Covers linear models, generalized linear and non-linear regression, and models. Includes interpretation of parameters, including collapsibility and non-collapsibility, estimating equations; likelihood; sandwich estimations; the bootstrap; Bayesian inference: prior specification, hypothesis testing, and computation; comparison of approaches; and diagnostics. Prerequisites: STAT 512 and STAT 513;BIOST/STAT 533 or STAT 421/STAT 502 and STAT 423/STAT 504; a course in matrix algebra. Offered: jointly with STAT 570; Autumn