Statistica Sinica 24 (2014), 1613-1631
Abstract: We propose to use a constrained local polynomial regression to estimate the unknown parameters in ordinary differential equation models with a goal of improving the smoothing-based two-stage pseudo-least squares estimate. The equation constraints are derived from the differential equation model and are incorporated into the local polynomial regression in order to estimate the unknown parameters in the differential equation model. We also derive the asymptotic bias and variance of the proposed estimator. Our simulation studies show that our estimator is clearly better than the pseudo-least squares estimator in estimation accuracy with a small price of computational cost. An application to immune cell kinetics and trafficking for influenza infection further illustrates the benefits of the proposed method.
Key words and phrases: Constrained optimization, local polynomial smoothing, ordinary differential equation.