Using weighted clustering and symbolic data to evaluate institutes’s scientific production

It is increasingly common to use tools of Symbolic Data Analysis to reduce the data set without losing much information. Moreover, symbolic variables can be used to preserving the privacy of individuals when their information are present in the data set. In this work, we use information about researchers of institutions from Brazil through the tools of Symbolic Data Analysis and a weighted clustering method for interval data. The main goal is to analyze the scientific production of Brazilian institutions. Results of the cluster analysis and concluding remarks are given.