The call admission control schemes for ATM-type networks are based on the concept of effective bandwidth (EB). Most such schemes focus on the cell loss rate as the exclusive QoS metric and therefore base their EB on cell-loss rate approximations. We use simulation data to develop regression models for cell loss and cell delay; these estimates can be used to compute effective bandwidths to satisfy both cell loss and delay. We compare the accuracy of the regression models with that of the well-known fluid-flow model by Anick et al. Our results indicate that the regression models are computationally simple and sufficiently accurate for practical use.