Main Article Content
Groundwater is the water present beneath the earth’s surface in soil pore spaces and the fractures of rock formations. Establishing a probability distribution that provides a good fit to groundwater quality has recently become a topic of interest in the fields of hydrology, meteorology among others. In this paper, three groundwater datasets including calcium, magnesium, and chloride are fitted to the normal, lognormal, gamma, Weibull, logistic, and log-logistic distributions to select the best groundwater model. The measures of goodness of fits such as the Akaike information criterion (AIC), Bayesian information criterion (BIC), and log-likelihood are computed to compare the fitted models. The results show that the gamma distribution gives better fits for calcium and magnesium datasets while the lognormal distribution provides a better fit for the chloride dataset than other competing models. This research describes an application of probability distributions and the best-fitted distribution to a practical problem involving groundwater data analysis. By assuming the distribution of data, analysts can utilize the characteristics of the distribution to make predictions on outcomes.