This paper presents a robust class of estimators for the parameters of a de
terministic signal in impulsive noise. The proposed technique has the struc
ture of the maximum likelihood estimator (MLE) but has an extra degree of f
reedom: the choice of a nonlinear function (which is different from the sco
re function suggested by the MLE) that can be adjusted to improve robustnes
s, The effect of this nonlinear function is studied analytically via an asy
mptotic performance analysis. We investigate the covariance of the estimate
s and the loss of efficiency induced by nonoptimal choices of the nonlinear
function, giving special attention to the case of cc-stable noise. Finally
, we apply the theoretical results to the problem of estimating parameters
of a sinusoidal signal in impulsive noise.