Sharp observation from Gary Smith, discussing the perils of letting stats lead you around by the nose:
Our distant ancestors benefitted from noticing that elephants could lead them to water and that wildebeest stampedes might warn them of predators. The best pattern spotters were more likely to survive and reproduce, passing on their pattern-recognition skills to future generations. The problem today is that instead of observing elephants trudging toward water holes and wildebeest fleeing lions, we are inundated by complex data for stock prices, election polls, tweeted words, and pretty much anything that can be measured. We are hard-wired to look for patterns and tempted to believe that the patterns we discover are meaningful. But the data deluge has made the number of bogus coincidences waiting to be discovered so large, relative to the number of real causal relationships, that it is almost certain that a randomly discovered pattern is just a statistical coincidence.
Well, it wasn’t our Savannah Sabertooth ancestors. It was our Old Stacks ancestors.
The overflow of instantly accessible and readable and calculable data is only 20 years old. Before 2000, a researcher had to stomp up and down narrow stairways in the Old Stacks of his university library and hand-copy** information from heavy volumes of past journals.
Smith calls the problem Hypothesizing After Results are Known, or HARK.
The real driving force of this inverse causation is NOT instant info. Grants are the driver. You really do have to KNOW the results of the experiment before you start applying for the grant. You have to perform small trial runs, or figure most of the stats, before you can get the budget for grad assistants and the new lab toys you “need”. This inverse causation was operating for many years before instant info.
The deeper and broader problem is that the official “scientific method” has no correlative or causative relationship with actual science. Actual science happens all the time in every living thing and every organelle within every cell. Sensory input gives us a frustration or a need for improvement, and we perform experiments, using negative feedback to smoothly narrow down the gap between actual output and desired goal. There is no hypothesis anywhere in this process, only an overriding PURPOSE of survival and improvement and enjoyment.
LIFE IS PURPOSE.
= = = = =
** Hand-copy: Libraries often prohibited Xeroxing from journals because of copyright rules. So a good researcher carried another tool beginning with X, and used it frequently and precisely.