Asymptotic criteria for designs in nonlinear regression with model errors

Rok, strany: 2006, 543 - 553

We derive bounds for the design optimality criteria under the assumption that the supposed regression model $y(x_k) =η(x_k,θ)+ε_k$, $k=1,2,…$, does not correspond to the true one. The investigation is based on the asymptotic properties of the LSE of $θ$, and full proofs of these properties are presented under the assumption that the sequence of design points $\{x_k\}_k=1^∞ $ is randomly sampled according to a design measure $ξ $. The bounds and the asymptotic properties are related to the intrinsic measure of nonlinearity of the model.

ISO 690:

Pázman, A., Pronzato, L. 2006. Asymptotic criteria for designs in nonlinear regression with model errors. In Mathematica Slovaca, vol. 56, no.5, pp. 543-553. 0139-9918.

APA:

Pázman, A., Pronzato, L. (2006). Asymptotic criteria for designs in nonlinear regression with model errors. Mathematica Slovaca, 56(5), 543-553. 0139-9918.