Subject: Re: Timing: recent highs
If the optimal parameter values have changed, they were just tuned for the data. Which means they are useless going forward.

Your conclusion does not follow from your antecedent. It's certainly possible that the "99-day rule" becomes the "100-day rule" some years later, when optimized on additional data, and that both rules are useful.

The "mean January temperature" changes each year, based on additional data. But knowing the mean January temperature to date is not useless - it can guide me when getting dressed.


John