Fitting the Distribution of Air Temperature for the State of Mato Grosso Do Sul, Brazil

Abstract

In this study, the objective was to verify the quality of the adjustment of the monthly average air temperature series in the State of Mato Grosso do Sul, using data retrieved from the National Institute of Meteorology networks in the state of Mato Grosso do Sul, Brazil. To achieve this objective, various distributions were fitted to the series. Goodness-of-fit test statistics (Kolmogorov-Smirnov, Anderson-Darling, CramerVon Mis), model selection criteria (AIC and BIC), and coefficient of Skewness and Kurtosis were employed, which showed that the air temperature is not uniformly distributed over the region. The result shows that the two-parameter Weibull distribution fits the data best. Furthermore, the air temperature of Mato Grosso do Sul, Brazil for the period of this study is slightly above average in most cases with few extremely low values. It is recommended that the two-parameter Weibull distribution be used when considering probability model for air temperature series in the state of Mato Grosso do Sul, Brazil.