This paper addresses statistical estimation problems of the optimal repair-cost limits minimizing the long-run average costs per unit time in discrete seting. Two discrete repair-cost limit replacement models with/without imperfect repair are considered. We derive the optimal repair-cost limits analytically and develop the statistical non-parametric procedures to estimate them from the complete sample of repair cost. Then the discrete total time on test (DTTT) concept is introduced and applied to propose the resulting estimators. Numerical experiments through Monte Carlo simulation are provided to show their asymptotic convergence properties as the number of repair-cost data increases. A comprehensive bibliography in this research topic is also provided.