Simulating Collusion: Challenging Conventional Estimation Methods

Author:

Bellert Nicole1,Günster Andrea1

Affiliation:

1. Zurich University of Applied Sciences

Abstract

Abstract

The empirical literature in industrial economics relies on hazard rate models to estimate the probability of death and survival as well as to explain the duration of collusion. Estimations are based on detected and convicted offenses. Detected cartels are, however, a non-random sample of their population of collusive activity. We question whether hazard rate and linear estimation methods derive consistent unbiased estimators explaining collusion. We simulate collusive behavior of industries with different number of firms based on three classical models of collusion, additionally varying four variables of antitrust enforcement. It is the first easily amenable and amendable simulation tool for collusion. The simulation provides a ground-truth data set of undetected and detected cartels; a population and its sample. Applying hazard rate and linear models on the sample fails to deliver consistent unbiased estimates for the population. Controlling for sample and feature selection on the population of all potential offenders does not improve prediction. The use of average treatment effects and average duration bias shows to quantify the magnitude of any bias well; a solution for future research relying on detected cartel cases. JEL Classification: C13 , C63 , D43 , 43 , L41 , L44

Publisher

Springer Science and Business Media LLC

Reference630 articles.

1. Stata {{Bookstore}}: {{Introductory Econometrics}}: {{A Modern Approach}}, {{Seventh Edition}}. C:\Users\bell\Zotero\storage\QPJ8T5W6\introductory-econometrics.html, english, https://www.stata.com/bookstore/introductory-econometrics/, The seventh edition introduces discrete covariates and the modern potential outcome approach to causal inference earlier and more accessibly in the new sections 2.7, 3.7, 4.7, and in the improved section 7.6. The new subsections 13.2(a) and 13.2(b) clearly explain the difference-in-differences approach to causal inference. The result is that an excellent introductory book has been made even better., 2024-02-11, Stata {{Bookstore}}

2. (2007) European {{Competition Law Annual}}: 2006 : {{Enforcement}} of {{Prohibition}} of {{Cartels}}. Hart Publishing, C:\Users\bell\Zotero\storage\HEUJSKZH\2007 - European Competition Law Annual 2006 Enforcemen.pdf, english, 978-1-84113-751-3 978-1-4725-6014-8, 2023-12-13, 10.5040/9781472560148, European {{Competition Law Annual}}

3. {Abrantes-Metz}, Rosa M. and Connor, John M. and Metz, Albert D. (2013) The {{Determinants}} of {{Cartel Duration}}. IO: Theory eJournal https://doi.org/10.2139/ssrn.2263782, Duration, english, In this paper we model cartel duration as a mixed proportional hazard model and condition on cartel characteristics such as the agency first detecting the cartel, industry, if it is a bid rigging or price fixing cartel, the number of countries affected, the affected sales, and measures of the economic cycle and trend. Results are intuitive and fairly consistent across models, and conform well with theory and prior empirical work. We also found that the model results are sensitive to the presence of unobserved heterogeneity.Among other results, we find that cartels first detected by United States or European Union agencies tend to be longer-lived, likely because those detected by other jurisdictions are primarily follow-ups of related larger and older cartels first uncovered in the United States or Europe. Bid rigging cartels tend to be longer-lived than others, while cartels distributed across geographies tend to be shorter-lived. Cartel durations are increasing in the size of a cartel's affected sales and sanctions. Industries such as Petroleum & Coal, Finance & Insurance, and Food, Feed, Tobacco & Transportation have shorter-lived cartels, while industries such as Electronic Products have longer-lived cartels. The state of the economy can impact the duration of a cartel as well. Cartels where the leading firm has a market share of at least 40% have longer durations. However, the wide variation in the unobserved frailty factor suggests that additional, significant covariates remain unaccounted for in our information set., 2023-12-04, 1556-5068

4. {Abrantes-Metz}, Rosa M. and Taylor, Christopher T. and Froeb, Luke M. and Geweke, John. A {{Variance Screen}} for {{Collusion}}. C:\Users\bell\Zotero\storage\VIZTXSY7\papers.html, english, In this paper, we examine price movements over time around the collapse of a bid-rigging conspiracy. While the mean decreased by sixteen percent, the standard deviation increased by over two hundred percent. We hypothesize that conspiracies in other industries would exhibit similar characteristics and search for "pockets" of low price variation as indicators of collusion in the retail gasoline industry in Louisville. We observe no such areas around Louisville in 1996-2002., 2021-03-22, 10.2139/ssrn.683922, Social Science Research Network, Rochester, NY, ID 683922, March, 2005, {{SSRN Scholarly Paper}}

5. Accenture. Accenture {{Cost}} of {{Cybercrime Study}} 2019. C:\Users\bell\Zotero\storage\3CSI4LUA\accenture-2019-cost-of-cybercrime-study-final.pdf, https://www.accenture.com/\_acnmedia/pdf-96/accenture-2019-cost-of-cybercrime-study-final.pdf, 2022-06-29, 2019

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3