CSI: Computing for Statistical Inference

Lecturer
Dr. G. Qian., La Trobe, Semester 1.
Syllabus
Introduction of some modern computer intensive methods for statistical modelling and inference.
  1. Bootstrap for exploring the sampling distribution of a parameter estimator. Cross-validation for model selection.
  2. EM algorithm for maximum likelihood estimation with incomplete data.
  3. Markov chain, Monte Carlo algorithms for Bayesian computation in spatial statistics and image analysis. Gibbs sampler.
  4. Use of S-plus for practising these methods.
Prerequisites
Statistics and probability at third year undergraduate level.
  • Generic skills

    •  

    References
    References
    • Efron, B. and Tibshirani (1993) An Introduction to the Bootstrap, Chapman and Hall.
    • Knuth, D.E. (1981) The Art of Computer Programming, Vol. 2: Semi-numerical algorithms, 2nd Edition. Chapter 2., Addison-Wesley
    • Tanner, M. (1996) Tools for Statistical Inference, 3rd Edition, Springer-Verlag.
    • Rao, C.R. (Editor) (1993) Handbook of Statistics, Vol. 9., North-Holland.

    Back to list of elective components

    Last updated: 30 October 2002.