Statistical pitfalls in corpus research

Add to your list(s) Download to your calendar using vCal

• Toni Rietveld, Radboud University Nijmegen
• Wednesday 20 October 2010, 16:00-17:30
• GR-06/07, English Faculty Building.

If you have a question about this talk, please contact Chris Cummins.

The availability of large memory spaces in computers has promoted the creation of corpora of normal and pathological speech and language samples. The analysis of these corpora demands different strategies to those used in balanced factorial designs.

In this talk I will discuss four topics: 1) the incorrect use of “significance” as an index of effect size, 2) the importance of indices of agreement between transcribers, 3) the danger of unit dependencies in the analysis of data obtained in the context of dyadic communication and 4) a way of coping with sequential dependencies in the analysis of corpus data.

This talk is part of the RCEAL Tuesday Colloquia series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• GR-06/07, English Faculty Building
• RCEAL Tuesday Colloquia

Note that ex-directory lists are not shown.