Data Reconciliation is a technique that has been developed more than fifty years ago and has been refined over the past few decades and is now being deployed routinely in several process industries such as refining, petrochemicals, mineral processing and hydro-metallurgy. The main aim of data reconciliation is to obtain accurate estimates of all process variables and parameters using plant measurements that are invariably corrupted by random errors and may also contain biases and other gross errors. These reconciled estimates are subsequently used either in offline exercises such as simulation, retrofitting, and de-bottlenecking or in online optimization and control applications. In this presentation, a brief history of data reconciliation, its assumptions, and uses are reviewed. New developments in this area are highlighted such as robust data reconciliation to handle model uncertainties, and reconciliation using identified models derived purely from operating data. Several case studies in the mineral processing industries reported in the literature are also highlighted to indicate the potential benefits of this technique.