There is no dispute that rigorously conducted experiments or randomized controlled trials of sufficient statistical power are the gold standard research design to detect important beneficial or harmful effects of existing or new interventions. In practice, however, there are a number of situations in which random allocation is not possible for either ethical or logistic reasons. The alternative in these situations is to use observational methods, in which the outcome of care patients receive as part of their natural treatment is studied. Before drawing inferences from the outcomes of groups of intensive care patients receiving different interventions, the confounding factors (ie. the characteristics that could affect both their selection and risk for a particular outcome) have to be taken into account. This is the purpose of measurement and adjustment for case mix. Case mix measurement and adjustment is, therefore, a methodologic tool for approximating randomization when randomization is not possible, The ability to make inferences from observed differences in outcomes among patient groups hinges on the ability to measure and adjust for case mix. However, there are a number of theoretical and practical problems of measuring case mix in intensive care. This article selectively reviews some of the studies published during the past year that used the case mix measurement known as the Acute Physiology And Chronic Health Evaluation (APACHE) II.