AbstractIn many situations where the interest lies in identifying clusters one might expect that notall available variables carry information about these groups. Furthermore, data quality (e.g.outliers or missing entries) might present a serious and sometimes hard-to-assess problemfor large and complex datasets. In this paper we show that a small proportion of atypicalobservations might have serious adverse e ects on the solutions found by the sparse clusteringalgorithm of Witten and Tibshirani (2010). We propose a robusti cation of their sparse K-means algorithm based on the trimmed K-means algorithm of Cuesta-Albertos et al. (1997).Our proposal is also able to handle datasets with missing values. We illustrate the use of ourmethod on microarray data for cancer patients where we are able to identify strong biologicalclusters with a much reduced number of genes. Our simulation studies show that, when thereare outliers in the data, our robust sparse K-means algorithm performs better than othercompeting methods both in terms of the selection of features and also the identi ed clusters.This robust sparse K-means algorithm is implemented in the R package RSKC which is publiclyavailable from the CRAN repository.