In this study, the price elasticity of water demand was estimated using disaggregated data of approximately 30,000 households recorded over five years: two years before and three years after a tariff revision. From the results of the latent class analysis, the mean price elasticity was -0.1. The households were divided into three groups: 35%–55% of the households did not respond to the tariff revision, and households with high water demand prior to the revision had higher elasticity. In addition, no statistically significant difference was observed in elasticity between the first and third years after revision.