|
PureBytes Links
Trading Reference Links
|
Let's think about this a bit. I can flip a coin and make predictions.
At least half will be right in *real time*. If you allow me to select
*past* predictions I have made, I can make it look like I get 90%
right. :-)
To be a fair test, the predictions would have to be made ahead of
time, and there must be enough predictions to see if the person is
doing better than flipping a coin. The *bare minimum* would be 30-60
predictions in total to get a hint of significance.
The posts stating "there, see, I made *a* past prediction correctly"
are statistical nonsense. :-) Let's try to think just a bit
statistically, please.
ztrader
To unsubscribe from this group, send an email to:
realtraders-unsubscribe@xxxxxxxxxxxxxxx
Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/
|