Abstract
Manipulative authorities can bunch tenders just below thresholds to implement noncompetitive procurement practices. I use regression discontinuity manipulation tests to identify the bunching manipulation scheme. I investigate the European Union public procurement data set that covers more than two million contracts. The results show that 10–13% of the examined authorities exhibit a high probability of bunching. These authorities are less likely to employ competitive procurement procedures. Local firms are more likely to win contracts from a bunching authority. The probability that the same firm wins contracts repeatedly is high when an authority has high bunching probability. Empirical results suggest that policy makers can effectively employ regression discontinuity manipulation tests to determine manipulative authorities.
Similar content being viewed by others
Availability of data and material
The data set used in the paper is publicly available. The data set can be downloaded at https://data.europa.eu/euodp/en/data/dataset/ted-csv. The European Commission Directorate-General for Internal Market, Industry, Entrepreneurship, and SMEs maintains the integrity of the data set.
Change history
25 June 2022
A Correction to this paper has been published: https://doi.org/10.1007/s00181-022-02270-0
Notes
Directive 2014/24/EU states that the thresholds are EUR 5,548,000 for construction and EUR 144,000 for other contracts. In addition, thresholds for all services concerning social and other specific services listed in Annex XIV and all subsidized services are EUR 750,000 and EUR 221,000, respectively, available at https://ec.europa.eu/growth/single-market/public-procurement/rules-implementation/thresholds_en.
The report is available at https://www.eca.europa.eu/Lists/News/NEWS1901_10/INSR_FRAUD_RISKS_EN.pdf.
Authorities with sufficient number of observations.
The CSV files for 2018 do not contain information about estimated costs. I use the contract award notices csv files. The files are available at https://data.europa.eu/euodp/data/dataset/ted-csv.
The standard forms of the EU are available at “ http://simap.ted.europa.eu/web/simap/standard-forms-for-public-procurement.
Article 5-1 of the 2014/24/EU describes estimated cost as: “ The calculation of the estimated value of a procurement shall be based on the total amount payable, net of VAT, as estimated by the contracting authority, including any form of option and any renewals of the contracts as explicitly set out in the procurement documents.”
Cattaneo et al. (2018) state that “ ... bandwidths much larger than the MSE-optimal bandwidth will lead to estimated RD effects that have too much bias, and bandwidths much smaller than the MSE-optimal choice will lead to RD effects with too much variance.” (page 106)
10 (15) contracts below and above the threshold.
The Stata rddensity package used for manipulation testing is available at https://rdpackages.github.io/rddensity/. The Stata do file is provided as Supplementary Material. The file uses the contract award notices csv files available online and produces all figures and tables of the paper. The do file employs the rddensity package to calculate manipulation probabilities.
Recent thresholds are EUR 209,000 for goods and services and EUR 5,225,000 for construction.
The excess mass contains 3500 contracts. The difference between the actual number of contracts and the counterfactual distribution at the bracket just below the threshold is 3500.
CJM state that “[s]tandard kernel density estimators are invalid at or near boundary points, while other methods may remain valid but usually require choosing additional tuning parameters, transforming the data, a priori knowledge of the boundary point location, or some other boundary-related specific information or modification.” (page 1)
2044 authorities with more than 20 observations, and 1416 authorities with more than 30 observations in optimal bandwidths.
The TED data contain address information on the winning firm for 394,327 contracts. Accordingly, I can construct the Local Winner dummy variable for 394,327 contracts.
These contacts are won by firms that have sufficient observations. Therefore, I can calculate manipulation test statistics and probabilities for these firms.
References
Aryal G, Gabrielli MF (2013) Testing for collusion in asymmetric first-price auctions. Int J Ind Organ 31:26–35
Bajari P, Ye L (2003) Deciding between competition and collusion. Rev Econ Stat 85:971–989
Baltrunaite A, Giorgiantonio C, Mocetti S, Orlando T (2021) Discretion and supplier selection in public procurement. J Law Econ Org 37(1):134–166. https://doi.org/10.1093/jleo/ewaa009
Bobilev R, Guglielmo A, Paltseva E, Spagnolo G (2015) Public procurement thresholds and data in Sweden. Konkurrensverket (KKV) Report 3
Calzolari D, Spagnolo G (2009) Relational contracts and competitive screening. Center for Economic Policy Research (CEPR) Discussion Paper 7434
Cattaneo MD, Idrobo N, Titiunik R (2018) A practical introduction to regression discontinuity designs: vol I. Quantitative and computational methods for social science Cambridge University Press, Monograph prepared for cambridge elements
Cattaneo MD, Frandsen D, Titiunik R (2015) Randomization inference in the regression discontinuity design: an application to party advantages in the U.S. senate. J Causal Infer 3(1):1–24
Cattaneo MD, Jansson M, Ma X (2018) Manipulation testing based on density discontinuity. Stata J 18(1):234–261
Cattaneo MD, Jansson M, Ma X (2020) Simple local polynomial density estimators. J Am Stat Assoc 115(531):1449–1455
