“…This test opines for the universality of the model, because it helps to assess, whether the assumption that the parameters are the same for all categories is reasonable. Substantially, parallel lines test suggest a hypothesis testing (Berger, 1982;Tsiotas and Polyzos, 2013a), under the null hypothesis H 0 : the location parameters of the model are the same for all categories of the dependent variable and the alternative H 1 : the general model stands that has different parameters per category. Here, the statistical significance is calculated for the general model and, consequently, the null hypothesis is acceptable (Norusis, 2004) when p value (Doan, 2005) presents higher scores than 0,05 or 0,1 (McCullagh and Nelder, 1989).…”