100m Predictor
Predict your 100m time based on your block 30 and fly 10 times. Wind and reaction time are optional. The dataset used to train this model is men's 100m times ranging from 9.58s to slightly above 11s. If your times are outside of this range, predictions will be less accurate.
Methodology
This predictor is based on a log-level regression model trained on >800 professionally timed men's 100m races with 10m split data, which is available here.
The data was cleaned to remove Paralympic athletes and races where the athlete was obviously injured. Reaction time was removed from the data to isolate the effects of block 30 and fly 10 times. For races that didn't have reaction time available, the average reaction time (0.149s) for the dataset was used.
Fly 10 times were converted to velocities (m/s) prior to training the model as I suspected velocity would be more predictive. A log-level regression was chosen as the data didn't look linear, and because the log-level model produced a significantly better fit than a linear fw model. The trained model has an R² value of 0.964 and a mean squared error of 0.004.
Wind correction is based on Moniat, Fabius, and Emanuel (2018).