Cattaneo MD, Jansson M, Ma X (2021a) Local regression distribution estimators. J Econ (forthcoming)
Cattaneo MD, Jansson M, Ma X (2021b) lpdensity: local polynomial density estimation and inference. J Stat Softw (forthcoming)
Cattaneo MD, Titiunik R, Vazquez-Bare G (2017) Comparing inference approaches for RD designs: a reexamination of the effect of head start on child mortality. J Policy Anal Manage 36(3):643–681
Cattaneo MD, Titiunik R, Vazquez-Bare G (2020) The regression discontinuity design. Handbook of research methods in political science and international relations. Sage Publications, Ch. 44, pp 835–857
Chetty R, Friedman JN, Olsen T, Pistaferri L (2011) Adjustment costs, firm responses, and micro vs. macro labor supply elasticities: evidence from Danish tax records. Q J Econ 126:749–804
Coviello D, Guglielmo A, Spagnolo G (2018) The effect of discretion on procurement performance. Manage Sci 64
Decarolis F, Giorgiantonio C (2020) Corruption red flags in public procurement: new evidence from italian calls for tenders. Bank of Italy Discussion Papers (QEF) No. 544
Europe Economics (2006) Evaluation of public procurement directives. European Commission, London, September
Fazekas M, Toth IJ, King LP (2016) An objective corruption risk index using public procurement data. Eur J Crim Policy Res 22:369–397
Ishii R (2009) Favor exchange in collusion: empirical study of repeated procurement auctions in Japan. Int J Ind Organ 27(2):137–144
Kawai K, Nakabayashi J (2020) Detecting large-scale collusion in procurement auctions. J Polit Econ (Forthcoming)
Kutlina-Dimitrova Z, Lakatos C (2016) Determinants of direct cross-border public procurement in EU member states. Rev World Econ 152:501–528
McCrary J (2008) Manipulation of the running variable in the regression discontinuity design: a density test. J Econom 142(2):698–714
Padhi SS, Mohapatra PKJ (2011) Detection of collusion in government procurement auctions. J Purch Supply Manage 17:207–221
Palguta J, Pertold F (2017) Manipulation of procurement contracts: evidence from the introduction of discretionary thresholds. Am Econ J Econ Pol 9:293–315
Schurter K (2020) Identification and inference in first-price auctions with collusion. Pennsylvania State University Working Paper
Szucs F (2017) Discretion and corruption in public procurement. Working Paper. Available at: https://sites.google.com/view/ferencszucs/research
World Bank (2012) Why reform public procurement? Available online at: http://www.worldbank.org/content/dam/Worldbank/document/MNA/ Why_Reform_Public_Procurement_English.pdf. Accessed 10 May 2019
Funding
Not applicable
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The author has nothing to disclose.
Code availability
I conducted the empirical analysis using Stata 15 software. The Stata codes for the regression discontinuity tests are available at https://rdpackages.github.io/. I will provide the Stata do file which uses the csv files provided by the European Union and produces all the tables and the figures of the paper.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The original online version of this article was revised: The author’s affiliation was incorrectly published as “Department of Economics, TOBB University of Economics and Technology, Sogutozu Street, No: 43, 06560 Ankara, Turkey”. It is corrected as “Department of Economics and Finance, College of Economics and Political Science, Sultan Qaboos University, Muscat, Oman”.
I would like to thank two anonymous reviewers for their careful reading of the manuscript and their many insightful comments and suggestions.
Supplementary Information
Below is the link to the electronic supplementary material.
Appendices
Appendix A: The CJM methodology
In this section, I rewrite some of the major equations of CJM and summarize their methodology. The supplementary material supplied by CJM provides detailed proofs and derivations.
CJM proposes a local polynomial density estimator to estimate the probability density function of the estimated cost (c), f(c). The manipulation test is a hypothesis test on the continuity of the density f(c) at the EU threshold, T. The test is formulated as follows:
CJM estimates the density f(c) using a local-density estimator based on the cumulative distribution function of the observed sample. Specifically, the test statistic is
where \(\hat{V_{p}^{2}}(h)=\hat{V}\left\{ {\hat{f}}_{+,p}(h)-{\hat{f}}_{-,p}(h)\right\} \) is a variance estimator such that \(V(x)=e'_{1}A(x)^{-1}B(x)A(x)^{-1}\). \(A(x)=f(x)\int _{h^{-1}(X-x)}r_{p}(u)r_{p}(u)'K(u)du\) and \(B(x)=f(x)^{3}\int \int _{h^{-1}(X-x)}min(u,v)r_{p}(u)r_{p}(v)'K(u)K(v)dudv.\) Detailed descriptions of the notation and derivations are available at Theorem 1 of CJM (page 3).
CJM develops AMSE criterion functions to calculate the optimal bandwidths. The bandwidths are chosen to minimize the AMSE of the following density estimators, separately:
Appendix B: The distribution of manipulating authorities within EU countries
Figure 6 displays the percentages of authorities with p-values below 0.05 in each country with adequate number of observations.
Appendix C: Binomial test results
This section displays the binomial test results for alternative windows and alternative initial window sample sizes. The test is conducted for different sample sizes in the initial window. Each test presents results or 10 windows. Table 3 displays the binomial manipulation test results.
Rights and permissions
About this article
Cite this article
Tas, B.K.O. Bunching below thresholds to manipulate public procurement. Empir Econ 64, 303–319 (2023). https://doi.org/10.1007/s00181-022-02250-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00181-022-02250-4