The effects of different experimental designs on parameter es - timation in the kinetics of a reversible chemical reaction * *

Using the experimental design methods, instead of deterministic ones commonly used by chemists, to estimate the kinetic constants is a very important subject in chemical researches, since such-obtained kinetic parameters have much better statistical properties. D-optimum design is a popular statistical technique, which emphasizes to obtain the estimated parameters with the smallest content of the confidence region. But for nonlinear models, such as the kinetic model of a reversible reaction, the D-optimum design is locally optimal at the value of the initial chosen parameters. The goal of this article is try to put different experimental design techniques, i.e., uniform design, orthogonal design and D-optimum design into a common framework, and to attempt to gain some insight on when and where which of these three experimental methods can be expected to work well. The extensive Monte Carlo experiments have been done in order to compare the performance of these methods from point of view of prediction and the variance of estimated parameters. The results showed that the D-optimum design often gave the best performance, but it was easy to broken done for estimation of parameters, when the initial parameters are far away from the true parameters. The orthogonal design was also broken down in some situations. The uniform design is the most stable, and it works well in all situations.