SARMAC XI Pre-conference Workshops

The conference will be preceded by two workshops on Wednesday 24 June: Sigi Sporer on effect size and meta-analysis from 9 to 12 and EJ Wagenmakers et al. on Bayesian analysis from 1 to 4. These workshops will be held only if sufficient numbers register, and the start and end times might be adjusted.

EFFECT SIZE CALCULATION AND INTRODUCTION TO META-ANALYSIS

Siegried L. Sporer, Ph.D.

Objectives
The aim of this workshop is to enable participants to calculate effect sizes for experimental and correlational designs and to introduce them to the principles of how to conduct a meta-analysis. Bring a laptop to get hands-on experience. Participants will learn to calculate effect sizes with a spreadsheet made available online beforehand for registered users. Participants learn the basic steps in conducting a meta-analysis and will be sensitized to the importance of assessing published meta-analyses critically.

Contents
•   How to formulate a research question and hypotheses in meta-analysis
•   Literature search (with PsychInfo and SSCI)
•   Calculation of effect sizes (d, r, OR) with Excel (calculated in workshop use content available beforehand)
•   Steps in preparing a meta-analysis (coding sheet, inter-coder reliability)
•   Introduction to principles of Fixed-effects and Random-effects models
•   Introduction to principles of moderator analyses and meta-regression
•   Critically reading and interpreting meta-analyses (publication bias)

Prerequisites
Well-grounded knowledge of statistical techniques (ANOVA (t-, F-test, chi2, correlation, (multiple) regression)

Recommended reading
Cummings, G. (2012). Understanding the new statistics. New York: Routledge/Taylor & Francis.
Lipsey, M. W., & Wilson, D. B. (2001). Practical meta-analysis. Thousand Oaks, CA: Sage Publications.
Sporer, S. L., & Cohn, L. D. (2011). Meta-analysis. In B. D. Rosenfeld, & S. D. Penrod (Eds.), Research methods in forensic psychology (pp. 43-62). New York: Wiley.

Instructor

Prof. Sporer received his B.A. from the University of Colorado and his M.A. and Ph.D. from the University of New Hampshire. He is now Prof. of Social Psychology and Psychology and Law at the University of Giessen, Germany, after teaching at the University of Aberdeen, Scotland. Originally trained in social psycholoogy, his research interests expanded to basic research on facial recognition and its application to person identifications in criminal proceedings. He has also been interested in meta-memory, as well as various aspects of deception and its detection. In recent years, he has specialized in meta-analysis, primarily in the psychology and law area. He has published an introductory book chapter on meta-analysis, more than half a dozen meta-analyses, and is currently preparing six additional meta-analyses with colleagues around the globe for publication. Prof. Sporer has taught courses and workshops on meta-analysis to audiences with different levels of expertise, from Master's students to Ph.D. candidates to professionals at the American Psychology-Law Society.

A Graphic User Interface (GUI) Program for Bayesian Hypothesis Testing

Eric-Jan Wagenmakers
Richard D. Morey
Jonathon Love

Bayesian hypothesis testing presents an attractive alternative to p-value hypothesis testing. The most prominent advantages of Bayesian hypothesis testing include (1) ability to quantify evidence in favor of the null hypothesis; (2) ability to quantify evidence in favor of the alternative hypothesis; and (3) ability to monitor and update evidence as the data come in. Despite these practical advantages, Bayesian hypothesis testing is still relatively rare. An important impediment to the widespread use of Bayesian tests is arguably the lack of user-friendly software for the run-of-the-mill statistical problems that confront psychologists for almost every experiment: the t-test, ANOVA, correlation, regression, and contingency tables.

In this workshop Eric-Jan Wagenmakers, Richard Morey, and Jonathon Love introduce JASP (http://jasp-stats.org), an open-source, user-friendly "point and click" GUI that allows the user to carry out both classical and Bayesian hypothesis tests for standard statistical problems. Not only is JASP a fresh and innovative statistical software in its own right, JASP enables easy Bayesian analysis via Morey and Rouder's powerful BayesFactor (http://bayesfactorpcl.r-forge.r-project.org/) software, but without users having to know R.

This three-hour workshop will provide attendees with a friendly, gentle introduction to the theory behind Bayesian hypothesis testing, and will illustrate the possibilities of of JASP using concrete examples. At the end of this workshop, participants should be able to carry out statistical analyses in JASP, interpret the output, and report the results.

The workshop will be from 1pm to 4pm Wednesday, 24 June 2015. The charge for the workshop is $75. SARMAC 2015 will kick off later that afternoon.

Presenter Biographies

Eric-Jan Wagenmakers is Professor of Psychology at the University of Amsterdam. He studied with Raaijmakers at Amsterdam and earned his PhD in 2000 and then did postdoctoral studies with Roger Ratcliff and with Han van der Maas and Peter Molenaar. E.J.’s primary interests
are in Bayesian inference, models of decision making, and the interaction between quantitative modeling and cognitive neuroscience. He co-authored with Michael Lee a book on Bayesian modeling (published in 2013 by Cambridge).

Richard D. Morey is an Associate Professor of Psychometrics and Statistics in the Faculty of Behavioural and Social Sciences at the University of Groningen; as of 1 January, he takes up a Senior Lectureship in Psychology at Cardiff University. He earned a PhD in psychology and a Master's degree in statistics with Jeffrey Rouder and Paul Speckman at the University of Missouri. His interests are three-fold: Bayesian cognitive modelling, Bayesian statistical inference, and the cognition of statistical evidence. He is the author of the BayesFactor (http://bayesfactorpcl.r-forge.r-project.org/) software for statistical inference, which allows Bayesian analysis of common research designs in the social and behavioural sciences.

Jonathon Love is a Software Developer and Researcher at the University of Amsterdam. He completed his studies with Andrew Heathcote at the University Newcastle, Australia, and has over 15 years experience in software development. Jonathon's interests are promoting the use of liberated (free and open source) software in science and developing software which bridges the gap between methodologists and applied researchers. He is the lead developer of the JASP project.