Common use of Select Best-Fit Model for Subject Monitored Year Clause in Contracts

Select Best-Fit Model for Subject Monitored Year. During each Harvest-Monitored Year, a best fit model (Initial Model) will be developed using Akaike’s Information Criterion (▇▇▇▇▇▇▇ and ▇▇▇▇▇▇▇▇, 2002) and based on only the subject year’s harvest-monitoring results. The model will estimate YL (dependent variable) at POFU from TNHB65, and Area Served (independent variables). The model that provides best performance while avoiding unacceptable anomalies will be selected. 3.2.14.4.1. In general, a monotonically increasing relationship avoids Anomaly A (prediction of constant non-zero YL or increasing YL with decreasing TNHB65 less than 400 hours), and Anomaly B (prediction of decreasing YL with increasing TNHB65 greater than 400 hours). 3.2.14.4.1.1. If an Initial Model exhibits Anomaly A, the model will be adjusted such that no additional increase in YL occurs with incremental reduction in TNHB65. This will be achieved by setting the slope equal to zero for all points below the TNHB65 at which Anomaly A occurs, to the lowest observed TNHB65. Note that this interval may vary continuously across the range of Area Served, based on YL response to this variable. 3.2.14.4.1.2. An Initial Model exhibiting Anomaly B will not be adopted and the next best fit model will be evaluated for acceptance. 3.2.14.4.2. If R2≥0.50, the Initial Model will be retained and the analyses continued as described in Section 6.3. If R2<0.50, then the regression development will continue as described in Section 3.2.14.5.