Dispersion Measures & Multilevel Regression

← Back to Domain-Specific Families

Abstractions about modeling heterogeneity and dispersion in grouped or clustered data, covering regression extensions for clustered outcomes (Hierarchical Generalized Linear Model, Binomial Regression, Multilevel Regression with Poststratification), dispersion statistics (Lexis Ratio, Variation Ratio, Interaction), and selection-correction methods like Heckman Correction.

11 abstractions in this family — domain-specific abstractions that sit near one another in structural-signature space (k-means over structural-signature embeddings). Each is shown with its short description.

• Acknowledgment index — A scientometric index of named support and influence in scholarly acknowledgments, exposing funding, technical, collegial and institutional contributions that citation counts do not capture.
• Binomial regression — Model a binomial response by linking each observation's success probability to predictors, keeping trial denominators, link choice, variance assumptions, and overdispersion diagnostics explicit.
• Heckman correction — A two-step or full-likelihood econometric method that models sample selection and adds the implied inverse Mills ratio to correct outcome estimates under joint-normality assumptions.
• Hierarchical generalized linear model — An extension of generalized linear modeling that represents clustered or multilevel responses through random effects and linked conditional distributions that can be nonnormal.
• Historical significance — Judge why a past person, event, development, or experience merits historical attention by applying explicit, contestable criteria whose answers change with question, scale, evidence, and present perspective.
• Historiometry — The quantitative study of historical people, achievements and change using coded documentary records and statistical analysis.
• Interaction (statistics) — A model relation in which the association or effect of one predictor on an outcome changes with the level of another predictor.
• Lexis ratio — A dispersion ratio comparing observed variation in grouped binomial proportions with the variation expected under one common success probability.
• Multilevel regression with poststratification — An estimation method fitting a hierarchical outcome model to sample data and averaging cell predictions using known target-population cell counts.
• Thurstonian model — A latent-variable model that explains discrete choices, rankings or ordered responses by comparing noisy continuous psychological values, commonly modeled as jointly normal.
• Variation ratio — A nominal-data dispersion measure equal to the proportion of observations outside the modal category.