master class

Understanding Statistics for Human–Computer Interaction and Related Disciplines

6th and 7th February 2020

A statistics master class by Alan Dix

Registration

The master class is FREE, but places are limited, so do register ASAP at eventbrite

NOTE:  The event is full and we’re not taking more registrations, but there will be a re-run soon.  Please keep an eye here, the HCIstatistics Facebook page, or Twitter @HCIStatistics or  @alanjohndix for news.

Do you find statistics confusing? This course fills the gap between the ‘how to’ knowledge in basic statistics courses and deep understanding, from traditional hypothesis testing to Bayesian techniques.

This is a ‘master class’ in that many of issues discussed will not be found in a traditional textbook or statistics course – but expressed in ways that do not assume any existing statistical expertise.  It includes aspects of statistical `craft’ skill that you will not find in conventional material.

Format

A one/two day course:

  • day 1 –  ‘taught’ day with hands in exercises: understanding randomness, different kinds of statistics, gaining power, interpreting results
  • day 2 –  workshop day – bring your own data and questions to discuss in round table

You can attend either day 1 on its own or both days.  Please let us know whether you intend to attend both days or just the first day.

About the master class

Many find statistics confusing, perhaps more so given publicity concerning problems of traditional statistics, replication, and alternatives such as Bayesian statistics. Based on a new book to be published by Morgan-Claypool in 2020, this course will help attendees navigate this morass: to understand the statistics in articles and the press and to make appropriate choices in empirical or quantitative studies. It fills the gap between the ‘how to’ knowledge of basic statistics courses and deep understanding. You won’t learn a hundred new statistical techniques, but you will find out what those you have heard of and use actually mean.

Intended Audience(s)

The course is intended for both experienced researchers and students who have already, or intend to engage in quantitative analysis of empirical data or other forms of statistical analysis. It will also be of value to practitioners using quantitative evaluation.

The course will assume some familiarity with statistical concepts theoretical or practical, for example, the use of t-tests or similar techniques. There will be occasional formulae, but the focus of the course is on conceptual understanding not mathematical skills.