Measurement error is an inescapable reality in most domains of research. Incidental variation in experimental setting, participant motivation and mood are among the multitude of factors that introduce error into measurement. I created a pedagogic spreadsheet that demonstrates the attenuation of correlation resulting from measurement error. The spreadsheet allows students to explore the sensitivity of the Spearman correction for attenuation of correlation to violation of assumptions. The spreadsheet demonstrates that the Spearman correction may not be advisable under certain circumstances. Some students conflate measurement error with sampling error. To clarify this misunderstanding, the spreadsheet uses a Monte Carlo simulation to demonstrate the difference between sampling error and measurement error and how they interact in practice.
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Fisher, Christopher R.
A Pedagogic Demonstration of Attenuation of Correlation Due to Measurement Error,
Spreadsheets in Education (eJSiE):
1, Article 4.
Available at: http://epublications.bond.edu.au/ejsie/vol7/iss1/4