Abstract:
|
The NIH data sharing policy specifies that data from finished research should be made available for public use while safeguarding the privacy of participants, and protecting confidential and proprietary data. NIH requires that researchers submit a data sharing plan along with their funding applications. Researchers releasing public or open data need to ensure that the data have enough information to reproduce the main research findings while protecting study participants' privacy. In this paper, we present non-standard privacy preserving techniques (also known as disclosure-avoidance techniques) for releasing public-use data. We discuss methods that are relevant to clinical trials, and illustrate each method with simulated clinical trial data. This paper evaluates each technique and the extent to which the technique limits research utility while protecting confidentiality.
|