Linear Discriminant Analysis
Linear Discriminant Analysis - Related Videos
04:57
Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size (LEfSe) in Microbiome Data
0 Views •
Cited by 81 •
2022
LEfSe (LDA Effect Size) is a tool for high-dimensional biomarker mining to identify genomic features (such as genes, pathways, and taxonomies) that significantly characterize two or more groups in microbiome data.
02:55
Stereotypes, Prejudice, and Discrimination
0 Views •
2020
Humans are very diverse and although we share many similarities, we also have many differences. The social groups we belong to help form our identities (Tajfel, 1974). These differences may be difficult for some people to reconcile, which may lead to prejudice toward people who are different. Prejudice is a negative attitude and feeling toward an individual based solely on one’s membership in a particular social group (Allport, 1954; Brown, 2010). Prejudice is common against people who are...
06:41
Testing for Odor Discrimination and Habituation in Mice
0 Views •
Cited by 66 •
2015
This manuscript describes a protocol to examine the olfactory system of rodents. The olfactory habituation/dishabituation test will allow investigators to determine whether a mouse habituates to a repeatedly presented odor and whether the mouse demonstrates dishabituation when presented a novel odor.
01:25
Price Discrimination under Monopoly
0 Views •
2024
Price discrimination under monopoly refers to the practice where a monopolist charges different prices for the same product or service to different customers or in different markets. This strategy allows the monopolist to capture more consumer surplus, turning it into additional profits. For price discrimination to be effective, three conditions must be met: 1) the firm must have market power, 2) the firm must have the ability to separate markets or customers, and 3) the firm faces different...
10:05
Measurement & Analysis of the Temporal Discrimination Threshold Applied to Cervical Dystonia
0 Views •
Cited by 1 •
2018
Methods for the measurement and analysis of the temporal discrimination threshold are presented, and its application to the study of the pathogenesis of cervical dystonia are discussed.
FAQs
LDA compares class centers through their estimated means while accounting for shared within-class covariance. The optimization favors directions where between-class variation is large relative to variation within classes. For neural measurements, this weighting identifies combinations of features that separate labeled activity patterns without treating every feature as equally informative, producing a projection tied to the experimental categories.
The shared covariance estimate captures how features vary together within the classes and determines how strongly each feature contributes to separation. It therefore affects both the discriminant projection and the placement of decision boundaries. In neuroscience datasets using electrophysiological, imaging, or behavioral measurements, this step connects the classifier’s weighting to the measured patterns of within-class variability.
It is useful when a study needs fewer feature dimensions that still emphasize predefined categories. The resulting linear combinations can summarize class-related structure for comparing brain states or examining stimulus-, movement-, or cognitive-state patterns, while retaining a direct relationship to the original measured features.
Begin with observations assigned to predefined classes and select the measured features used for discrimination. Estimate each class’s mean and the shared within-class covariance, then derive discriminant combinations and use them to classify observations. The resulting assignments can support comparisons among neural or clinical categories.
The method can be applied to electrophysiological, imaging, or behavioral measurements when observations correspond to labeled stimuli, movements, cognitive states, or clinical groups. Researchers can use it to decode category-associated activity patterns, compare brain states, or evaluate whether measured features contain information about a clinical or neural category.
A successful separation indicates that the measured feature combinations distinguish the predefined categories in the analyzed data. The interpretable decision boundaries and efficient computation make LDA useful for decoding experiments and for evaluating whether recorded measurements carry category-related information, including distinctions among neural states or clinical groups.