As an increasing amount of statistical data is published as RDF, intuitive ways of satisfying information needs and getting new insights out of this type of data becomes increasingly important. Question answering systems provide intuitive access to data by translating natural language queries into SPARQL, which is the native query language of RDF knowledge bases. Existing approaches, however, perform poorly on statistical data because of the different structure. Based on a question corpus compiled in previous work, we created a benchmark for evaluating statistical questions answering systems and to stimulate further research. Building upon a previously established algorithm outline, we detail a Question Anwering algorithm for statistical Linked Data, which covers a wide range of question types, evaluate it using the benchmark and discuss future challenges in this field. To our knowledge, this is the first question answering approach for statistical RDF data and could open up a new research area.