Stat 6519 Regression models


Linear statistical inference and its applications are fundamental to all areas of applied statistics. This new course will cover the basic regression models which are frequently used in linear statistical inferences. It will provides a powerful kit of tools to the Master of Applied Statistics students for the success in their future career.

The course  introduces simple and multiple linear regression, Gauss-Markov theorem and followed by
residual analysis, tests of linear hypotheses, model building and regression diagnostics, analysis of variance and covariance and error-in-variable problems.

Credit restriction

Stat-6519 cannot be used to satisfy the minimum course requirements of the M.Sc. in statistics programme.

Tentative course outline

  1. Simple and multiple linear regression, Gauss-Markov theorem.
  2. Residual analysis.
  3. Tests of linear hypotheses.
  4.  Model selection.
  5.  Regression diagnostics.
  6. Analysis of variance.
  7. Analysis of covariance.
  8. Error-in-variable problems in regression models


  • N. R. Draper, H. Smith. Applied Regression Analysis, John Wiley & Sons, Inc. New York, 1966.
  • C. R. Rao. Linear Statistical Inference and Its Applications, 2nd edition, John Wiley \& Sons, Inc. New York, 2001.
  • D. A. Belsley, E. Kuh, R. E. Welsch. Regression Diagnostics—Identifying influential data and sources of collinearity, John Wiley & Sons, Inc. New York, 1980.
  • J. P. Buonaccorsi. Measurement Error--Models, Methods and Applications, Chapman & Hall/CRC, New York, 2010.