Reference buildings are useful tools for evaluating energy saving measures of an entire building stock. The objective of this study is to develop a method for obtaining reference buildings for the low-income housing stock in Florianopolis, Southern Brazil. Field data collection was performed in order to build a database on geometrical features of houses. Reference buildings were obtained using cluster analysis, which aims to find subgroups within a sample. For that, hierarchical and non-hierarchical techniques were applied in combination. Reference buildings were taken as the nearest houses to the mean of their clusters. Computer simulation using Energyplus were performed to verify the accuracy of the found reference buildings. The 120 housing units sample database obtained from the survey resulted into two reference buildings after cluster analysis: a 76 m(2) house, with living room, kitchen and three bedrooms, and a 37 m(2) house, with combined living room and kitchen and two bedrooms. Simulations have shown that the reference buildings can represent their cluster properly, since the degree-hour values obtained for them were similar to the housing median sample. Cluster analysis proved to be a technique useful for obtaining reference buildings, although one should be very careful in selecting the variables involved in the analysis. (C) 2016 Elsevier B.V. All rights reserved.