Abstract. -It has been suggested recently that new quantitative methods for analyzing comparative data permit the identification of evolutionary processes. Specifically, it has been proposed that new comparative methods can distinguish the direct effects of natural selection on the distribution of a trait within a clade from the effects of drift, indirect selection, genotype-byenvironment interaction, and uncontrolled environmental variation. Such methods can supposedly unravel t-he relative importance of these factors by the phylogenetic analysis of traits, performance attributes, and habitats. We argue that they cannot. We show that many different evolutionary mechanisms can, in principle, account for any one interspecific pattern, and we illustrate our case using examples from the comparative literature. We argue that these confounded mechanisms can only be unraveled if patterns of selection or genetic variation and covariation are directly measured in many species within a clade. Even though comparative methods are valuable for examining the evolutionary history of traits, they will often mislead in the study of adaptive processes.