The Discipline of Business Experimentation
指出企业常将统计噪声误判为因果关系，导致错误决策；提出进行有效商业实验需明确目的、确保利益相关者承诺遵守结果、评估可行性、选择合适样本量，并充分利用实验数据。
The data you already have can’t tell you how customers will react to innovations. To discover if a truly novel concept will succeed, you must subject it to a rigorous experiment. In most companies, tests do not adhere to scientific and statistical principles. As a result, managers often end up interpreting statistical noise as causation--and making bad decisions. To conduct experiments that are worth the expense and effort, companies need to ask themselves several questions: Does the experiment have a clear purpose? Managers must figure out exactly what they want to learn in order to determine if testing is the best approach. Have stakeholders made a commitment to abide by the results? Are they willing to walk away from a project if the findings suggest they should? Is the experiment doable? The complexity of the variables in a business experiment and their interactions can make it difficult to determine cause-and-effect relationships. Choosing the right sample size is important. How can we ensure reliable results? Randomized field trials, “blind” tests, and big data can help. Have we gotten the most value out of the experiment? Conducting the experiment is just the beginning. Use the data to assess which components of a new initiative might have the highest ROI or the markets where it is most likely to be successful