Effective dimensionality of environmental indicators: a principal component analysis with bootstrap confidence intervals

Yu, Chang-Ching; Quinn, J.; Dufournaud, Christian M.; Harrington, Joseph J.; Rogers, Peter; Lohani, B. N.

doi:10.1006/jema.1998.0184

Cited by 64 publications

(36 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These linear combinations represent a type of abstract measurements or factors that are better descriptors for the data-set structure than the original measurements. The minimum requirement to provide a stable solution in PCA is that the number of observations must be greater than the number of independent variables (Yu et al, 1998).…”

Section: Introductionmentioning

confidence: 99%

Multivariate statistical analysis of hydrochemical and radiological data of Serbian spa waters

Tanaskovic

Golobočanin

Miljević³

2012

Journal of Geochemical Exploration

103

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Multivariate statistical analysis of hydrochemical and radiological data of Serbian spa waters

Tanaskovic

Golobočanin

Miljević³

2012

Journal of Geochemical Exploration

103

View full text Add to dashboard Cite

“…This study shows that colour was an important attribute in distinguishing among the samples. In this respect, PCA reinforces the more subjective JAR scale measures [36,37,38]. It provides an objective way of aggregating indicators so that the variation in data can be accounted for as concisely as possible.…”

Section: Colourmentioning

confidence: 91%

Descriptive sensory quality of Kenya’s indigenous chicken meat from different ecotype- clusters reared under an intensive system

Oloo¹,

Mahungu²,

Kahi³

2018

AJFAND

View full text Add to dashboard Cite

Indigenous chicken (IC) in Kenya performs a major food security and socio-economic function for most households, especially of the rural poor. The trend has been to move from rearing IC on free-range systems to more intensive and semi intensive systems. This study was conducted by use of Quantitative Descriptive Analysis (QDA) and the Just About Right (JAR) scale scores to quantify the appeal of the IC meat reared under intensive systems. The IC used in the study had been obtained from Taita, Kakamega and Narok ecotype clusters kept under the intensive system at Indigenous Chicken Improvement Programme (INCIP) unit at Egerton University. During the intensive rearing, the chickens were given the same treatment in terms of feed, disease control at all the stages and water was given ad-libitum. The chickens were slaughtered at the same age and only cocks were used as control for sensorial differences accruing due to sex. Five cocks from each ecotype cluster were slaughtered after a feed withdrawal period of 8-10 hours and their meat prepared by boiling for sensory evaluation after ageing on ice for 3-6 hours. A trained panel of tasters (13-15) was used to evaluate the descriptive and JAR sensorial quality of indigenous chickens' meat from the breast and thighs. One commercial broiler (Kenbro) was used as a control. Results showed that there was significant effect at P<0.05 of the ecotype of the IC on its meat aroma, flavour and brown colour intensity. The JAR scale showed that the consumers' scores for the colour, flavour, juiciness, tenderness of indigenous chicken was 'just about right' compared to broiler which was described by colour as too light, flavour too strong, too juicy in terms of expression of juiciness and too tender with regard to texture. The Principal Component Analysis results showed that there were two principal components (colour and texture) that accounted for 55.4 % and 11.6% and 53.9 and 19% for both descriptive scores and JAR scores for IC meat, respectively. This study indicates sensorial differences among the Kenyan Indigenous chicken ecotypes (of different genetic characteristics) under intensive systems and demonstrates significant difference among various attributes from the commercial broiler.

show abstract

“…This allows a clear visual interpretation of significant differences, rather than just investigating the precision of the estimate as demonstrated in previous studies (e.g. Yu et al, 1998). If spheres overlap, significant differences between the assemblages at the study locations are unlikely.…”

Section: Multivariate Techniques Such As Principal Components Analysimentioning

confidence: 95%

“…The technique is analogous to the calculation of sample means and their respective confidence intervals in univariate analysis: if appropriate confidence limits of the different sample means overlap, no significant difference in mean values occurs (Schenker and Gentleman, 2001;Payton et al, 2003). In this case, confidence limits of the first three principal components are calculated by a bootstrapping exercise (similar to Yu et al, 1998). However, in our study, the assemblages at the study locations are plotted in three dimensions using the first three principal components as x, y and z coordinates, but the points are plotted as spheres, the size of the sphere based on the calculation of a confidence radius.…”

Section: Multivariate Techniques Such As Principal Components Analysimentioning

confidence: 99%

Use of confidence radii to visualise significant differences in principal components analysis: Application to mammal assemblages at locations with different disturbance levels

Catlin-Groves

Kirkhope

Goodenough

et al. 2009

Ecological Informatics

View full text Add to dashboard Cite

Effective dimensionality of environmental indicators: a principal component analysis with bootstrap confidence intervals

Cited by 64 publications

References 0 publications

Multivariate statistical analysis of hydrochemical and radiological data of Serbian spa waters

Multivariate statistical analysis of hydrochemical and radiological data of Serbian spa waters

Descriptive sensory quality of Kenya’s indigenous chicken meat from different ecotype- clusters reared under an intensive system

Use of confidence radii to visualise significant differences in principal components analysis: Application to mammal assemblages at locations with different disturbance levels

Contact Info

Product

Resources

About