FIVE MOST IMPORTANT PUBLICATIONS

Márta Pintér

- On the Rate of Convergence of Error Estimates for the
Partitioning Classification Rule,
*Theoretical Computer Science*, 284(1), pp. 181-196, 2002. - Prediction from randomly right censored data,
*Journal of Multivariate Analysis*, 80, pp. 73-100, 2002. (with Michael Kohler and Kinga Máthé) *Efficient Algorithms*, chapter of a textbook on Formal Methods in Computer Science, editor A. Pataricza, to appear (with Lajos Rónyai)- Scale-sensitive dimensions and skeleton estimates for classification,
*Discrete Applied Mathematics*, 85, pp. 37-61, 1998. (with Gábor Lugosi)

/earlier version: A data-dependent skeleton estimate and a scale-sensitive dimension for classification,*Technical Report, Pompeu Fabra University*, Dec. 1996./ - On the asymptotic normality of the resubstitution error estimate
for partitioning classification rule,
In
*Advances in Data Science and Classification*, A. Rizza, M. Vichi, H. H. Bock (Eds.), Springer, pp. 197-204, 1998. (with László Györfi)