Università della Svizzera italiana

Infinitesimal robustness for diffusions

La Vecchia, Davide ; Trojani, Fabio

In: Journal of the american statistical association, 2010, vol. 105, no. 490, p. 703–712

We develop infinitesimally robust statistical procedures for the general diffusion processes. We first prove the existence and uniqueness of the times-series influence function of conditionally unbiased M-estimators for ergodic and stationary diffusions, under weak conditions on the (martingale) estimating function used. We then characterize the robustness of M-estimators for diffusions and...

Università della Svizzera italiana

Robust inference with GMM estimators

Ronchetti, Elvezio ; Trojani, Fabio

In: Journal of Econometrics, 2001, vol. 101, no. 1, p. 37-69

The local robustness properties of Generalized Method of Moments (GMM) estimators and of a broad class of GMM based tests are investigated in a unified framework. GMM statistics are shown to have bounded influence if and only if the function defining the orthogonality restrictions imposed on the underlying model is bounded. Since in many applications this function is unbounded, it is useful to...

Università della Svizzera italiana

Optimal conditionally unbiased bounded-influence inference in dynamic location and scale models

Mancini, Loriano ; Ronchetti, Elvezio ; Trojani, Fabio

In: Journal of the American Statistical Association, 2005, vol. 100, no. 470, p. 628-641

This paper studies the local robustness of estimators and tests for the conditional location and scale parameters in a strictly stationary time series model. We first derive optimal bounded-influence estimators for such settings under a conditionally Gaussian reference model. Based on these results, optimal bounded-influence versions of the classical likelihood-based tests for parametric...