There has been considerable interest recently in scientific misconduct. Although much has been written and discussed about specific cases, very little, if any, research has been carried out on the process of fraud. An understanding of this aspect can contribute much to methods of detection and lead to recommendations for preventing misconduct and for implementation of appropriate sanctions where fraud has been detected and proved. In this article I initiate a study of the process of fraud using a series of (...) case studies. Hypotheses are generated by methods pioneered by Peirce and most recently developed and thoroughly discussed by Glaser and Strauss under the name of grounded theory. Some illustrations of what can be learned from such studies are included. (shrink)