Within each subregion elevation was the lead predictor variable influencing probabilities of burning, and its significant PH ratio indicated the effect of elevation was maintained through time.
Then, Algorithm 3.1 is used to obtain the WL fixed-lead prediction error p τ (tk+10|t k ) which is compared with the SL fixed-lead prediction error p ¯ τ ( t k + 10 | t k ) in Figure 2. As could be expected, this figure shows that the WL fixed-lead predictor presents a better behavior than the SL fixed-lead predictor.
The results obtained are displayed in Figure 1 which shows that, not only the WL fixed-lead predictor presents a better behavior than the SL fixed-lead predictor but also the difference between both errors (in the mean square sense) increases with τ, and hence, the WL technique becomes more effective.
Again, the improved precision attained with the WL fixed-lead predictor with respect to the SL fixed-lead predictor is observed as τ increases.
On the basis of the set of observations {y t1), y t2),..., y t100)}, we consider the problem of computing the fixed-lead predictor ŝ tk+10|t k ).
Moreover, the cross-correlation matrix between s(t i ) and v(t i ) is of the form (7) with D(t i ) = F(t i ) = [t i /25, t i /25]T and C ( t i ) = E ( t i ) = [ e - 1 / 2 t i 2, e - 1 / 2 t i 2 ] T. In this example, we consider the problem of computing the fixed-lead predictor ŝ tk+10|t k ).
As a measure for comparing the performance of the WL and SL fixed-lead predictors we use the one defined in [6], the mean square of the difference between both errors, for ∑ = ( 2 τ τ 2 ).
Figure 1 Performance of fixed-lead predictors.
Second, although some might argue that concurrent blood lead tests are not an adequate biomarker of a child's lifetime exposure, recent studies indicate that concurrent blood lead level is a stronger predictor of lead-associated IQ decrements than blood lead measured during early childhood (Chen et al. 2005; Lanphear et al. 2005).
Bone lead remained a significant predictor of blood lead after adjusting for covariates in a final multivariate regression model.
