Relationship | Method | External RMSE* | Internal RMSE | AIC | Coverage (%) | AW | Coverage MCSE |
Absolute training load | |||||||
Constant | Rolling average | 4.85 | 0.113547 | 1422.92 | 34.7 | 5.17478 | 0.90 |
EWMA | 4.77 | 0.113548 | 1423.42 | 36.3 | 5.17179 | 0.91 | |
REDI | 5.53 | 0.113557 | 1424.10 | 20.3 | 3.40114 | 0.74 | |
DLNM | 1.44 | 0.112434 | 1317.15 | 34.8 | 2.05600 | 0.95 | |
Decay | Rolling average | 5.38 | 0.113590 | 1421.80 | 30.2 | 5.16930 | 0.87 |
EWMA | 5.17 | 0.113587 | 1421.85 | 31.8 | 5.12554 | 0.88 | |
REDI | 6.21 | 0.113605 | 1423.80 | 18.7 | 3.42154 | 0.71 | |
DLNM | 1.55 | 0.112245 | 1295.30 | 32.4 | 2.07977 | 0.93 | |
Exponential decay | Rolling average | 2.13 | 0.113599 | 1424.65 | 85.0 | 5.54695 | 0.58 |
EWMA | 1.88 | 0.113588 | 1423.86 | 85.1 | 5.37141 | 0.61 | |
REDI | 1.97 | 0.113603 | 1425.00 | 74.2 | 3.69208 | 0.64 | |
DLNM | 0.76 | 0.113368 | 1407.08 | 81.6 | 2.02633 | 0.65 | |
Relative training load (%Δ)† | |||||||
Constant | ACWR | 0.113643 | 1426.16 | ||||
Week-to-week %Δ | 0.113646 | 1426.40 | |||||
DLNM %Δ | 0.113627 | 1389.28 | |||||
Decay | ACWR | 0.113615 | 1424.73 | ||||
Week-to-week %Δ | 0.113617 | 1425.12 | |||||
DLNM %Δ | 0.113553 | 1383.52 | |||||
Exponential decay | ACWR | 0.113565 | 1423.33 | ||||
Week-to-week %Δ | 0.113566 | 1423.27 | |||||
DLNM %Δ | 0.113700 | 1401.39 |
*Monte Carlo SE for RMSE was <0.001 for all simulations. The scale of the RMSE depends on the scale of the coefficients, and it is therefore only interpretable by comparing values in the same analysis – the values cannot be interpreted in isolation.
†Due to differences in scale between methods and simulation for relative training load, external RMSE, coverage, and AW could not be calculated in a comparable manner.
ACWR, acute:chronic workload ratio; AIC, Akaike’s information criterion; AW, average width of 95% CIs; Coverage, coverage of 95% CIs; DLNM, distributed lag non-linear mode; EWMA, exponentially weighted moving average; MCSE, Monte Carlo Standard Error; REDI, robust exponential decreasing index; RMSE, root-mean-squared error.