The present invention extends to methods, systems, and computing system program products for iteratively calculating covariance for Big Data. Embodiments of the invention include iteratively calculating one or more components of a covariance for two modified computation subsets based on one or more components of a covariance for two previous computation subsets and then calculate the covariance for two modified computation subsets based on the iteratively calculated components. Iteratively calculating covariance avoids visiting all data elements in the modified computation subsets and performing redundant computations thereby increasing calculation efficiency, saving computing resources and reducing computing system's power consumption.