Re: LOS (again)
Posted: Thu Nov 29, 2012 7:00 pm
H.G.,hgm wrote:Cutting short a match erodes your confidence. For example, when you test until the the score exceeds the the 1.96 STD interval around 50%, and abort the test immediately when it does this, you can only have 90% confidence that they were indeed of different strength. While normally 1.96 STD corresponds to a confidence of 95%, when it happens over a predetermined number of games (without paying attention to intermediate results). The possibility to stop early exactly doubles the probability that you will accept a fluke (from 5% to 10%), because you don't give it the opportunity to correct itself by an average result in the remainder of the test.
You use the terminology, "doubles the probability that you will accept a fluke."
Is there a simple way to calculate or approximate a modified error margin?
I am mathematically challenged but this would be useful to know. Here is an example that may help:
For example if the error margin of +/- 8 ELO is reported but you are exactly half way through the test you intent to run, could you pretend the error margin was 16 or perhaps 11.3137 or some other value? The 11.3137 value is the error margin multiplied by the square root of 1 / (1/2), which seems like a good guess to me if this is valid at all.
Don