Inference for partial correlation when data are missing not at random

• DOI: 10.1016/j.spl.2018.05.027
• Publication Date: 2018-06-05T17:55:32Z
• Authors: Tetiana Gorbach; Xavier de Luna
• Keywords: 03 medical and health sciences; 0302 clinical medicine; FOS: Mathematics; Mathematics - Statistics Theory; Statistics Theory (math.ST); 0101 mathematics; 01 natural sciences

We introduce uncertainty regions to perform inference on partial correlations when data are missing not at random. These uncertainty regions are shown to have a desired asymptotic coverage. Their finite sample performance is illustrated via simulations and real data example.