Endogenous Selection Research Articles

Peer effects and endogenous social interactions

This paper proposes a solution to the problem of endogenous selection of peers in the linear-in-means model. We do not require to specify a model for how the selection of peers comes about. Rather, we exploit two restrictions that are inherent in many such specifications to construct conditional moment conditions. The restrictions in question are that link decisions that involve a given individual are not all independent of one another, but that they are independent of the link decisions made between other pairs of individuals that are located sufficiently far away in the network. These conditions imply that instrumental variables can be constructed from leave-own-out networks.

Evaluating methodological approaches to assess the severity of infection with SARS-CoV-2 variants: scoping review and applications on Belgian COVID-19 data

BackgroundDifferences in the genetic material of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants may result in altered virulence characteristics. Assessing the disease severity caused by newly emerging variants is essential to estimate their impact on public health. However, causally inferring the intrinsic severity of infection with variants using observational data is a challenging process on which guidance is still limited. We describe potential limitations and biases that researchers are confronted with and evaluate different methodological approaches to study the severity of infection with SARS-CoV-2 variants.MethodsWe reviewed the literature to identify limitations and potential biases in methods used to study the severity of infection with a particular variant. The impact of different methodological choices is illustrated by using real-world data of Belgian hospitalized COVID-19 patients.ResultsWe observed different ways of defining coronavirus disease 2019 (COVID-19) disease severity (e.g., admission to the hospital or intensive care unit versus the occurrence of severe complications or death) and exposure to a variant (e.g., linkage of the sequencing or genotyping result with the patient data through a unique identifier versus categorization of patients based on time periods). Different potential selection biases (e.g., overcontrol bias, endogenous selection bias, sample truncation bias) and factors fluctuating over time (e.g., medical expertise and therapeutic strategies, vaccination coverage and natural immunity, pressure on the healthcare system, affected population groups) according to the successive waves of COVID-19, dominated by different variants, were identified. Using data of Belgian hospitalized COVID-19 patients, we were able to document (i) the robustness of the analyses when using different variant exposure ascertainment methods, (ii) indications of the presence of selection bias and (iii) how important confounding variables are fluctuating over time.ConclusionsWhen estimating the unbiased marginal effect of SARS-CoV-2 variants on the severity of infection, different strategies can be used and different assumptions can be made, potentially leading to different conclusions. We propose four best practices to identify and reduce potential bias introduced by the study design, the data analysis approach, and the features of the underlying surveillance strategies and data infrastructure.

Correction to “Training, Recruitment, and Outplacement as Endogenous Adverse Selection”

Correction to “Training, Recruitment, and Outplacement as Endogenous Adverse Selection”

Understanding the public-private sector wage gap in Germany: New evidence from a Fixed Effects quantile Approach∗

The public-private sector wage gap is an important labor market indicator, reflecting sectoral differences in wage and recruitment policies. We provide new evidence on this sectoral gap throughout the wage distribution in Germany. Using data from the German Socio-Economic Panel (1984–2017), we decompose the wage gap and control for unobservable factors that endogenously determine the occupational sector choice. Our estimates confirm the result in the literature that women benefit from working in the public sector. For men, we find that they are unambiguously disadvantaged, with higher remuneration in the private sector across the entire wage distribution. This result contrasts with previous findings in the literature. Moreover, our findings show that taking endogenous selection into account substantially changes the decomposition of the gap, and it is crucial for assessing alternative policy measures. • We decompose the public-private sector wage gap in Germany over a long time span. • We adopt a novel approach that takes endogenous sector choice into account. • Women benefit from working in the public sector throughout the wage distribution. • Men are penalized for working in the public sector throughout the wage distribution. • Controlling for selection changes the assessment of alternative policy measures.

National development banks and loan contract terms: Evidence from syndicated loans

In this study, we examine whether national development banks (NDBs) fill market gaps in the syndicated loan market. Existing theories make conflicting arguments, but little empirical research has systematically investigated the roles of NDBs in credit markets. To fill the gap, we build a novel and comprehensive list of NDBs worldwide. Using a large, international sample of non-sovereign syndicated loans over the past two decades, we find that loans with NDBs have longer maturity and higher loan spreads than those without. These results hold using the propensity score matching technique and the treatment effects model that account for the endogenous selection of NDBs. We also find that NDBs provide financial support for credit-rationed borrowers and play a countercyclical role during global liquidity cycles. Our study implies that NDBs address market failures in the syndicated loan market.

