Understanding Biplots

Gower, J. C.; Gardner-Lubbe, Sugnet; Roux, Niël le

doi:10.1002/9780470973196

Cited by 201 publications

(165 citation statements)

References 0 publications

Supporting

Mentioning

138

Contrasting

Unclassified

Order By: Relevance

“…The quantitative data (n = 7), were subjected to analysis-of-distance (AoD) as described in Gower et al [43] to display the differences between the AF and wool measurements, respectively, of the lambs. The resulting 14 × 14 distance matrix was used as input to a principal coordinate analysis (PCO), and the construction of the associated AoD biplot depicted in Figure 5 graphically illustrates these differences.…”

Section: Comparison Of the Voc Content Of Wool And Af Of Twinsmentioning

confidence: 99%

Characterization of amniotic fluid of Dohne Merino ewes (Ovis aries) and its possible role in neonatal recognition

Viviers

Bekker

Burger

et al. 2015

Zeitschrift Für Naturforschung C

View full text Add to dashboard Cite

Amniotic fluid (AF) was investigated as a possible source of the neonatal recognition cue that plays a crucial role in ewe-lamb bonding in sheep. A total of 70 of the 133 volatile organic compounds (VOCs), previously identified in the cranial wool of neonatal Dohne Merino lambs, was also identified in AF collected individually from neonatal twins. As in the case of the wool of neonatal lambs, the VOC profiles (GC-MS) of the AF of twins were remarkably similar. However, the VOC profiles of the AF differed from that of the wool VOCs of the same lambs. The VOCs that best represent the total variance in the AF and wool of neonatal lambs were not identified as ligands of the AF proteins. These observations suggest that it is unlikely that the neonatal recognition cue of sheep could be a maternal label derived from the AF in which a lamb is born, and that the neonatal recognition cue is probably produced by the lamb. Taking cognizance of the temporal changes that take place in the quantitative composition of the cranial wool VOCs, we hypothesize that components of the neonatal recognition cue are already produced by the lamb well before its birth and that the quantitative composition in which these volatiles are released into the AF does not correspond to the composition of the recognition cue of the lamb at its birth. When grooming the newborn lamb, its mother removes AF containing incorrect chemical information from her lamb's body and this affords her enough time to learn its personal recognition cue.

show abstract

Section: Comparison Of the Voc Content Of Wool And Af Of Twinsmentioning

confidence: 99%

Characterization of amniotic fluid of Dohne Merino ewes (Ovis aries) and its possible role in neonatal recognition

Viviers

Bekker

Burger

et al. 2015

Zeitschrift Für Naturforschung C

View full text Add to dashboard Cite

show abstract

“…Ref. [19]). Another possibility is to present the rows as axes and the columns as points (or vice versa).…”

Section: Visualisation For Biadditive Modelsmentioning

confidence: 99%

“…In addition, the values of αþ β ¼ 1 (as defined in Appendix A) are at choice and λ-scaling is available (see Ref. [19]). In this way, a variety of equivalent representations, which may be regarded as items drawn from a toolbox, is available for presentational purposes.…”

Section: Visualisation For Biadditive Modelsmentioning

confidence: 99%

“…Ref. [19]). Whilst [1] explain the technical construction of these triplots, instruction on how to interpret these triplots, especially in the case of interaction arrays, is lacking.…”

Section: Visualisation For Three-way Datamentioning

confidence: 99%

“…introduced in the context of biplots in Refs. [17] and [19]; and in the context of triplots in Ref. [1].…”

Section: Triadditive Visualisationmentioning

confidence: 99%

See 2 more Smart Citations

Visualising interactions in bi- and triadditive models for three-way tables

Albers

Gower

2017

Chemometrics and Intelligent Laboratory Systems

Self Cite

View full text Add to dashboard Cite

This paper concerns the visualisation of interaction in three-way arrays. It extends some standard ways of visualising biadditive modelling for two-way data to the case of three-way data. Three-way interaction is modelled by the Parafac method as applied to interaction arrays that have main effects and biadditive terms removed. These interactions are visualised in three and two dimensions. We introduce some ideas to reduce visual overload that can occur when the data array has many entries. Details are given on the interpretation of a novel way of representing rank-three interactions accurately in two dimensions. The discussion has implications regarding interpreting the concept of interaction in three-way arrays.

show abstract