August 27, 13:00-17:00 CEST
Improving the Informational Value of Studies
Increased attention to the design of experiments has lead to journals starting to require sample size justifications and a-priori power analyses. How do you decide upon the sample size in studies? How can you design reliable but efficient studies, that allow you to both show the presence, and the absence, of an effect that is meaningful?
|13:15-14:30||Type 2 error control: Statistical power. Which sample sizes do you need, and which effects can you study? How do you perform and report a power analysis, and how can you perform power analyses using simulations?|
|14:30 – 14:45||Coffee break|
|14:45-15:30||Sequential analyses: How can you design studies by repeatedly collecting data without inflating error rates? What are similarities and differences between Frequentist and Bayesian approaches to sequential analyses?|
|15:30 – 15:45||Coffee break|
|15:45 – 17:00||What would falsify your hypothesis? How can we specify falsifiable predictions? How do you determine your smallest effect size of interest based on theory, practical relevance, or feasibility, and test for equivalence?|
Daniel Lakens is an experimental psychologist working at the Human-Technology Interaction group at Eindhoven University of Technology. In addition to his empirical work in cognitive and social psychology, he works actively on improving research methods and statistical inferences, and has published on the importance of replication research, sequential analyses and equivalence testing, and frequentist statistics. He was involved in establishing dedicated grants for replication studies by the Dutch science funder NWO, and co-edited the first special issue on Registered Reports in psychology in 2014. His lab is funded until 2022 by a VIDI grant on a project that aims to improve the reliability and efficiency of psychological science. He teaches about better research practices on Coursera, and received the Leamer-Rosenthal Prize for Open Social Science in 2017 for his course ‘Improving Your Statistical Inferences’ in which more than 50.000 learners have enrolled.