Quote:
Originally Posted by zinner
Isn't that exactly what statistical significance is? I would change casual relationship to correlation however since I am not familiar with casual relationship as a scientific term (maybe it is?).
|
No, it's not. In research work there is a mathematical definition of statistical significance. In layman's terms it could be thought of presented as proof that a valid correlation does truly exist (as opposed to the numbers being what they are by some coincidence).
It does not do anything to identify the root CAUSE of why the numbers are the way they are.
Let's say someone comes up with a study that illustrates a correlation between brain surgeons and ownership of homes in excess of 6000 square feet. Assuming the numbers are right, statistical significance might reassure us that the connection between brain surgeons and large homes does in fact exist. But it doesn't tell us anything about WHY that connection exists.
I chose a silly/simple example for ease of explanation here, but in this case most people would assume the CAUSE of the connection is simply higher income = potentially larger homes. But what if someone comes along and shows a statistically significant correlation between another high-income profession and smaller homes, or the statistical significance illustrated above simply doesn't hold up for other professions of same income level? Then one might theorize there is another cause, like maybe brain surgeons work in tight spaces with their hands and thus feel a psychological need for more personal space in their living areas?
In other words that the fact a relationship exists can be proven does not prove WHY that relationship exists.