Psychology statistics group

PsychStats is an informal and multidisciplinary group who are interested in statistics. The group started within psychology, and a majority of the members are from various psychological disciplines including education, individual differences (intelligence & personality), linguistics, reasoning and neuroscience. However, we are not limited to psychology with members from the broader community at Edinburgh including business, sociology, epidemiology, clinical psychology and medicine.

Members have experience with a range of methods requiring overlapping knowledge (e.g., ANOVA, multiple regression, multilevel/mixed effects modelling, factor analysis, structural equation modelling), using a range of different software packages (e.g., R, Python, MPlus, Mx, SAS, SPSS).

As a department, we now teach all methodology classes in R, and are increasingly over the coming years will be making these resources open source.

Journal Clubs

The psychology statistics group is an informal group that leads two journal clubs Psychstats JC and REPS (REproducible Psychological Science). Each journal club runs once per month at two-week intervals. The start dates for the JC in each academic year will be shared via the mailing list, and on Tom Booth’s University profile page.

Psychstats

Psychstats meetings are a chance to see talks on specific methodologies and their applications. Talks are given by members of the psychology statistics group, and have included in the past; mixed –effects models, SEM, factor analysis, introductions to Bayesian methods, missing data etc. In addition, we also have weeks where we will discuss new papers. If you have suggestions for topics you would like to see, please contact Tom Booth by email with “Psychstats Topic Suggestion” in the subject line. We can’t promise to get them all in, but we will try and cover the most requested.

REPS

REproducible Psychological Science is a journal club all about reproducibility and the replication crisis. This JC successfully ran for the first time in 2017-18, so we are going to roll it out again. The aim of this JC is to provide attendees with an overview of the workflow for reproducible research. Sessions cover topics like; preregistration and project management, replication designs and evaluation, github and version control, power analysis etc. Alongside the talks, we also actively contribute as a group to a multi-lab collaboration, selected by the group in the first meeting.

Other meetings of interest

Though not run by this group, two other talks series/meetings may be of particular interest.

• EdinbR:
  • EdinbR is the Edinburgh usergroup for the R programming language. Researchers at the University of Edinburgh started EdinbR in February 2015 with the aim of bringing together scientists, statisticians and programmers from all over Edinburgh to discuss R-related matters. We encourage collaboration between local R users and organise training events for those interested in learning the language.
• Centre for Statistics:
  • The recently opened Centre for Statistics runs a talk series and has a number of other resources that may be of interest. Please follow the link below to their website for more details.

EdinbR

Centre for Statistics

Invited Speakers

Finally, we have been able across the years to secure some resources to bring in external speakers. This has largely been through internal university funding for enhancement of education. If there are any current PhD students who would be interested in applying for funds and running a talk series, please contact Tom Booth.

Mailing list

If you would like to be added to the mailing list, please follow the "Instructions for using Sympa" below. If you have any issues, please contact Tom Booth. This is a moderated, low volume list, where JC talks are advertised, and members of the list can discuss statistical issues, or seek guidance on issues they may be having. Please use the list respectfully. We will also use this mailing list to let people know about our own talks, and talks organised locally by other Universities if they are relevant.

Instructions for using Sympa

Tom Booth