This study investigates various possible approaches in dealing with missing or erroneous data sets. Cleaning up erroneous values and filling in missing values in a meaningful way play a critical role for the consequent data analysis and decision making. What makes a meaningful way depends on available prior information. In this preliminary study, a number of possible approaches are proposed and tested on an actual Huntington disease data, depending on the assumptions.
Keywords: Gaussian process model; erroneous data; low rank matrices; missing data.