引:769
作者
Goloboff, PA
Farris, JS
Källersjö, M
Oxelman, B
Ramírez, MJ
Szumik, CA
机构
[1] Inst Super Entomol Dr Abraham Willink, Fac Ciencias Nat, RA-4000 San Miguel De Tucuman, Argentina
[2] Naturhistoriska Riksmuseet, Molekylarsyst Lab, S-10405 Stockholm, Sweden
[3] Uppsala Univ, Evolutionary Biol Ctr, Dept Systemat Bot, SE-75236 Uppsala, Sweden
[4] Amer Museum Nat Hist, New York, NY 10024 USA
来源
CLADISTICS-THE INTERNATIONAL JOURNAL OF THE WILLI HENNIG SOCIETY | 2003年 / 19卷 / 04期
关键词
BOOTSTRAP; LIMITS;
D O I
10.1016/S0748-3007(03)00060-4
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Several aspects of current resampling methods to assess group support are reviewed. When the characters have different prior weights or some state transformation costs are different, the frequencies under either bootstrapping or jackknifing can be distorted, producing either under- or overestimations of the actual group support. This is avoided by symmetric resampling, where the probability p of increasing the weight of a character equals the probability of decreasing it. Problems with interpreting absolute group frequencies as a measure of the support are discussed; group support does not necessarily vary with the frequency itself, since in some cases groups with positive support may have much lower frequencies than groups with no support at all. Three possible solutions for this problem are suggested. The first is measuring the support as the difference in frequency between the group and its most frequent contradictory group. The second is calculating frequencies for values of p below the threshold under which the frequency ranks the groups in the right order of support (this threshold may vary from data set to data set). The third is estimating the support by using the slope of the frequency as a function of different (low) values of p; when p is low, groups with actual support have negative slopes (closer to 0 when the support is higher), and groups with no support have positive slopes (larger when evidence for and against the group is more abundant). (C) 2003 The Willi Hennig Society. Published by Elsevier Science (USA). All rights reserved.
引用
收藏
页码:324 / 332
页数:9
相关论文
共 19 条
[1]   On the interpretation of bootstrap trees: Appropriate threshold of clade selection and induced gain [J].
Berry, V ;
Gascuel, O .
MOLECULAR BIOLOGY AND EVOLUTION, 1996, 13 (07) :999-1011
[2]  
BREMER K, 1988, EVOLUTION, V42, P795, DOI [10.2307/2408870, 10.1111/j.1558-5646.1988.tb02497.x]
[3]  
BREMER K, 1994, CLADISTICS, V10, P295, DOI 10.1006/clad.1994.1019
[4]  
CARPENTER JM, 1996, CLADISTICS, V12, P215
[5]  
DELAET J, 2002, PAUP PHYLIP CAN ATTR
[6]   1977 RIETZ LECTURE - BOOTSTRAP METHODS - ANOTHER LOOK AT THE JACKKNIFE [J].
EFRON, B .
ANNALS OF STATISTICS, 1979, 7 (01) :1-26
[7]   Conjectures and refutations [J].
Farris, JS .
CLADISTICS-THE INTERNATIONAL JOURNAL OF THE WILLI HENNIG SOCIETY, 1995, 11 (01) :105-118
[8]   Parsimony jackknifing outperforms neighbor-joining [J].
Farris, JS ;
Albert, VA ;
Kallersjo, M ;
Lipscomb, D ;
Kluge, AG .
CLADISTICS, 1996, 12 (02) :99-124
[9]   A SUCCESSIVE APPROXIMATIONS APPROACH TO CHARACTER WEIGHTING [J].
FARRIS, JS .
SYSTEMATIC ZOOLOGY, 1969, 18 (04) :374-&
[10]  
Farris JS, 2002, CLADISTICS, V18, P334, DOI 10.1111/j.1096-0031.2002.tb00155.x