Révész | M0.02

Plantage Muidergracht 12, 1018 TV Amsterdam

Jul 18 @ 09:00 UTC - Jul 18 @ 12:30 UTC

Public session

Recently developed safe tests based on e-values, and anytime-valid confidence intervals form a suite of statistical methods that simplify and optimise the design, conduct, and inferential process for both single-lab experiments and large-scale multi-lab (replication) studies. Safe tests combine the interpretability of Bayes factors (i.e. measuring evidence for and against a null hypothesis) with frequentist power and type I error guarantees. These guarantees are maintained even if the safe test is conducted after each observation and used to determine whether the experiment should be (prematurely) stopped or continued. Similarly, unlike 95% (Bayesian) credible intervals and 95% (frequentist) confidence intervals, a 95% anytime-valid confidence interval will, with at least 95% chance, cover the true effect size regardless of whether or how data collection is stopped. In this workshop we will provide an introduction to this novel framework of statistical inference, and show how it can be exploited to yield more generalisable conclusions with less data. We will alternate between short theoretical lectures and hands-on practical sessions that focus on designing and making inference for practical problems with R/RStudio.

Jul 18 @ 14:00 UTC - Jul 18 @ 17:30 UTC

Public session

In this workshop, participants will learn how to use hidden semi-Markov pattern analysis (HMP, Anderson, Zhang, Borst, \& Walsh, 2016) to detect cognitive stages on a by-trial basis in EEG data. HMP combines hidden semi-Markov models with multivariate pattern analysis to quantify the number of cognitive processes within a trial as well as estimate their durations on a single-trial basis. The workshop is decomposed into lectures about the method and tutorials. Tutorials will be based on a python implementation with new functionalities (see https://github.com/GWeindel/hmp) and will guide participants through all the possibilities offered by HMP. After this workshop, participants will be familiar with the method and the code, able to simulate data corresponding to their research question, fit HMP models to their data, analyse the resulting models and draw inferences on experimental and individual differences, and leverage their EEG analysis through by-trial estimates of cognitive events timing. The last lecture will allow participants to further think about how they can integrate HMP with cognitive and statistical models of behaviour. To make the most of the workshop you should bring your laptop with Anaconda installed (see [anaconda](https://www.anaconda.com/products/distribution%3E) for how to install). Once conda is installed you can already download MNE python (https://mne.tools/) to save some time during the set-up, a recommended way is to use a dedicated conda environment as follows (see [conda managing environments](https://conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html#)): ``` $ conda create --override-channels --channel=conda-forge --name=hmp mne ``` Please don't yet install the hsmm_mvpy package (https://github.com/GWeindel/hsmm_mvpy), instructions will be given during the workshop.

Jul 19 @ 09:00 UTC - Jul 19 @ 11:00 UTC

In-person session

Jul 19 @ 11:20 UTC - Jul 19 @ 12:40 UTC

In-person session

Jul 20 @ 09:00 UTC - Jul 20 @ 10:20 UTC

In-person session

Jul 20 @ 11:00 UTC - Jul 20 @ 12:00 UTC

In-person session

Jul 21 @ 09:00 UTC - Jul 21 @ 10:40 UTC

In-person session

Jul 21 @ 11:00 UTC - Jul 21 @ 12:40 UTC

In-person session