In this paper, we study estimation of the probability density (pdf) and cumulative distribu-tion functions (cdf) of the log-power normal distribution using maximum likelihood (ML), uni-formly minimum variance unbiased (UMVU), least square (LS), weighted least square (WLS), Cramer-von-Mises (CVM) and Anderson-Darling (AD) estimation methods. The outcomes are compared using the mean integrated squared error (MISE). It is shown that the ML es-timation is more ecient than the others based on simulation studies. Also, certain useful characterizations of this distribution are presented. A real data set about the daily ozone level measurements in New York city is analyzed for the illustrative purposes.
