RESPONDENT ANONYMITY AND DATAMATCHING
In: Public opinion quarterly: journal of the American Association for Public Opinion Research, Band 21, Heft 3, S. 384-388
ISSN: 0033-362X
It is frequently necessary to request L7J R's to indicate their name for purposes of repeated observation or data matching. However, it seems that this violation of R's anonymity unfavorably affects frankness of response. On the other hand use of deceit, such as marking questionnaires with invisible ink, raises ethical & public relations problems for researchers. '...there is need for a procedure or code, as simple & mechanical as possible, which avoids direct use of R's name on the questionnaire & which ensures that persons (researchers, clerks) handling the questionnaire or additional data cannot know the name of the R who filled out the specific questionnaire.' A specific procedure is proposed as a solution to this problem in the common res situation where it is necessary to match data from a questionnaire with data available in a file (Sch records). The main point in the proposed procedure is the use of 2 codes in such a way that no person who has access to m's knows both of the codes. Questionnaire & file data are matched while retaining full anonymity for questionnaire responses. W. Delany.