>Maybe you didn't notice that I very carefully set it up to compare two 0.045's with a 0.06 and an 0.01. (I.e. the combined probability is less than two 0.045's.)<
I noticed that, and it doesn’t change the fact that an arbitrary line has to be drawn somewhere. If the line has been drawn at two trials of <0.05 each, then 0.06 and 0.01 is close but no cigar.
I don’t see any point in continuing this thread. You can have the last word.
“The efficient-market hypothesis may be the foremost piece of B.S. ever promulgated in any area of human knowledge!”