It seems that the Shape graph at the top is capped to the max of the ATL curve.
My CTL curve is peaking above the ATL peak and it gets cropped, i.e. it's not possible to see it's peak.
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 VO...
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.