Runalyze

This should be a useful feature to add to runalyze: predict marathon performance from average weekly mileage (in the eight weeks leading up to a race), and the average training pace.

Details in https://rua.ua.es/dspace/bitstream/1004 ... 11-520.pdf

Sorry, but reading this sentence is enough for me to ignore this study:

This study collected training data of twenty-two runners (twenty-one males, one female), ...

In addition, this study did not look at heart rate at all. You can be sure that our estimations based on the effective VO2max are more accurate than this simple regression.

Indeed it's limited as usual for these studies. I wonder if the equation could be verified against the runalyze user data? It would be interesting to see if it can still reproduce the 4 minute error that they got on their limited data.

> You can be sure that our estimations based on the effective VO2max are more accurate

Is there any quantification of the accuracy, e.g. "predicts the performance to 2 minutes margin"?

> In addition, this study did not look at heart rate at all

Perhaps it can be still useful to users that don't record heart rate data during run, or maybe use the less accurate optical sensors.