Data set used to estimate the autoregressive distributed lag (ADL) model to understand how water quality measures (e.g., raw water TOC and algal toxin) and other variables affect drinking water treatment costs at the Bob McEwen Water Treatment Plant in southwestern OH. This dataset is associated with the following publication: Heberling, M., J.I. Price, C. Nietch, M. Elovitz, N. Smucker, D.A. Schupp, A. Safwat, and T. Neyer. Linking Water Quality to Drinking Water Treatment Costs Using Time Series Analysis: Examining the Effect of a Treatment Plant Upgrade in Ohio. WATER RESOURCES RESEARCH. American Geophysical Union, Washington, DC, USA, 58(5): e2021WR031257, (2022).