Vertical Contracts with Endogenous Product Selection: An Empirical Analysis of Vendor Allowance Contracts

Producers frequently provide retailers with financial incentives to secure product distribution. These payments often take the form of vendor allowances: lump-sum transfers to retailers that do not directly depend on quantity sold. I introduce an estimation strategy that uses observed product selections to inform unobserved allowances. I use retailers’ replacement threats, which may allow them to capture both vendor transfers and lower wholesale prices. A counterfactual restricts firms to contract on only wholesale prices. Results show that vendor allowances may have not only (negative) product distortion effects but also (potentially positive) pricing effects.

Social insurance programs and later-life mortality: Evidence from new deal relief spending

A growing body of research explores the long-run effects of social programs and welfare spending. However, evidence linking welfare support in early life with longevity is limited. We add to this literature by evaluating the effect of in-utero and early-life exposure to the largest increases in welfare spending in the US history under the New Deal programs. Using Social Security Administration death records linked with the 1940-census and spending data for 115 major cities, we show that the spending is correlated with improvements in old-age longevity. A treatment-on-treated calculation focused on a period when spending rose by approximately 1900 percent finds that a 100 percent rise in municipal spending in the year of birth is associated with roughly 3.5 months higher longevity. We show that these effects are not driven by endogenous selection of births, selective fertility, endogenous migration, and sample selection caused by endogenous data linking. Additional analysis suggests that rises in education and socioeconomic status are likely channels of impact.

Effects of incorporating public innovation intermediaries on technology transfer performance: evidence from patent licensing of Japan’s Kohsetsushi

The incorporation of public organizations is meant to improve their efficiency and contribution to national and local economies. In Japan, incorporation has been implemented at the national and local levels since the late 1990s. This process alters the incentive system comprising intellectual property (IP) ownership, managerial freedom, and rent sharing, which promotes IP commercialization. This study assesses the economic consequences of the incentive system reform, taking the example of a public innovation intermediary, Kohsetsushi. Unlike the incorporation of national universities, the incorporation of Kohsetsushi is at the discretion of local governments. Therefore, there should be a comparative advantage for both incorporated and unincorporated Kohsetsushi. A dataset representative of both types of Kohsetsushi was established to estimate the average treatment effects on the treated (ATT), identify the type of selection into incorporation, and discuss the economic consequences of endogenous selection by local governments. The counterfactual analysis of licensing income revealed a negative ATT of incorporation and negative selection into not choosing incorporation. Incorporated Kohsetsushi would have had higher licensing income had they not been incorporated. The evidence does not support comparative advantage. The unintended consequence might have been caused by the lack of harmonization between the incentive and evaluation systems.

Tension zone trapped by exogenous cline: Analysis of a narrow hybrid zone between two parapatric Oxytropis species (Fabaceae).

Hybrid zones have been widely highlighted for their interest in understanding evolutionary processes. It is generally accepted that hybrid zones can be maintained in a balance between dispersal and selection. However, the selective forces can either be endogenous (i.e., genetic incompatibilities between parental taxa) or exogenous (i.e., parental taxa are adapted to different environments). In this study, we evaluated these alternatives and determined the maintenance of a narrow hybrid zone between parapatric distributed Oxytropis diversifolia and O. leptophylla in Nei Mongol, China. For 507 individuals sampled from two populations in the hybrid zone, 12 O. diversifolia populations and five O. leptophylla populations, we measured leaf‐morphological characteristics, quantified genetic structure using 11 nuclear microsatellite loci and five chloroplast DNA intergenic regions, collected micro‐ and macrohabitat data, and conducted geographical cline analysis. We found that the two species differed in leaf morphology, and putative hybrids showed either intermediacy or a bias to O. diversifolia. Parental taxa formed two genetically distinct clusters, while populations in the hybrid zone consisted of both parental forms and various admixed individuals, exhibiting a bimodal pattern. The hybrid zone was coupled to ecological transitions of both microhabitat (i.e., the slope) and macroclimatic conditions. However, the genetic clines were significantly narrower than the environmental cline. Our results indicate that endogenous selection can be primarily responsible for maintaining the hybrid zone, while local adaptation accounts for the position of the zone. We further suggest the probable outcome of hybridization could be introgression.

