Greg Kochanski

Hilary Term 2005, weeks 1-8 (Jan-Apr 2005) University of Oxford. The course meets Tuesdays at 11:00, in the Centre for Linguistics and Philology.

This course explores

• Why one needs quantitative models: a historical view of major goofs in other fields.
• Understanding Probability. We will review probability, conditional probabilities and Bayes' Theorem.
• Converting hypotheses about language into mathematical models.
• Statistical techniques that your mother didn't teach you.
  LI The Limits to ANOVA. LI Bootstrap and Monte-Carlo techniques: powerful and simple techniques for going beyond ANOVA. LI Robust statistics (clean ways to deal with the possibility of mistakes in the data). LI Machine learning systems.

The primary goal is to give the student the tools to figure out what data and theories are reliable. Secondarily, to provide tools for his or her own work.

Topics discussed may include spam filtering, attribution of authorship and style, reconstructing language groups in historical linguistics, tests of optimality theory, and models of the origin of English place names.

Prerequisites: General understanding of probability, basic statistical concepts, algebra. Some programming experience is useful, but not essential. There may be some computer examples. Students who have completed Formal Foundations for Linguistics (S. Pulman) will meet the prerequisites.

Target Audience: Linguistics and Philology. It could have application inside Experimental Psychology.