SA-EP8-The Friedman Test [ ENGLISH ] cover art

SA-EP8-The Friedman Test [ ENGLISH ]

SA-EP8-The Friedman Test [ ENGLISH ]

Listen for free

View show details

About this listen

 🎙️ Episode Title: The Friedman Test – Ranking Repeated Measures with Confidence 🔍 Episode Description: Welcome to another episode of “Pal Talk – Statistics”, the show where complex concepts are simplified with clarity and confidence! In today’s episode, we dive into a non-parametric test that’s perfect for repeated measures or matched group comparisons — the Friedman Test. Ever wondered how to compare three or more related groups without assuming normality? That’s where the Friedman Test steps in — a solid alternative to repeated-measures ANOVA, especially when your data doesn't play by the normal distribution rules. In this episode, we explore: ✅ What is the Friedman Test? The Friedman Test is a non-parametric test used when you want to compare three or more related or matched groups — such as when the same participants are tested under different conditions or over time. It works on ranked data, making it robust against outliers and non-normal distributions. ✅ When to Use It? You’ll find the Friedman Test incredibly useful when: You have repeated observations on the same subjects Your data is ordinal, not normally distributed, or contains outliers You want an alternative to repeated-measures ANOVA ✅ How the Test Works – Step-by-Step Set up your null and alternative hypotheses Rank the values within each row (subject) Calculate the Friedman test statistic Compare the result to the chi-square distribution to determine significance We walk you through each step with an easy, real-world example — such as measuring reaction times of students across three different study techniques. ✅ Assumptions of the Friedman Test We cover the essential assumptions: Data must come from related samples (repeated or matched groups) Ordinal or continuous data Same number of observations per group ✅ What Happens After a Significant Result? If your Friedman Test result is significant, what’s next? We discuss post hoc analysis, like the Wilcoxon Signed-Rank Test with Bonferroni correction, to pinpoint where differences lie. ✅ Real-World Applications Medical trials comparing pain levels across treatments in the same patients Comparing productivity of employees across different work environments Measuring student satisfaction after three different learning modules ✅ Friedman Test vs Repeated-Measures ANOVA We compare both methods and help you understand when to use one over the other — especially when your data doesn’t meet parametric assumptions. 👥 Hosts: Speaker 1 (Male): A statistician who brings research techniques to life. Speaker 2 (Female): A curious learner making sure every listener stays on track. 🎧 Whether you're in psychology, medicine, education, or behavioral science — this episode will empower you to analyze related group comparisons confidently, even when your data is far from perfect. 📌 Coming Soon on “Pal Talk – Statistics” Cochran’s Q Test Wilcoxon Signed-Rank Test Non-Parametric Effect Sizes Designing Experiments with Repeated Measures 💡 Enjoying the series? Subscribe, share, and rate “Pal Talk – Statistics” to help us grow a global community of curious, data-driven minds. 🎓 Pal Talk – Where Data Talks.
No reviews yet
In the spirit of reconciliation, Audible acknowledges the Traditional Custodians of country throughout Australia and their connections to land, sea and community. We pay our respect to their elders past and present and extend that respect to all Aboriginal and Torres Strait Islander peoples today.