Tutorials#

These tutorials walk you through using Pyriodic for circular data analysis, from getting started to phase diagnostics and circular statistics.

Overview of respiration data preprocessing and analysis

This tutorial covers a basic pipeline for preprocessing and analysis of respiration data collected during a experimental task.

Methods for phase extraction from respiration data

See notebook for details.

Descriptive statistics for circular data

We will explore how to compute descriptive statistics for circular data using the Pyriodic package, and illustrate why we need special methods for circular data.

Permutation test between observed samples and surrogate samples (peak-to-peak shuffled)

In this tutorial, we will perform a permutation test between observed samples and surrogate samples (peak-to-peak shuffled) to assess whether the observed samples are significantly different from what would be expected by chance.

Group-level permutation test between observed samples and surrogate samples (peak-to-peak shuffled)

In this tutorial, we will perform a permutation test between observed samples and surrogate samples (peak-to-peak shuffled) at group level to assess whether the observed samples are significantly different from what would be expected by chance.

Two sample permutation test of respiratory phase angles

This notebook runs permutation tests to compare two samples of respiratory phase angles. This is useful when you want to compare the phase angles of two different conditions or groups.

Two sample permutation test of respiratory phase angles at the group level

This notebook runs permutation tests to compare two samples of respiratory phase angles. This is useful when you want to compare the phase angles of two different conditions or groups.

Test association with behavioural variable such as reaction time

This notebook runs permutation tests to see whether there is a statistically significant relationship between the phase angle at which a target stimulus was presented and the response was given by the participant.

Generating surrogate data for inference

There are many ways to generate surrogate data for inference. Here we introduce and compare several methods. What is important to note is that the surrogate data should be generated in a way that preserves the null hypothesis. For example, if we are testing for a specific pattern in the data, the surrogate data should not contain that pattern. This means, that the choise of surrogate data depends on the hypothesis being tested. Furthermore, it can depend on how phase angles are extracted from the data, as different methods for extracting phase angles can lead to different distributions of phase angles.