eigenstigma

Eigenstigma is a theoretical construct used to describe the principal pattern by which stigma is distributed across multiple social dimensions. The term draws an analogy to eigenvectors in linear algebra, where complex data can be decomposed into orthogonal axes of variation. In this view, stigma is a multi-dimensional phenomenon that can be represented as a data matrix whose rows are individuals or contexts and whose columns correspond to attributes or perceived stigmatizing features (for example race, gender, disability status, health condition, or socioeconomic position).

By applying techniques such as eigen decomposition or principal component analysis to this matrix, researchers can identify eigenstigma directions—the eigenvectors that capture the most variance in perceived stigma. The eigenvalues indicate the strength or prominence of each axis. The first eigenstigma, associated with the largest eigenvalue, is interpreted as the dominant pattern of stigmatization, while subsequent eigenstigmas reveal secondary, independent patterns.

Uses of the concept include exploratory analysis of stigma data, comparison across populations or over time, and informing interventions that target the most influential stigma dimensions. The framework emphasizes that stigma can coexist across dimensions in structured, partly independent ways rather than as a single, uniform stigma.

Critics note that reducing stigma to mathematical axes risks oversimplification and can obscure context, history, and power dynamics. The approach also requires large, reliable data and careful methodological choices in matrix construction and interpretation. As a theoretical or analytical construct, eigenstigma is not universally adopted and remains one of several tools for studying stigma patterns.

See also: self-stigma, social stigma, principal component analysis, multivariate statistics.