Hypothesis testing for qualitative data; risks and rewards of statistical testing. The “replication crisis” in some experimental sciences.
What correlation means, how to calculate it, how to test whether it is significant.
The next tutorial exercises are practice exam questions, now online.
Corpora are the foundation for many data-driven applications: from experimental research into the development of language to automatic translation of written text.
Notes and solutions for Tutorial 4; Exercises for Tutorial 6; Information about the continuing strike.
Lecture 12 cancelled owing to heavy snow; here’s a link to last year’s recording, some homework reading and additional references.
Information about the strike planned for this week, and beyond.
As advertised just before Friday’s lecture
Defining and using schemas to capture particular kinds of XML document.
Notes for Tutorial 3 now online, together with the next set of exercises.