Correlation is not causation. Too often we make the leap from correlation to causation around time. Event A occurs, then Event B occurs. It\u2019s easy\u00a0to go from \u201cA happened just before B happened\u201d to \u201cA caused B.\u201d Case in point\u2014in a NYC black-out, many people thought they had caused the power outage by flipping a switch or using an appliance. While the correlation is true enough \u2013 these factors did co-occur \u2013 turning on a hair dryer is not a valid cause. What\u2019s missing is the mechanism of the cause\u2014the logic that describes how a purported cause actually caused the observed effect.<\/p>\n
But close correlation between the two actions is so seductive that we tend to jump to cause. You are close \u2013 you have found a pattern that might have some explanatory power. But you need to clarify the mechanism of the cause.<\/p>\n
In the power outage case, we can simply look at the logic of the situation: I\u2019ve used this same appliance at the same time of day every day for over two years without causing a blackout \u2013 how did today\u2019s incident cause the blackout when the other incidents did not? During root cause analysis, we hear this all the time \u2013 \u201cThere must be something about the new supplier of Compound K, because the day we switched to that our yields went down.\u201d And that\u2019s as far as it goes. But it needs to go farther.<\/p>\n
In a recent case involving a bio-pharma process that dropped in yield by 22%, almost overnight, just such a supplier change was present. \u201cIt\u2019s the new soy oil,\u201d they declared. \u201cIt must be.\u201d The decrease in production did correspond in time to the change in suppliers, but that\u2019s not enough. What is it about that new soy oil that\u2019s causing the drop in production? The key fact in that case related to when in the process the production dropped. Did it drop during the growth phase, when the bugs are multiplying? Did it happen in the production phase, when those fully-grown bugs are now producing antibodies?<\/p>\n
In this case, it was the growth phase that had dropped. After the growth phase, the process produced as much protein as expected, as a percentage of the fewer organisms from the growth phase. We asked, \u201cWhat about the soy oil aids in the growth of organisms?\u201d The answer was proteins \u2013 the higher the level of protein in the soy oil, the greater the production. Armed with this logic, we checked the protein levels of the old soy oil against the new soy oil. It turned out that the new oil had over 20% less protein, which provided the rationale for the change in suppliers being identified as the cause.<\/p>\n
Next time you hear someone positioning a correlation as a cause, ask about the mechanism \u2013 \u201cI can see that that these two things co-occur, but how does this change cause the specific deviation we are seeing?\u201d If you can answer that, you have a real cause you can test.<\/p>\n","protected":false},"excerpt":{"rendered":"
Correlation v Causation\u2014Avoid Jumping to Cause Correlation is not causation. Too often we make the leap from correlation to causation around time. Event A occurs, then Event B occurs. It\u2019s easy\u00a0to go from \u201cA happened just before B happened\u201d to \u201cA caused B.\u201d Case in point\u2014in a NYC black-out, many people thought they had caused […]<\/p>\n","protected":false},"author":5,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[1],"tags":[],"ppma_author":[163],"class_list":["post-24338","post","type-post","status-publish","format-standard","hentry","category-other"],"acf":[],"yoast_head":"\n