Mode Hunting Using Pettiest Components Analysis

Principal component analysis has been used to reduce dimensionality of datasets for a long time. In this paper, we will demonstrate that in mode detection the components of smallest variance, the pettiest components, are more important. We prove that when the data follows a multivariate normal distribution, by implementing "pettiest component analysis" when the data is normally distributed, we obtain boxes of optimal size in the sense that their size is minimal over all possible boxes with the same number of dimensions and given probability. We illustrate our result with a simulation revealing that pettiest component analysis works better than its competitors.