Distribuição Beta Log-normal

Autor(es) e Instituição: 
Fredy Castellares UFMG
Lourdes Montenegro UFMG
Gauss Cordeiro UFRP
Fredy Castellares

For the first time, we introduce the beta log-normal distribution for which the log-normal distribution is a special case. Various properties of the new distribution are discussed. Expansions for the cumulative distribution and density functions that do not involve complicated functions are derived. We obtain expressions for its moments and for the moments of order statistics. The estimation of parameters is approached by the method of maximum likelihood and the expected information matrix is derived. The new model is quite flexible in analyzing positive data as an important alternative to the gamma, Weibull, generalized exponential, beta exponential and Birnbaum-Saunders distributions. The flexibility of the new distribution is illustrated in an application to a real data set.