Clustering without a metric

Matthews, Geoffrey B.; Hearne, James

doi:10.1109/34.67646

Cited by 38 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NMC was preferred over hierarchical clustering and principal components analysis because of the heteroscedasticity among the variances of the parameters (Matthews and Hearne 1991). To assess the validity of the classifications established by NMC, results from the actual data (nonrandom) were compared with those obtained from three sets of data that were created by randomizing the actual data.…”

Section: Discussionmentioning

confidence: 99%

Barriers to upstream passage by two migratory sculpins, prickly sculpin (Cottus asper) and coastrange sculpin (Cottus aleuticus), in northern Puget Sound lowland streams

Thomas

Richard

2014

Can. J. Fish. Aquat. Sci.

View full text Add to dashboard Cite

We identified and characterized barriers to the upstream distribution by prickly sculpin (Cottus asper) and coastrange sculpin (Cottus aleuticus), based on their longitudinal distribution in 11 streams in the Puget Sound lowlands of Washington State. Eight streams had upstream limits associated with particular instream structures, and these were compared to distinguish features of barriers and non-barriers. In seven streams perch height greater than 15 cm resulted in a complete barrier. In one stream water velocity >4 m·s−1 created a partial barrier. Five of the eight barriers were one- or two-step fish ladders installed to facilitate upstream passage of Pacific salmon and trout. Water quality, physical habitat, and the presence of other fishes were not related to the presence or absence of sculpin species. Fish passage criteria in western North American streams are based on the swimming abilities of Pacific salmon and trout, without consideration for other, less motile native fishes. Structures installed to surmount previously identified impediments to upstream migration continue to inhibit sculpin movement, resulting in loss of upstream habitats for adults, with potential consequences to population size and trophic dynamics.

show abstract

Section: Discussionmentioning

confidence: 99%

Barriers to upstream passage by two migratory sculpins, prickly sculpin (Cottus asper) and coastrange sculpin (Cottus aleuticus), in northern Puget Sound lowland streams

Thomas

Richard

2014

Can. J. Fish. Aquat. Sci.

View full text Add to dashboard Cite

show abstract

“…In this section we attempt to outline the similarities and dissimilarities of multivariate methods used in ecotoxicology, focusing on nonmetric multidimensional scaling (MDS, incorporated in the PRIMER computer program; [15]), nonmetric clustering (NMC, incorporated in the Riffle computer program; [16]), and our own approach of canonical ordination using RDA and PRC (incorporated in the CANOCO computer program; [6,9]). …”

Section: Comparison With Other Techniques Used In Mesocosm Experimentsmentioning

confidence: 99%

Principal Response Curves: Analysis of Time-Dependent Multivariate Responses of Biological Community to Stress

Brink

Braak

1999

Environ Toxicol Chem

136

View full text Add to dashboard Cite

In this paper a novel multivariate method is proposed for the analysis of community response data from designed experiments repeatedly sampled in time. The long‐term effects of the insecticide chlorpyrifos on the invertebrate community and the dissolved oxygen (DO)–pH–alkalinity–conductivity syndrome, in outdoor experimental ditches, are used as example data. The new method, which we have named the principal response curve method (PRC), is based on redundancy analysis (RDA), adjusted for overall changes in community response over time, as observed in control test systems. This allows the method to focus on the time‐dependent treatment effects. The principal component is plotted against time, yielding a principal response curve of the community for each treatment. The PRC method distills the complexity of time‐dependent, community‐level effects of pollutants into a graphic form that can be appreciated more readily than the results of other currently available multivariate techniques. The PRC method also enables a quantitative interpretation of effects towards the species level.

show abstract

“…One of these was calculated using Euclidean distance and the other with cosine of vector distance [22,23]. The third test used nonmetric clustering and association analysis (NCAA) as computed by the program RIFFLE [24–27]. Each of these methods assigns individual microcosms to clusters without the intervention of the investigator.…”

Section: Methodsmentioning

confidence: 99%

A test of the community conditioning hypothesis: Persistence of effects in model ecological structures dosed with the jet fuel jp‐8

Landis

Markiewicz

Matthews

et al. 2000

Enviro Toxic and Chemistry

View full text Add to dashboard Cite

The foundation of the community conditioning hypothesis, the persistence of effects, was tested in a series of microcosm experiments. Experiments were conducted with the water‐soluble fraction of the turbine fuel JP‐8 using the standard protocols for the standardized aquatic microcosm (SAM). A repeat trial was conducted using the SAM protocol but with a 126‐d test period, twice the standard duration. The results were examined using a variety of conventional univariate, multivariate, and graphical techniques. The principal conclusions were as follows. Effects are persistent in these model ecological systems long after the degradation of the toxicant. Patterns of impacts are detectable at concentrations 15 times lower than an experimentally derived single‐species EC50. The replicate experiments are not replicable in the specific, but the broad pattern of the disruption of algal‐ herbivore dynamics followed by more subtle effects are consistently repeated. The durability of the indirect effects and therefore the information about historical events appears to be a consistent feature of these microcosm systems. The identity of the treatment groups persists. The critical features of the community conditioning hypothesis—persistence of information within ecologicalsystems and the reappearance of patterns and therefore the nonequilibrium dynamics—are again confirmed. The implications of these findings for environmental toxicology, monitoring, and ecological risk assessment are discussed.

show abstract

Clustering without a metric

Cited by 38 publications

References 11 publications

Barriers to upstream passage by two migratory sculpins, prickly sculpin (Cottus asper) and coastrange sculpin (Cottus aleuticus), in northern Puget Sound lowland streams

Barriers to upstream passage by two migratory sculpins, prickly sculpin (Cottus asper) and coastrange sculpin (Cottus aleuticus), in northern Puget Sound lowland streams

Principal Response Curves: Analysis of Time-Dependent Multivariate Responses of Biological Community to Stress

A test of the community conditioning hypothesis: Persistence of effects in model ecological structures dosed with the jet fuel jp‐8

Contact Info

Product

Resources

About