Separable Nonlinear Least-Squares Parameter Estimation for Complex Dynamic Systems
Table 2
MSE ratios for linear parameters (large samples).
Prior
Low noise
High noise
SIR
LV
GMA
FHN
SIR
LV
GMA
FHN
Low
12.0
9.6
3.9
3.9
3.8
3.2
2.2
2.2
Medium
4.1
4.3
2.8
1.9
1.6
1.6
1.6
1.3
High
1.0
2.2
0.7
2.3
0.7
1.2
0.5
1.5
The sample size is for the GMA and Lotka–Volterra models; for the FitzHugh–Nagumo system; and for the SIR model. The noise levels are and . For an interpretation of the results, see Table 1. There is an increased advantage of SLS over NLS in comparison to Table 1.