MATH-408: Regression methods

Lectures in this course (33)

Introduces regression analysis, covering linear and nonlinear models, Poisson regression, and failure time analysis using various datasets.

Covers iterative weighted least squares, Poisson regression, mixed models, and likelihood ratio statistic.

Explores variable selection methods and the bias-variance trade-off in statistical modeling.

Explores binary response interpretation, link functions, logistic regression, and model selection using deviances and information criteria.

Covers iterative weighted least squares, model checking, Poisson regression, and fitting multinomial models using Poisson errors.

Covers jacamar data analysis, smoking data models, and challenges with log-linear models in visual impairment data.

Explores marginal models in modern regression, emphasizing interpretation and application in statistical analysis.

Explores overdispersion, model assessment, and regression techniques for count data.

Explores random effects, model checking, and nested vs. crossed effects in modern regression modeling.

Covers the linear mixed model, including fixed and random effects, estimation, and inference techniques.

Explores maximum likelihood estimation, profile log likelihood, inference on coefficients, quasi-likelihood, model comparison, and REML method.

Covers iterative weighted least squares, model checking, and generalized linear models in regression analysis.

Covers the IWLS algorithm for obtaining MLEs in regression models and discusses the likelihood ratio statistic and deviance in model fitting.

Covers inference, weighted least squares, spring barley data analysis, and smoothing techniques.

Explores the optimization and penalization of natural cubic splines, including roughness penalties and Bayesian inference.

Explains the construction of natural cubic splines, emphasizing smoothness and continuity in the function representation.

Explores roughness penalty, band matrices, and Bayesian inference in regression smoothing.

Covers regression methods focusing on spline smoothing and penalised fitting to balance data fidelity and smoothness.

Covers iterative weighted least squares, generalized linear models, and model checking.

Covers point estimation, confidence intervals, and hypothesis testing for smooth functions using mixed models and spline smoothing.

Page 1 of 2