Panel data methodology is one of the most popular tools for quantitative analyses in the field of social sciences, particularly on topics related to economics and business. This technique allows us simultaneously addressing individual effects, numerous periods, and in turn, the endogeneity of the model or independent regressors. Despite these advantages, there are several methodological and practical limitations to perform estimations using this tool. Two types of models can be estimated with Panel data. While those of static nature have been the most developed, for performing dynamic models still remain some theoretical and practical constraints. This paper focus precisely on the latter, dynamics panel data, using an approach that combines theory and praxis, and paying special attention on estimations with macro database, that is to say, dataset with a long period of time and a small number of individuals, also called long panels.