Overpricing in public procurement: Methodology based on the identification of discrepant values

• Diogo Soares Federal University of Santa Catarina (UFSC)
• João Pedro D. da Silva Federal University of Santa Catarina (UFSC)
• Andre Wüst Zibetti Federal University of Santa Catarina (UFSC)
• Simone S. Werner Federal University of Santa Catarina (UFSC)

DOI: https://doi.org/10.5753/sbbd_estendido.2024.244291

Abstract

One of the aims of public procurement is to avoid overpriced contracts, but identifying them can be difficult. This article presents a methodology to identify overprices, focusing on detecting outliers, considering as a previous step the unit price adjustment by regression models. To illustrate, we used items from Electronic Invoices (NF-e) for gasoline commonly purchased by Public Institutions in Santa Catarina. The results demonstrated that the use of the price modeling process prior to the application of outlier identification techniques is important to avoid the mistaken identification or non-identification of overpriced items.

Keywords: Methodology, discrepant values

References

Buckland, W. R. and Buckland, W. R. (1979). Outliers in statistical data. Journal of the Operational Research Society.

Rousseeuw, P. J. and Leroy, A. (1987). Robust Regression and Outlier Detection. Wiley Series in Probability and Statistics. Wiley.

Silva, M. O., Costa, L. G. L., Gomide, L. D., Santos, G. B. D., Oliveira, G. P., Brandão, M. A., Lacerda, A., and Pappa, G. L. (2024). Overpricing analysis in brazilian public bidding items. Journal of Interactive Systems.

Tukey, J. (1972). Some graphical and semigraphical displays. T.A. Bancroft, ed., Statistical Papers in Honor of George W. Snedecor.

Wooditch, A., Wooditch, A., Johnson, N. J., Johnson, N. J., Solymosi, R., Solymosi, R., Ariza, J. M., Ariza, J. M., Langton, S., and Langton, S. (2021). Ordinary least squares regression. null.

Wu, J. (2020). The normal distribution. Essentials of Pattern Recognition.