I study the nature and extent of manipulation of test scores using an experiment in the Italian education system consisting in the random assignment of external monitors to classrooms. To do so, I develop a method based on a likelihood approach, which distinguishes between manipulation and unlikely results happening for other reasons. The results show frequent manipulation, which is not associated with an increase in the correlation of the answers after we control for mean test scores. The manipulation is concentrated in the South and Islands, and it tends to favor female students, and immigrants in Italian tests. Finally, the negative correlation between the amount of manipulation and the number of missing answers in the difference between open ended and multiple choice questions suggest that teachers are more responsible for the manipulation than students.