Originally Posted by
SeenItAll
Not at all. Statistics is about accepting or rejecting hypotheses that are made in advance of knowing the data. Claimed confirmation of a hypothesis that was generated after seeing the data is just cherry-picking. Given there are so many parameters to cherry-pick from, it is sure that you can find some that will all align between the incidents -- but this has no probative value as statistical inference. Indeed, each of these crashes is so different from one another in terms of the stage of flight, that I doubt any similarity will be found. And note that trim problems generally don't cause an immediate nosedive into the ground. You generally see the flight crew struggling with the imbalances for some minutes (or at least multiple seconds) before control is finally lost. That doesn't seem to be the case with the altitude profile shown here.
Not at all. Indeed the p value (if one is to use the dreaded p value in order to accept hypothesis) should be adjusted and fairly small. In essence, we could go in blind over all data available, but adjust the p value according to degrees of freedom available to avoid false positives.
Now given that the flight data sample is huge (say, all flights in the past 3 years), the probability of false positive is actually small anyway. So is there a statistically significant difference between # of flights that did/didn't crash in the group of flights which are Boeing in low visibility on final/approach?
And btw, picking a hypothesis up front makes no difference. Imagine 20 different statisticians would decide to test a hypothesis over flight data, each unbeknown and independent of each other. Each would choose a different parameter, but p of only 0.05. Those results would not be different, but there would indeed likely be at least 1 false positive due to stupidly large p value (0.05 is really astronomical when you think about it).