Patterns of ordination and classification instability resulting from changes in input data order

Tausch, Robin J.; Charlet, David A.; Weixelman, Dave A.; Zamudio, Desiderio C.

doi:10.2307/3236404

Cited by 85 publications

(34 citation statements)

References 24 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The TWINSPAN software, which imitates the principles used in phytosociology, has received much criticism because of its sensitivity to order of data input (Tausch et al 1995), and problems with detecting the major gradient within the species data (Belbin and McDonald 1993). However, when applying TWINSPAN classi® cation on the 19 plant communities, it succeeded in arranging the communities along ā oristic gradient that re¯ects the major gradient in vegetation cover and the environmental moisture gradient.…”

Section: Sampling and Classi® Cationmentioning

confidence: 98%

Mapping and analysing arctic vegetation: Evaluating a method coupling numerical classification of vegetation data with SPOT satellite data in a probability model

Nilsen¹,

Elvebakk²,

Brossard³

et al. 1999

International Journal of Remote Sensing

View full text Add to dashboard Cite

Vegetation and environmental data were collected at 266 sampling points distributed in a regular manner along transects covering the Brù ggerhalvù ya peninsula, on the north-western coast of Spitsbergen. Transects with sampling points were drawn in advance on aerial photographs. The analysis of releve Â s and collection of ground data along transects represent an e cient, representative and precise way of sampling. The vegetation data were classi® ed and 19 plant communities distinguished. The plant communities were subjected to detrended correspondence analysis (DCA). Among the recorded variables, moisture is the one with the highest correlation along axes one and two, and re¯ects a coincidental moisture and vegetation cover gradient. The vegetation component responsible for this positive correlation is the bryophytes. Likewise, the TWINSPAN classi® cation con® rms this gradient in a dendrogram re¯ecting the hierarchical structure of the plant communities.Plant communities constitute the base of a statistical model that links the communities and the SPOT satellite data. The model then classi® es and maps plant communities by means of satellite data, covering the entire Brù ggerhalvù ya peninsula. Satellite data and environmental data were analysed regarding their ability to distinguish the plant communities in a discriminant function analysis (DFA). The results of the DFA indicate that it may be reasonable to include all the information from the di erent satellite channels when using satellite data for vegetation classi® cation purposes. Among the satellite data the panchromatic channel is the one adding the most unique information to the power of the model in separating plant communities.The classi® cation of satellite data using the probability model indicates that plant communities with less than 30% vegetation cover could be classi® ed with the same degree of con® dence or better, as compared with plant communities with more than 30% vegetation cover. The overall percentage of correctly classi-® ed releve Â s increased by 13% when using probability level two instead of level one (57.8 to 71.1%). The probability classi® cation model makes it possible

show abstract

Section: Sampling and Classi® Cationmentioning

confidence: 98%

Mapping and analysing arctic vegetation: Evaluating a method coupling numerical classification of vegetation data with SPOT satellite data in a probability model

Nilsen¹,

Elvebakk²,

Brossard³

et al. 1999

International Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Notably, intuitive dimension-reduction and projection methods such as (PCA) and correspondence analysis can be criticized on the grounds that their eigenvalues must be iteratively estimated and that they require that the number of eigenvalues to be used be selected. Because of this, the overall "broad pattern" results can be entry order-sensitive (Tausch et al 1996). This is especially so if only a few major components are sought.…”

mentioning

confidence: 98%

A Classification-Based Machine Learning Approach for the Analysis of Genome-Wide Expression Data

Lyons‐Weiler¹

2003

Genome Res.

View full text Add to dashboard Cite

Three important areas of data analysis for global gene expression analysis are class discovery, class prediction, and finding dysregulated genes (biomarkers). The clinical application of microarray data will require marker genes whose expression patterns are sufficiently well understood to allow accurate predictions on disease subclass membership. Commonly used methods of analysis include hierarchical clustering algorithms, t-, F-, and Z-tests, and machine learning approaches. We describe an approach called the maximum difference subset (MDSS) algorithm that combines classification algorithms, classical statistics, and elements of machine learning and provides a coherent framework. By integrating prediction accuracy, the MDSS algorithm learns the critical threshold of statistical significance (the ␣ or P-value), eliminating the arbitrariness of setting a threshold of statistical significance and minimizing the effect of the normality assumptions. To reduce the false positive rate and to increase external validity of the predictive gene set, a jackknife step is used. This step identifies and removes genes in the initial MDSS with low combined predictive utility. The overall MDSS provides a prediction that is less dependent on an arbitrary study design (sample inclusion or exclusion) and should thus have high external validity. We demonstrate that this approach, unlike other published methods, identifies biomarkers capable of predicting the outcome of anthracycline-cytarabine chemotherapy in cases of acute myeloid leukemia. By incorporating two criteria-statistical significance and predictive utility-the approach learns the significance level relevant for a given data set. The MDSS approach can be used with any test and classifier operator pair.

show abstract

“…Nomenclature follows Godfrey and Wooten (1981 parts of ponds and/or levees were included in areas that were classified as natural marsh, Some species that are difficult to identify correctly using helicopter surveys, such as some grasses and sedges, were grouped by genus. After this, species occurring in less than 5 stations (approximately 1% of the stations) were removed to reduce the influence of these rare species in the analysis and increase stability of the analysis (Tausch et al 1995). The abundance data from all years (343 stations) were clustered using two-way indicator species analysis (TWINSPAN) with the stan- (Hill 1979) to determine vegetation types.…”

Section: Methodsmentioning

confidence: 99%

Long-term vegetation change in Louisiana tidal marshes, 1968–1992

et al. 1999

View full text Add to dashboard Cite

The Louisiana coastal marshes form some of the most extensive wetlands within the continental United States. The problem of land loss in these coastal marshes is well-documented, but very little is known about possible changes in vegetation composition that might be associated with this loss. We analyzed vegetation data collected from 1968 to 1992 in the tidal wetlands of Terrebonne parish and described five vegetation types that occur in this region. Our data did not show the predicted change to more salt-tolerant vegetation. This is probably due to the influence of the Atchafalaya River in the study area. However, we documented a large change in the dominant vegetation of the fresh marsh. Panicum hemitornon-dominated marshes occupied 51% of the study area in 1968 and only 14% in 1992. This vegetation type was replaced with Eleocharis baldwinii-domJnated marshes (3% in 1968 to 41% in 1992). This change occurred adjacent to an area of significant conversion to open water. Based on limited available data from the literature, we ev',duated three potential driving factors in this change-grazing, water-level increase, and water quality-but could not determine the cause of change definitively.

show abstract

Patterns of ordination and classification instability resulting from changes in input data order

Cited by 85 publications

References 24 publications

Mapping and analysing arctic vegetation: Evaluating a method coupling numerical classification of vegetation data with SPOT satellite data in a probability model

Mapping and analysing arctic vegetation: Evaluating a method coupling numerical classification of vegetation data with SPOT satellite data in a probability model

A Classification-Based Machine Learning Approach for the Analysis of Genome-Wide Expression Data

Long-term vegetation change in Louisiana tidal marshes, 1968–1992

Contact Info

Product

Resources

About