Measurement is a core foundation of quality improvement (QI), and analysis of data for QI requires distinct approaches and tools as compared with other areas of healthcare. QI efforts can use structural, process, outcome, and balancing measures, and each measure should have a clear operational definition. Data for improvement should be analyzed dynamically over time, with a focus on understanding the variation present in the data. Distinguishing between common cause and special cause variation is necessary to evaluate and guide improvement efforts. Statistical process control tools such as run charts and control charts can be powerful tools to analyze data over time and help understand variation. This article continues a series of QI educational papers in the Journal of Perinatology, and offers a review of the use of data and measures to drive improvement.