Identifying and avoiding common misinterpretations in using statistics
-
Updated
Jul 2, 2018 - Jupyter Notebook
Identifying and avoiding common misinterpretations in using statistics
This code is an implementation of the A statistic, otherwise known as the probability of superiority, in SAS. The A statistic is a non-parametric form of the common language effect-size. Both it and its counterpart, RProbSup, are available at the website linked below.
A Shiny R web application to estimate differences in diagnostic efficiency based on differences between single-condition cases.
This script computes two indices of effect size for pairwise comparisons based on the Mann Whitney U statistic.
Two sample data analysis method that tests for negligible and meaningful effect sizes (through difference in means)
Effect-Size-Based Meta-Analysis for Multi-Dataset Evaluation of RecSys Experiments
Computation and visualization of standardized mean differences from simulated data
Social studies lab dedicated to preferences between NA and EU in board games
More Meaningful Measurements: Effect Sizes and Confidence Intervals for Proportions using Python
Basic Analytical Statistics with Excel [Spreadsheets]
Estimation Approach to Statistical Inference [R Package]
Effect size measures
This repo is no longer being maintained. See this repo instead: https://github.com/hauselin/esconvert
Interpret effects and visualise uncertainty
Calculating robust effect sizes using bootstrap (resampling) technique in R.
Add a description, image, and links to the effect-size topic page so that developers can more easily learn about it.
To associate your repository with the effect-size topic, visit your repo's landing page and select "manage topics."