{"id":573,"date":"2009-09-14T07:37:12","date_gmt":"2009-09-14T14:37:12","guid":{"rendered":"http:\/\/www.questionpro.com\/?p=573"},"modified":"2023-08-23T06:08:47","modified_gmt":"2023-08-23T06:08:47","slug":"correlation-isnt-causality","status":"publish","type":"post","link":"https:\/\/www.questionpro.com\/blog\/correlation-isnt-causality\/","title":{"rendered":"Correlation isn’t Causality"},"content":{"rendered":"
\n
\"Business<\/figure><\/div>\n\n\n

I came across a published report recently that made me wonder why people persist in reporting that there is a causal research<\/a> relationship when the data doesn\u2019t justify the assertion. Actually, the reasons aren\u2019t all that hard to figure out. Usually, it\u2019s because the relationship seems obvious, and sometimes it is when the person writing the report has a bias they wish to share.<\/p>\n\n\n\n

But I\u2019m getting ahead of myself.  Let\u2019s start with a couple of definitions:<\/p>\n\n\n\n

A correlation <\/strong>is simply the test of the relationship between two variables.  Pearson\u2019s coefficient, commonly used to test linear relationships between scale variables, will be 1 (or -1) for perfect correlation.  Other coefficients are used for different types of variables. Tools such as SPSS that calculate correlation coefficients generally provide some guidance as to whether the relationship is significant \u2013 the strength of the correlation.<\/p>\n\n\n\n

What correlation tells you is given the value of the one variable, what to expect for the value of another variable.<\/p>\n\n\n\n

Causality<\/strong>, on the other hand, is a statement that if the value of one variable is changed then the value of the second variable will change accordingly.  Correlation is necessary, but not sufficient, for a cause-and-effect relationship.<\/p>\n\n\n\n

It is easy to find good examples of correlations where assuming a causal relationship would be absurd. The Wikipedia article on the topic<\/a> shows a chart of Mexican lemons imported from Mexico to the US plotted against total US highway fatalities. This is an example of a coincidental correlation.<\/p>\n\n\n\n

Another type of misinterpretation occurs when the order of the cause and effect is reversed. Daniel Huff\u2019s excellent \u201cHow To Lie With Statistics\u201d<\/a> discusses the relationship between smoking and college grades.  Apparently the results were used to promote the idea that giving up smoking would lead to improved grades.  But it is equally feasible that lower grades caused students to take up smoking.<\/p>\n\n\n\n\t

\n\t\t
\n\t\t\t
\n\t\t\t\tCreate memorable experiences based on real-time data, insights and advanced analysis.<\/span>\n\t\t\t\tRequest Demo<\/a>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n\t
\n\t\t
\n\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t\t\t