A growing number of studies in finance decompose multiperiod portfolio returns into a series of single-period returns, using these to test asset pricing models or market efficiency or to evaluate the returns to investment strategies such as those based on momentum, size, and value-growth. We provide a formal analysis of the decomposition method. Crucially, we argue and present empirical evidence that some methods researchers use involve portfolios that nobody would seriously consider ex ante, that transactions costs associated with such portfolios make them poor investment vehicles, and that they can lead to spurious statistical inferences. © The Author 2006. Published by Oxford University Press on behalf of The Society for Financial Studies. All rights reserved.