Continuously stirred tank reactors (CSTRs) play a big role in chemical engineering and in industries nowadays. Therefore, it is important and necessary to make sure CSTRs work successfully by avoiding disturbance from external factors. In this paper, we look at the impact of different kind of uncertainties (errors) to the model fitting and the parameter estimation of the CSTR's, for both cases of exothermic and endothermic reactors by taking into consideration of high and low variances of noise into concentration and temperature of the model. Two parameters, activation energy E and pre-exponential Arrhenius reaction rate k 0 have been estimated and investigated, due to their sensitivities to the system facilitated by the guessed noisy data and by using Minimization Assimilation Method (MAM). Results showed that, the increase of noise in measurements affects activation energy E much more than the pre-exponential Arrhenius reaction rate k 0 for all types of noise as k 0 converges to its guessed values. Also, from the results obtained, the endothermic CSTR is more sensitive than the exothermic CSTR for any kind of noise according to much deviation observed in its estimated activation energy values. Furthermore, quasi random noise has provided closer values for parameter estimation compared to the remaining types of noise but with negative activation energies for both cases (exothermic and endothermic).