Discriminant function analysis with nonindependent data: consequences and an alternative

The discriminant function analysis (DFA) is a multivariate method that is frequently used in bioacoustic research to examine, for instance, whether calls from different species, contexts, or social groups can be distinguished by their acoustic properties. Most published studies include more than one call per subject into such an analysis. This, in fact, leads to a two-factorial data set that includes the factor ‘subject’ in addition to the factor of interest (e.g. species, context, or social group). The regular version of the DFA, however, does not allow for the analysis of such data sets without violating the assumption of independence. In this paper, we show that analysing factorial data sets using a conventional DFA is a case of pseudoreplication and tends to produce (sometimes grossly) incorrect results. In such a case the discriminability of species, contexts or groups etc. can be drastically overestimated. Furthermore, we provide a permutation-based procedure that copes with such data sets.

[1]  Philip H. Crowley,et al.  RESAMPLING METHODS FOR COMPUTATION-INTENSIVE DATA ANALYSIS IN ECOLOGY AND EVOLUTION , 1992 .

[2]  J. Godin,et al.  Phenotypic Variability within and between Fish Shoals , 1996 .

[3]  M. Obrist.  Flexible bat echolocation: the influence of individual, habitat and conspecifics on sonar signal design , 1995, Behavioral Ecology and Sociobiology.

[4]  G. Quinn,et al.  Experimental Design and Data Analysis for Biologists , 2002 .

[5]  R. Byrne,et al.  THE 'WHINNY' OF SPIDER MONKEYS: INDIVIDUAL RECOGNITION BEFORE SITUATIONAL MEANING , 1999 .

[6]  S. Hurlbert.  Pseudoreplication and the Design of Ecological Field Experiments , 1984 .

[7]  S. H. Jenkins.  Data pooling and type I errors: a comment on Leger & Didrichsons , 2002, Animal Behaviour.

[8]  Roger Mundry,et al.  Experimental Designs and Data Analysis for Biologists , 2003 .

[9]  R. Tercafs.  Cooperative breeding in birds: Long-Term Studies of Ecology; Behavior: Peter B. Stacey; Walter D. Koenig. Cambridge University Press; UK. 1990. 615 pp. ISBN 0-521-37890-7 , 1991 .

[10]  Donald E. Kroodsma,et al.  Suggested experimental designs for song playbacks , 1989, Animal Behaviour.

[11]  D G Pitt,et al.  Applications of computer-intensive statistical methods to environmental research. , 1998, Ecotoxicology and environmental safety.

[12]  P. Good,et al.  Permutation Tests: A Practical Guide to Resampling Methods for Testing Hypotheses , 1995 .

[13]  Claudia Fichtel,et al.  Coordination of Group Movements in Wild Verreaux's Sifakas (Propithecus Verreauxi) , 2004 .

[14]  D. Adams,et al.  Using randomization techniques to analyse behavioural data , 1996, Animal Behaviour.

[15]  Andy P. Field,et al.  Discovering Statistics Using SPSS , 2000 .

[16]  F. Juanes,et al.  The importance of statistical power analysis: an example from Animal Behaviour , 1996, Animal Behaviour.

[17]  Wulfert P. van den Brink,et al.  A comparison of the power of the t test, Wilcoxon's test, and the approximate permutation test for the two‐sample location problem , 1989 .

[18]  J. Hooton,et al.  Randomization tests: statistics for experimenters. , 1991, Computer methods and programs in biomedicine.

[19]  B. Tabachnick,et al.  Using Multivariate Statistics , 1983 .

[20]  R. Jaeger,et al.  Social monogamy in a territorial salamander , 2000, Animal Behaviour.

[21]  R. Alatalo,et al.  Female–female aggression and female mate choice on black grouse leks , 2000, Animal Behaviour.

[22]  R. Seyfarth,et al.  Acoustic Features of Female Chacma Baboon Barks , 2001 .

[23]  David R. Anderson,et al.  Model Selection and Multimodel Inference , 2003 .

[24]  J. Bortz.  Statistik: Fur Sozialwissenschaftler , 1993 .

[25]  Julie Gros-Louis,et al.  Alarm calls of white-faced capuchin monkeys: an acoustic analysis , 2005, Animal Behaviour.

[26]  C. Parr,et al.  Randomization Analyses: Mimicry, Geographic Variation and Cultural Evolution of Song in Brood‐Parasitic Straw‐Tailed Whydahs, Vidua fischeri , 2000 .

[27]  J. Kålås,et al.  Females of the lekking great snipe do not prefer males with whiter tails , 2000, Animal Behaviour.

[28]  I. Cuthill,et al.  The biological relevance of testing for perfect symmetry , 1997, Animal Behaviour.

[29]  S. Siegel,et al.  Nonparametric Statistics for the Behavioral Sciences , 2022, The SAGE Encyclopedia of Research Design.

[30]  Derek A. Roff,et al.  DISTRIBUTION-FREE AND ROBUST STATISTICAL METHODS: VIABLE ALTERNATIVES TO PARAMETRIC STATISTICS? , 1993 .

[31]  Roger Mundry,et al.  Testing related samples with missing values: a permutation approach , 1999, Animal Behaviour.

[32]  JULIA FISCHER,et al.  Use of statistical programs for nonparametric tests of small samples often leads to incorrectPvalues: examples fromAnimal Behaviour , 1998, Animal Behaviour.

[33]  Julian D. Olden,et al.  Assessing the robustness of randomization tests: examples from behavioural studies , 2001, Animal Behaviour.

[34]  C. Boesch,et al.  Wild Chimpanzees Produce Group‐Specific Calls: a Case for Vocal Learning? , 2004 .

[35]  L. Bejder,et al.  A method for testing association patterns of social animals , 1998, Animal Behaviour.

[36]  Amots Zehavi,et al.  The Handicap Principle: A Missing Piece of Darwin's Puzzle , 1997 .

[37]  A. Hayes.  Permutation test is not distribution-free: Testing H₀: ρ = 0. , 1996 .

[38]  C. N. Slobodchikoff,et al.  Communication of Stimulus Size and Shape in Alarm Calls of Gunnison’s Prairie Dogs, Cynomys gunnisoni , 1999 .