Imputation and paired samples in microRNA profiling

microRNAs are small non-coding RNA molecules that post-transcriptionally regulate gene expression, and can play an epigenetic role in many systems. This talk will include a summary of two statistical issues that arose in a recent microRNA profiling project where most subjects provided paired samples (from both healthy and diseased tissue). The first involves imputation of microRNA expression for subjects providing only one sample, and the second involves quantifying the benefit of various percentages of subjects with paired samples.