Statistical analysis is a powerful tool to apply when evaluating the perfor
mance of computer implementations of algorithms and heuristics. Yet many co
mputational studies in the literature do not use this tool to maximum effec
tiveness. This paper examines the types of data that arise in computational
comparisons and presents appropriate techniques for analyzing such data se
ts. Case studies of computational tests from the open literature are re-eva
luated using the proposed methods in order to illustrate the value of stati
stical analysis for gaining insight into the behavior of the tested algorit
hms.