The aggregate Lerner index is a popular composite measure of multi-product banks’ market power, based on the assumption that banks’ single aggregate output factor is total assets. This study identifies three limitations of the aggregate Lerner index that potentially distort its interpretation as a composite measure of market power. We investigate the empirical relevance of these limitations for a sample of U.S. banks covering the years 2011–2017. We establish an economically relevant bias in the value of the aggregate Lerner index and show that this bias may also affect regressions that use the Lerner index as a dependent or explanatory variable.