What Is Statistical Significance, in Plain Words

Significance in five lines

Statistical significance, in plain words, is the answer to one question: whether an average is a real thing or the kind of number chance throws up. It needs two numbers: the average, and how much that average itself would wobble from one sample to the next. The wobble is the spread of a single trade divided by the square root of how many trades there are. A result is called significant when the average sits several wobbles away from zero, not one wobble and not half of one. In the example, 135 trades of the plain 10:00 to 18:00 rule on the euro average plus 1.1 pips, where a pip is the fourth decimal place of the price, with a wobble of 2.4: the average is inside its own wobble, and nothing can be said yet.

Bathroom scales that wobble

Picture a pair of bathroom scales with a needle that shakes. Stand on them once and read a kilo above last week, and you have learned nothing, because the needle shakes by two kilos either way. Stand on them a hundred times and average, and the shake averages down, slowly, by the square root of the count: a hundred readings shrink it tenfold, not a hundredfold. The reading on the dial is the example rule's average trade, 1.1 pips, and the shake is its wobble, 2.4; the reading is inside the shake, which is what not significant means in plain words.

This paper is locked