Cluster Validation by Prediction Strength

Tibshirani, Robert; Walther, Guenther

doi:10.1198/106186005x59243

Cited by 519 publications

(509 citation statements)

References 11 publications

Supporting

Mentioning

505

Contrasting

Unclassified

Order By: Relevance

“…The sequence of predominating topographies (template maps) in the cumulative group-averaged data was identified using a hierarchical clustering based on an atomize and agglomerate approach. The optimal number of clusters to describe the dataset was identified using a modified KrzanowskieLai criterion (Tibshirani et al, 2005). Differences in the pattern of topographic maps observed between conditions in the group-averaged data were tested by calculating the spatial correlation between these template maps from the group-averaged data and each time-point of single-subject data from each experimental condition.…”

Section: Topographic Patterns Analysesmentioning

confidence: 99%

Plastic modifications within inhibitory control networks induced by practicing a stop-signal task: An electrical neuroimaging study

Manuel

Bernasconi

Spierer

2013

Cortex

View full text Add to dashboard Cite

Section: Topographic Patterns Analysesmentioning

confidence: 99%

Plastic modifications within inhibitory control networks induced by practicing a stop-signal task: An electrical neuroimaging study

Manuel

Bernasconi

Spierer

2013

Cortex

View full text Add to dashboard Cite

“…unige.ch/cartool.htm; see also Tibshirani et al, 2005). This clustering procedure identifies the topographies (ie maps) dominating the group-averaged AEPs across populations/ conditions.…”

Section: Eeg Recordings and Analysesmentioning

confidence: 99%

Glutathione Precursor, N-Acetyl-Cysteine, Improves Mismatch Negativity in Schizophrenia Patients

Lavoie

Murray

Deppen

et al. 2007

Neuropsychopharmacol

328

222

View full text Add to dashboard Cite

In schizophrenia patients, glutathione dysregulation at the gene, protein and functional levels, leads to N-methyl-D-aspartate (NMDA) receptor hypofunction. These patients also exhibit deficits in auditory sensory processing that manifests as impaired mismatch negativity (MMN), which is an auditory evoked potential (AEP) component related to NMDA receptor function. N-acetyl-cysteine (NAC), a glutathione precursor, was administered to patients to determine whether increased levels of brain glutathione would improve MMN and by extension NMDA function. A randomized, double-blind, cross-over protocol was conducted, entailing the administration of NAC (2g/day) for 60 days and then placebo for another 60 days (or vice versa). 128-channel AEPs were recorded during a frequency oddball discrimination task at protocol onset, at the point of cross-over, and at the end of the study. At the onset of the protocol, the MMN of patients was significantly impaired compared to sex-and age-matched healthy controls (p ¼ 0.003), without any evidence of concomitant P300 component deficits. Treatment with NAC significantly improved MMN generation compared with placebo (p ¼ 0.025) without any measurable effects on the P300 component. MMN improvement was observed in the absence of robust changes in assessments of clinical severity, though the latter was observed in a larger and more prolonged clinical study. This pattern suggests that MMN enhancement may precede changes to indices of clinical severity, highlighting the possible utility AEPs as a biomarker of treatment efficacy. The improvement of this functional marker may indicate an important pathway towards new therapeutic strategies that target glutathione dysregulation in schizophrenia.

show abstract

“…Examples are Ben-Hur et al (2002), Bryan (2004), Dudoit and Fridlyand (2002), Grün and Leisch (2004), Lange et al (2004), Monti et al (2001) and Tibshirani and Walther (2005). Many of these papers use stability or prediction strength measurements as a tool to estimate the true number of clusters.…”

Section: Introductionmentioning

confidence: 99%

Cluster-wise assessment of cluster stability

Hennig

2007

Computational Statistics & Data Analysis

606

502

View full text Add to dashboard Cite

Stability in cluster analysis is strongly dependent on the data set, especially on how well separated and how homogeneous the clusters are. In the same clustering, some clusters may be very stable and others may be extremely unstable.The Jaccard coefficient, a similarity measure between sets, is used as a clusterwise measure of cluster stability, which is assessed by the bootstrap distribution of the Jaccard coefficient for every single cluster of a clustering compared to the most similar cluster in the bootstrapped data sets. This can be applied to very general cluster analysis methods.Some alternative resampling methods are investigated as well, namely subsetting, jittering the data points and replacing some data points by artificial noise points. The different methods are compared by means of a simulation study.A data example illustrates the use of the cluster-wise stability assessment to distinguish between meaningful stable and spurious clusters, but it is also shown that clusters are sometimes only stable because of the inflexibility of certain clustering methods.

show abstract

Cluster Validation by Prediction Strength

Cited by 519 publications

References 11 publications

Plastic modifications within inhibitory control networks induced by practicing a stop-signal task: An electrical neuroimaging study

Plastic modifications within inhibitory control networks induced by practicing a stop-signal task: An electrical neuroimaging study

Glutathione Precursor, N-Acetyl-Cysteine, Improves Mismatch Negativity in Schizophrenia Patients

Cluster-wise assessment of cluster stability

Contact Info

Product

Resources

About