Distributional Analysis Techniques in Psychology
Date:
03/11/2014
Organised by:
University of Southampton / ESRC DTC
Presenter:
Dr Heather Sheridan
Level:
Intermediate (some prior knowledge)
Contact:
Dr. Heather Sheridan, h.sheridan@soton.ac.uk
Description:
In many scientific domains, researchers are interested in understanding the impact of a variable on a latency measure, such as the time it takes a subject to press a response button (e.g, reaction time), or the time that a subject spends looking at a stimulus (e.g., eye fixation duration). In Psychology, the vast majority of these studies have examined mean latencies (e.g., the average response time across multiple subjects or trials). However, there is now a growing recognition that distributional analysis techniques can lead to novel scientific insights, by providing fine-grained information that is not available from mean analyses alone. Accordingly, the main goal of the course is to provide students with a practical introduction to several distributional analysis techniques that are commonly used in Psychology and related disciplines, including histograms, hazard curves, survival curves, and ex-Gaussian fitting. Students will have the opportunity to practice these techniques on their own datasets, and they will be provided with demonstrations of how to perform distributional analyses using MATLAB scripts, free software, and online resources. The knowledge gained from the course will be widely applicable, given that distributional analyses are currently being used in a variety of scientific, clinical and applied settings.
Students will learn how to perform distributional analyses using Matlab. Students will also gain an in-depth understanding of the relative strengths and weaknesses of the distributional approaches.
The course is designed to orient students to distributional analysis techniques (e.g., histograms, survival curves, hazard curves, ex-Gaussian fitting), with the goal of providing students with a practical new tool for analysing their own datasets. As well, the course will provide students with the background knowledge that they need to critically evaluate and understand new advances in the field, given that many recent articles in Psychology have employed distributional analysis techniques to supplement traditional mean analyses. The students will leave the course with an appreciation for why distributional analyses are a useful way to examine reaction times and fixation time data, an understanding of some of the available techniques, and practical knowledge of how to carry-out these analyses on their own datasets. To accomplish these learning objectives, the course will include lectures, class discussions, practical tutorials and demonstrations, plenty of time for individual questions, and examples drawn from a variety of fields, including reading and language, visual search, scene perception and medicine.
Cost:
N/A
Website and registration:
http://www.southampton.ac.uk/esrcdtc/news/events/2014/11/03_dist_analysis_techniques.page
Region:
South East
Keywords:
Behavioural Research, Quantitative Data Handling and Data Analysis, Time Series Analysis, Quantitative Approaches (other), Quantitative Software
Related publications and presentations:
Behavioural Research
Quantitative Data Handling and Data Analysis
Time Series Analysis
Quantitative Approaches (other)
Quantitative Software