Statistically Significant Shortcuts in Statistics: Simplifying Complex Concepts
In this informative presentation by Milo Schield, shortcut formulas for statistical significance are explored to make understanding of key statistical ideas more manageable. Various shortcuts for proportions, Chi-squared tests, correlations, relative risk, and t-tests are discussed, aiming to enhance the ease of statistical analysis. These shortcuts offer efficient ways to determine statistical significance in different scenarios, accompanied by concrete examples and practical applications.
Uploaded on Oct 04, 2024 | 0 Views
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
V0C 1 2015 Schield SS Shortcuts Statistically-Significant Shortcuts by Milo Schield StatChat Feb 24, 2015 Slides at: www.StatLit.org/pdf/ 2015-Schield-StatChat-Slides.pdf
V0C 2 2015 Schield SS Shortcuts Background & Goal Statistical significanceis one of statistics big ideas. For Z-scores, statistical significance is a single value. For Chi-squared and the student-T, it is a function. For correlation and relative risk, its a complex function. We need to focus on big ideas in random sampling. Goal: To create shortcut formulas for statistical significance that are sufficient and memorable.
V0C 3 2015 Schield SS Shortcuts #1: Proportions Shortcut (SS) If |p2 - p1| > 1/Sqrt(n), then that difference is statistically significant Q. Has anyone seen this shortcut? Where? Yes! Seeing Through Statistics by Jessica Utts. Q. Anywhere else?
V0C 4 2015 Schield SS Shortcuts Chi-Squared 2(df+1) Chi-Squared Shortcut Statistically-Significant 20 Chi-squared > 2(DF+1) Chi-squared 15 10 Actual Cutoffs 5 0 1 3 5 7 9 Degrees of Freedom Has anyone seen this shortcut anywhere?
V0C 5 2015 Schield SS Shortcuts Shortcut Margin of Error for Correlation: 2/Sqrt(N) Correlation Shortcut (S/S) 0.6 Model (2 tail): r > 2/Sqrt(N) for #Pairs > 10 r > 2/Sqrt(N-1) for #Pairs > 4 0.5 0.4 0.3 Solid is the Model Dashed is Actual 0.2 Error < 5% 0.1 0 50 100 Sample Size (# of Pairs) 150 200 250 300 Has anyone seen this shortcut anywhere?
V0C 6 2015 Schield SS Shortcuts Relative-Risk Shortcut (SS) Consider two groups each of size n. Relative Risk: RR = p2/p1 RR>1 is statistically significant if RR-1 = 2/sqrt(k1) where k1 = n*p1 >4 Has anyone seen this shortcut anywhere?
V0C 7 2015 Schield SS Shortcuts T-Z: Actual vs. Model Shortcut for 2-tail T 4.0 3.5 3.0 Model: T > 1.645 + 2/(df-1) T 2.5 2.0 Actual 1.5 2 4 6 8 10 Degrees of Freedom Has anyone seen this shortcut anywhere?
V0C 8 2015 Schield SS Shortcuts Question What are the costs in teaching these sufficient shortcuts for statistical significance? 1. |p2-p1| > 1/sqrt(n) 2. Chi-squared: 2 > 2(df+1) 3. Correlation: r > 2/sqrt(n-1) for n > 4 4. RRisk > 1+ 2/sqrt(k1): k1=n*p1, p1<p2 5. t-stat (2-tail): t > 1.645 + 2/sqrt(df-1)
