The aim of this paper is to analyse the long-run performance of IPOs in the Spanish Capital Market. Due to the fact that the method of estimation of the returns influences both the magnitude of the abnormal return as well as the size and power of the statistical tests, we have used different methods with the aim of examining the robustness of the long-run perfomance of IPOs with respect to different specifications of the model. The results of the study show that the existence of long-run underperformance of Spanish IPOs depends on the methodology, benchmarks and weighting schemes used. There is long-run underperformance when the abnormal returns are calculated as BHARs on an equal-weighted basis, although the results depend on the test statistic used, but not when we follow a calendar time approach or we use BHARs on a value-weighted basis.

Key words: initial public offering (IPO), long-run return, BHAR, calendar-time portfolios.
JEL classification: G10, G12, G14.