Lobbying Uncovered: Corruption, Democracy, and Public Policy in Brazil

The preceding examples are just that: examples. Quality control over prediction tools like the 9152 Aprovometro is performed by those who subscribe to the service and are constantly monitoring the 9153 model’s degree of hits and misses. 9154 As Box said, models are always wrong, but some of them are more useful than others. JOTA’s 9155 team of data scientists believes in combining methods found in tools like the Aprovometro with views 9156 from experts in the field who are qualitatively capturing the political winds. By using methods like 9157 those presented in this book, it is possible to reduce the degree of uncertainty inherent in Brazil’s 9158 public institutions.