Heterogeneity in the Effect of Environmental Protection Expenditure in China: Causal Inference from Machine Learning

ABSTRACT The amount of fiscal expenditure on environmental governance in various regions of China in recent years has increased greatly, but its effect on environmental protection is often controversial in existing research. The conflicting finding is largely due to endogenous problems or selection bias. Generally, the cities with high smog pollution have been encountering environmental protection expenditure (EPE) shocks more greatly since 2011. To estimate the causal effects of EPE shocks more accurately, this research uses new machine learning to the estimate heterogeneous treatment effect of the EPE shock on urban air pollution from 216 cities in China, from 2011 to 2018. Empirical results from causal forests show the following. First, the positive EPE shock has contributed to China’s short-term improvements in air pollution. Long-term causality has not been confirmed statistically, though there is a strong correlation between an increase in EPE and a decrease in PM2.5. Second, a positive EPE shock leads to deterioration of smog in low-income and above-medium smog areas in the long term. Third, the positive EPE shock is conducive to the long-term improvement of air quality in moderately industrialized areas, but it does not lead to the long-term improvement of urban air pollution with a high or low degree of industrialization. Similarly, an EPE shock in cities with medium population density improves air quality for a long time, but runs the opposite in cities with high or low population density.

Training, Recruitment, and Outplacement as Endogenous Adverse Selection

This paper presents a model of a competitive labour market where workers vary in firm‐specific and general skills, and firms choose the kind of information to disclose. We show that provision of general training, recruitment, and outplacement are linked. Disclosing general human capital information on bad matches but revealing nothing about good matches (information disclosure that resembles outplacement support in professional service firms) leads to an efficient allocation of workers and creates adverse selection that enables workers to pay for general training. It also implies that wages of released workers can be higher than wages of those who are retained.

Cigarette smoking and quitting by individuals in Malaysia

ABSTRACT Objectives Understanding the sociodemographic characteristics associated with cigarette smoking and quitting decisions allows policy decision-making to attempt to curtail smoking. Individual smoking and quitting decisions are examined using an endogenous sample selection model. Methods Using data for 4,110 individuals from the 2011 Malaysian Global Adult Tobacco Survey, a probit model is estimated for quitting, subject to sample selection for smokers. Marginal effects of exposure variables are calculated for the probability of smoking and probability of quitting conditional on smoking. Results Ethnic Malays/Bumiputera, urbanites, ignorance of the hazards associated with secondhand smoke, lack of smoking rules at home, and lack of religious restriction contribute to smoking likelihoods. Older age, being a female, ethnic Chinese, married, at home smoking prohibition, and knowledge of secondhand smoke risks are associated with higher probability of quitting conditional upon smoking. Working in non-government occupations, individuals of other ethnic background, and smoking consent at home are associated with lower quitting probability conditional upon smoking. Conclusion Health awareness and educational programs should be directed at specific population groups with the above sociodemographic characteristics to discourage smoking initiation and promote quitting among smokers.

The reward and contract theories of patents in a model of endogenous growth

I develop a general equilibrium model of endogenous growth to jointly analyze two distinct theories of the patent system’s social value: (1) that patents stimulate innovation by enhancing private incentives to invest in R&D (reward theory) and (2) that patents disseminate technical information into the public domain through disclosure requirements (contract theory). The model features endogenous innovator selection into patents versus secrecy based on heterogeneous innovation size, the effective cost of disclosure, and expected licensing revenue from holding a patent. Innovation is cumulative, patent rights overlap across industries, and new innovators pay mandatory licensing fees to a subset of previous innovators if those innovators hold a patent. The economy’s endogenous patent propensity determines each new innovator’s licensing burden, consistent with the concept of patent thickets. The model captures the inherent tension between the two objectives of the patent system. In most cases, I find that stronger patent protection stifles innovation and reduces social welfare.

Financing new entrepreneurship: Credit or microcredit?

Building on the theory of information asymmetry, we investigate the impact of conventional banking versus the impact of microfinance on new entrepreneurship. We use a panel dataset collected from 49 developing countries between 2003 and 2018 and apply a random effects linear regression model with endogenous sample selection. We show, among other results, that conventional banking has no direct impact on new entrepreneurship. In contrast to conventional banking, microfinance appears to promote the growth of new entrepreneurship. However, as the conventional banking sector grows, the positive impact of microfinance on new entrepreneurship diminishes.

Interactions among endogenous, exogenous, and agency-driven attentional selection mechanisms in interactive displays.

Attentional selection is driven, in part, by a complex interplay between endogenous and exogenous cues. Recently, one's interactions with the physical world have also been shown to bias attention. Specifically, the sense of agency that arises when our actions cause predictable outcomes biases our attention toward those things which we control. We investigated how this agency-driven attentional bias interacts with simultaneously presented endogenous (words) and exogenous (color singletons) environmental cues. Participants controlled the movement of one object while others moved independently. In a subsequent search task, targets were either the previously controlled objects or not. Targets were also validly or invalidly cued. Both cue types influenced attention allocation. Endogenous cues and agency-driven attentional selection were independent and additive, indicating they are separable mechanisms of selection. In contrast, exogenous cues eliminated the effects of agency, indicating that perceptually salient environmental cues can override internally derived effects of agency. This is the first demonstration of a boundary condition on agency-driven selection.

