top of page

WORK IN PROGRESS

Effects of Family Refusal on Deceased Donor Organ Recovery

This paper elucidates the causal effect of family refusal on deceased organ recovery in Turkey. Using provincial and district-level panel data that span the period of 2012-2019 and employing a fixed-effects instrumental variables Poisson that leverages educational attainment and potential supply of donors as a source of exogenous variation in family refusal, results show that family refusal rate reduces the expected number of deceased organ donations by about 5 percent.

​

Keywords: Instrumental variables Poisson, brain death, family consent, deceased organ donation, Turkey

Mass Forced Displacement and Incarceration: A Comparative Case Study using Augmented Synthetic Controls

Kırdar, Lopez Cruz and Türküm recently published a study in the Journal of Economic Behavior & Organization and concluded that the incarceration rates for various violent and non-violent crime subcategories fell due to the arrival of Syrian refugees. Using the exact, but backward-extented data on incarceration rates used by Kırdar et al. (2022) and incorporating staggered treatment timing of refugee settlement across provinces via the augmented synthetic control, this study, in stark contrast, finds that the treatment effects are always positive (i.e. crime inducing). However, these estimates are of low precision such that following the onset of refugee influx, nineteen categories of crime rates would not have been any different in the absence of mass displacement across Syrian border. This indicates that the negative estimates reported by Kırdar et al. (2022) are of drastically wrong quantities no matter how precise they may be. Our results suggest that the method of choice of the researchers is one and possibly not the only source of bias.

​

Keywords: Augmented synthetic control, crime, refugees, Syrians, Turkey

Collusion, Counterfactuals and Machine Learning

Tacit collusion is a market conduct that enables firms to raise prices, produce less output and obtain supra-normal profits, considered to be illegal in the United States, Canada and most of the EU countries due to antitrust laws. Some industries, such as steel, cement and banking, are particularly known to be prone to collusion, characterized by a high degree of concentration, similar cost structures, significant barriers to entry and product homogeneity. However, as current practices have shown through my field experience as a former consultant, detection of collusive behavior is a very difficult and occasionally a heuristic process because (1) the enforcement faces the difficulty of finding hard evidence, (2) the predictions of the enforcer/regulator or the courts may be imperfect and/or (3) the existing detection tools may be unable to isolate the confounding factors that indicate collusive behavior when there is actually none (type I error) or non-collusion when there actually is (type II error).
 
This paper aims to (1) introduce a powerful routine for detecting collusive behavior using counterfactuals; (2) assess the extent to which the imputed counterfactual is aligned with the claims of the competition authorities and the decision of the courts using data on landmark cases in the EU and the US and (3) identify whether collusive behavior can be well-predicted via machine learning tools for effective monitoring.
 
I propose the use of the synthetic control, to ex-post detect collusive practices. The idea is to reproduce the colluders' price trajectory before they enter into a collusive agreement by using the convex combination of firms in the same relevant market that are known to be unrelated to the collusion. Causal inference can be carried out by comparing the price level of the synthetic firms (non-colluders) against colluders in the collusion period. This allows us to (i) identify whether unfavorable price movements are the consequence of collusive behavior (through the imputation of the counterfactual and falsification tests), (ii) measure the intensity of collusion through time by the size of post-collusion gap between the observed and the counterfactual; and (iii) identify firms that are more likely to steer collusive behavior (through an exercise called, leave-one-out synthetic controls). Using data on cases in the EU and the US, a comparison of inferences drawn from the synthetic control and the actual court decisions can be made to assess the extent to which courts commit type I and type II errors. The identification of the cause and effect serves not only to design optimal law enforcement and punishment schemes, but also to carry out out-of-sample prediction of firm behavior through machine learning algorithms such as boosting regression to which effective monitoring of collusive behavior and facilitating practices hinge upon.
​
JEL Classification: C15; C54; K21; K42 L41; L51
Keywords: Synthetic control, collusive behavior, boosting regression

Synthetic Control Method for Comparative Case Studies: A Critical Review

This review introduces the “nuts and bolts” of the implementation of the synthetic control; details when the method is likely to produce unreliable estimates; surveys the growing body of literature that uses the method in economics and political science and presents a 'user guide' for future implementations of the synthetic control. About 500 articles have been published since the inception of the method by Abadie and Gardeazabal (AER, 2003). While a careful screening of the past twenty years of published empirical research shows highly credible applications, there remains a significant number of poorly designed studies that lack the fundamental requirements to infer causality.

​

JEL Classification: C15; C54

Keywords: Synthetic control, comparative case study

bottom of page