Correlation

Correlation is ​a statistical measure ranging from +1.0 to -1.0, represented by 'r', that indicates how strongly two or more variables are related and whether that relationship is positive or negative.

A positive correlation (+1.0 to 0) indicates that the two variables move in the same direction, e.g., the variable of high school exam results might have a positive correlation with the variable of university exam results. A positive correlation of 0.97 is shown below:

Graphic created with Interpreting Correlations tool (Magnusson, n.d.).

A negative correlation (0 to -1.0) indicates that the variables move in opposite directions, e.g., years spent driving might have a negative correlation with amount of driving accidents. A negative correlation of -0.97 is shown below:

Graphic created with Interpreting Correlations tool (Magnusson, n.d.).

The strength of a correlation (how closely the two variables' are linked) is indicated by the value of 'r'. If 'r' is +1 or -1, very is a very strong correlation. If 'r' is 0, there is no correlation:

 

Graphic created with Interpreting Correlations tool (Magnusson, n.d.).

It's important to note that correlation does not equal causation. While in example of a positive correlation between high school and university exam results above might suggest a causation, there are a range of factors that need to be addressed. For example, hours spent studying, family background, life goals, amount of time spent socializing, or intellect might all play a part in causing the correlation. 

Correlation can show the strength and direction of a relationship between variables. But it's up to controlled experiments and well designed research studies to show causation.

Resources

Guide

Australian Bureau of Statistics - Correlation and Causation: this overview  of correlation and causation is easy to follow and explains the major features of correlation and its difference from causation.

Interpreting Correlations: An interactive visualization: this tool allows users to gain an understanding of negative and positive correlations though the use of an interactive scatter plot representing the user-controlled strength and polarity of a correlation value.

Sources

Magnusson, K. (n.d.). 'Interpreting Correlations: an interactive visualization' [webpage]. Retrieved from http://rpsychologist.com/d3/correlation/

 

This page is a stub (a minimal version of a page). You can help expand it. Click on Contribute Content or Contact Us to suggest additional resources, share your experience using the option, or volunteer to expand the description.

Updated: 19th August 2014 - 11:29am
This Option is useful for:
A special thanks to this page's contributors
Author
BetterEvaluation Website and Engagement Coordinator, BetterEvaluation and ANZSOG.
Melbourne, Australia.

Comments

There are currently no comments. Be the first to comment on this page!

Add new comment

Login Login and comment as BetterEvaluation member or simply fill out the fields below.