Previous work has identified that IPOs underperform a market index, and the purpose of this paper is to examine the robustness of this finding. We re‐examine the evidence on the long‐term returns of IPOs in the UK using a new data set of firms over the period 1985–92, in which we compare abnormal performance based on a number of alternative methods including a calendar‐time approach. We find that, using an event‐time framework, there are substantial negative abnormal returns to an IPO after the first 3 years irrespective of the benchmark used. However, over the 5 years after an IPO, abnormal returns exhibit less dramatic underperformance, and the conclusion on negative abnormal returns depends on the benchmark applied. Further if these returns are measured in calendar time, we find that the (statistical) significance of underperformance is even less marked.