A comparison among methods for estimation of the parameter of the Maxwell- Boltzmann distribution using simulation

Abstract

The Maxwell or Maxwell- Boltzmann distribution was invented to solve problems related to physics, chemistry and plays an important role in and other allied sciences. So in this paper Bayesian using special priorinformation for estimating the scale parameter of Maxwell distribution, the maximum likelihood estimation andthree different types of moments are presented for this. The  simulation by matlab program  is used to compare  these estimators with respect to the Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE), the results of comparison showed that for all the varying sample size, the estimators of Bayes method  with special prior distribution is followed by the Maximum likelihood estimatorhas  smaller MSE and MAPE compared to others, and in all cases the statistical hypotheses had been satisfied for both methods the MSEand MAPE decrease as sample size increases.