This study analyses, through cross-section estimation methods, the influence of spatial effects and human capital in the conditional productivity convergence (product per worker) in the economic sectors of NUTs III of mainland Portugal between 1995 and 2002. To analyse the data, Moran’s I statistics is considered, and it is stated that productivity is subject to positive spatial autocorrelation (productivity develops in a similar manner to productivity in neighbouring regions), above all, in agriculture and services. Industry and the total of all sectors present indications that they are subject to positive spatial autocorrelation in productivity. On the other hand, it is stated that the indications of convergence, specifically bearing in mind the concept of absolute convergence, are greater in industry. Taking into account the estimation results, it is stated once again that the indications of convergence are greater in industry, and it can be seen that spatial spillover effects, spatial lag (capturing spatial autocorrelation through a spatially redundant dependent variable) and spatial error (capturing spatial autocorrelation through a spatially redundant error term), as well as human capital, condition the convergence of productivity in the various economic sectors of Portuguese region in the period under consideration.