Hybrid differential evolution is applied to estimate the kinetic parameters of batch polymerization described by differential-algebraic equations. The dynamic behavior of the system consisted of the concentrations of the first and second initiators, the monomer conversion, the zeroth, first and second moments of dead polymer distributions and the total concentration of live polymer. The moments of dead polymer distributions and the total concentration of live polymer were in general difficult to measure in a real process. In this study, we considered that the estimation criterion consisted of some measurable data such as the concentrations of the first and second initiators, the monomer conversion, and the degree of polymerization and polydispersity. We used the worst observed error for all experiments as an objective function so that the parameter estimation problem becomes a min-max estimation problem. Several techniques were also employed to handle the estimation of kinetic parameters for comparison. Hybrid differential evolution could use five individuals to obtain a more satisfactory solution.