Does poor quality housing impact on child health? Evidence from the social housing sector in Avon, UK

The correlation between poor quality housing and children's physical health has been well documented. Yet a limitation of the literature is the prevalence of selection bias and comparatively little evidence on children's mental health outcomes. This study explored the role of housing (and neighbourhood) quality in explaining differences in childhood mental and physical health between those living in social-rented flats and houses. The social housing allocation process mitigated unobserved differences across the two groups addressing some of the issues of endogenous selection, although stopping short of representing causal identification. Poorer housing quality explained over 50% of the 0.18 standard deviation deficit in the mental health of children in flats compared with houses, with primary mediators being damp and mould, home temperature, and mother's perception of her own home, but played no role in explaining physical health deficits of children in flats. In contrast, neighbourhood quality did not account for any of the mental and physical health deficits observed. Taken together, the present study adds to the evidence that the home environment of children in social housing is related to their development, whilst taking us beyond the existing literature in terms of accounting for selection bias.

Did clickbait crack the code on virality?

Although clickbait is a ubiquitous tactic in digital media, we challenge the popular belief that clickbait systematically leads to enhanced sharing of online content on social media. Using the Persuasion Knowledge Model, we predict that clickbait tactics may be perceived by some readers as a manipulative attempt, leading to source derogation where the publisher may be perceived as less competent and trustworthy. This, in turn, may reduce some readers’ intention to share content. Using a controlled experiment, we confirm that high-emotional headlines are shared more and show evidence that clickbait often leads to inferences of manipulative intent and source derogation. We then use a well-known secondary data set containing 19,386 articles from 27 leading online publishers. We supplement it with Twitter share data, sentiment analysis, topic modeling, and additional control variables. We confirm that, on average, clickbait articles elicit far fewer shares than non-clickbait articles. Our results are stable, with large effect sizes even after controlling for endogenous selection.Supplementary InformationThe online version contains supplementary material available at 10.1007/s11747-021-00830-x.

Endogenous viral mutations, evolutionary selection, and containment policy design

How will the novel coronavirus evolve? I study a simple epidemiological model, in which mutations may change the properties of the virus and its associated disease stochastically and antigenic drifts allow new variants to partially evade immunity. I show analytically that variants with higher infectiousness, longer disease duration, and shorter latent period prove to be fitter. “Smart” containment policies targeting symptomatic individuals may redirect the evolution of the virus, as they give an edge to variants with a longer incubation period and a higher share of asymptomatic infections. Reduced mortality, on the other hand, does not per se prove to be an evolutionary advantage. I then implement this model as an agent-based simulation model in order to explore its aggregate dynamics. Monte Carlo simulations show that a) containment policy design has an impact on both speed and direction of viral evolution, b) the virus may circulate in the population indefinitely, provided that containment efforts are too relaxed and the propensity of the virus to escape immunity is high enough, and crucially c) that it may not be possible to distinguish between a slowly and a rapidly evolving virus by looking only at short-term epidemiological outcomes. Thus, what looks like a successful mitigation strategy in the short run, may prove to have devastating long-run effects. These results suggest that optimal containment policy must take the propensity of the virus to mutate and escape immunity into account, strengthening the case for genetic and antigenic surveillance even in the early stages of an epidemic.

When less conditioning provides better estimates: overcontrol and endogenous selection biases in research on intergenerational mobility

The counterfactual approach to causality has become the dominant approach to understand causality in contemporary social science research. Whilst most sociologists are aware that unobserved, confounding variables may bias the estimates of causal effects (omitted variable bias), the threats of overcontrol and endogenous selection biases are less well known. In particular, widely used practices in research on intergenerational mobility are affected by these biases. I review four of these practices from the viewpoint of the counterfactual approach to causality and show why overcontrol and endogenous selection biases arise when these practices are implemented. I use data from the German Socio-Economic Panel Study (SOEP) to demonstrate the practical consequences of these biases for conclusions about intergenerational mobility. I conclude that future research on intergenerational mobility should reflect more upon the possibilities of bias introduced by conditioning on variables.

Heterogeneous Peer Effects Under Endogenous Selection: An Application to Local and Migrant Children in Elementary Schools in Shanghai

Heterogeneous Peer Effects Under Endogenous Selection: An Application to Local and Migrant Children in Elementary Schools in Shanghai