The procedure of parameter estimation and the parameter estimates are not only affected by the measurement noise, which is present during any experiment, but are also influenced by the known model parameters. The most commonly used functional. which is based on the maximum likelihood principle, only accounts for the experimental noise but not the effect of the uncertainties in the known parameters. A new functional for parameter estimation has been proposed, which will also take into account the uncertainties in the known model parameters. It is shown that, in the presence of uncertainties in the known model parameters, the proposed functional is superior to previous functionals.