What question did this study set out to answer?

To present comprehensive classical and modern regression methodologies that bridge conceptual mathematical foundations with diverse real-world applications.

March 1, 1988Journal of the American Statistical Association

Classical and Modern Regression With Applications.

View Full Paper

Ask AI

Bookmark

Authors

RSR. Kirk SteinhorstUnited States Fish and Wildlife Service RMRaymond H. MyersUniversity of South Carolina

Discussion

Member takes

Implication

Methodological review demonstrates classical and modern regression modeling across diverse scientific disciplines, highlighting robust approaches for complex linear and nonlinear data.

Key Points

To present comprehensive classical and modern regression methodologies that bridge conceptual mathematical foundations with diverse real-world applications.
Synthesized theoretical linear model developments including least squares geometry, general linear hypotheses, and ANOVA equivalence.
Integrated diagnostics and estimation techniques such as maximum likelihood estimation, residual plotting, and Box-Cox transformations.
Applied linear, logistic, and non-normal error regression frameworks to empirical data sets from engineering, biology, management science, and economics.
Demonstrated unified estimation frameworks linking least squares geometric properties directly with classical analysis of variance models.
Established analytical pathways to diagnose and adjust for non-normal errors, autocorrelated observations, and simultaneous influential outliers using residual evaluation.
Formulated modeling strategies for non-continuous responses through generalized structures including logistic regression and categorical outcome formulations.

Cite This Study

Steinhorst et al. (1988) studied this question.

synapsesocial.com/papers/6a0cba01cf313b58ec7a667b https://doi.org/10.2307/2288958

View Full Paper

Ask AI

Bookmark

Implication

Methodological review demonstrates classical and modern regression modeling across diverse scientific disciplines, highlighting robust approaches for complex linear and nonlinear data.

Classical and Modern Regression With Applications.

Discussion

Member takes

Implication

Key Points

Cite This Study

Classical and Modern Regression With Applications.

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider