Testing for the Pareto type I distribution: a comparative study

Abstract Pareto distributions are widely used models in economics, finance and actuarial sciences. As a result, number of goodness-of-fit tests have been proposed for these the literature. We provide an overview existing distribution, focussing specifically on type I distribution. To date, only single paper testing has published. However, mentioned much wider scope than is case current as it covers multiple types distributions. The differs respects. First, narrower focus distribution allows larger to be included. Second, concerned with composite hypotheses compared simple (specifying parameters question) considered overview. Third, sample sizes two papers differ substantially. In addition, we consider different methods fitting Type distribution; method maximum likelihood closely related moment matching. It demonstrated that estimation profound effect, not powers achieved by various tests, but also way which numerical critical values calculated. show that, when using likelihood, resulting shape invariant can obtained Monte Carlo procedure. This matching employed. includes extensive power study. Based results obtained, recommend use test based phi divergence together estimation.