This document discusses the importance of context in understanding data. It argues that "data does not speak for itself" and that relying only on correlations in big data can lead to unreliable or meaningless results if the proper context is not understood. Specifically, it notes that humans design data collection systems and analyses, and their underlying assumptions, referred to as "mental models", influence the interpretation of the data. Ignoring these human influences and assumptions behind the data is a "false and dangerous notion" that could damage businesses. Understanding the context, including possible causal relationships, is crucial for reliably answering important questions using data.