Statistics 34300 is an intensive course in the theory and methods of linear regression and related techniques of statistical modelling. It is intended primarily for graduate students in Statistics and related fields.

The course is also open to undergraduates and others who have a solid understanding of matrix algebra and basic statistical theory. Thorough familiarity with the simple linear regression model is expected.

The course will review linear regression with a single predictor, and will cover the multiple-predictor case; least-squares estimation; associated distribution theory; estimation, confidence intervals and tests; regression with errors in the predictors; weighted least squares, assessing lack of fit; residual analysis; regression diagnostics; transformations; model building; collinearity; subset-selection methods, including stepwise regression; prediction; nonlinear least squares.

Prerequisite:
Math 250 or equivalent, Stat 244-245 or equivalent.

Required Texts:
Venables, W.N. and Ripley, B.D. (1999). Modern Applied Statistics with S-Plus (3rd ed). Springer-Verlag.
Weisberg, S. (1985). Applied Linear Regression, Second Edition. Wiley: New York.

Search  |  Directories  |  Statistics Home  |  UChicago
Department of Statistics - 5734 S. University Avenue - Chicago, IL 60637
uchicago^® - ©2000 The University of Chicago^® Department of Statistics