"New opinions are always suspected, and usually opposed, without any other reason but because they are not already common". John Locke (1689).
When discussing the usefulness of synthetic data one is often confronted with the following opinions: "We have real data available so we don't need synthetic data!"; "Others also do not work with synthetic data!"; "Synthetic data is not real data!"; "With synthetic data we lose data credibility!"; "We have more important things to do!"; "Synthetic data is a hobbyhorse of science!"
But synthetic population data sets are not intended to replace traditional data sets for all research purposes, and will certainly not reduce the need to collect more and better data. But they are increasingly used for multiple practical applications. Synthetic data generation makes the dissemination and use of information contained in confidential data sets possible, by creating replacement datasets that can be shared as public use files...