Search

This paper studies the effects of peers on the adoption of a Youth Employment Subsidy in Chile since its inception. We examine the effects that former classmates' and coworkers' adoption have on one's adoption. Identification comes from discontinuities in the assignment rule that allow us to construct valid instrumental variables for peers' adoption. Using a comprehensive set of administrative records, we find that classmates and especially coworkers play significant roles in the adoption of the subsidy. Peer effects are determined during the early stages of the program's implementation and vary by network characteristics and the strength of network ties.

This paper provides causal evidence that greater minority representation on school boards translates into greater investment in minority students. Focusing on California school boards, I obtain causal effects by instrumenting for minority (specifically, Hispanic) school board representation using the random order in which candidates appear on election ballots. Given the dearth of school-level expenditure data, I introduce detailed records from California’s School Facility Program (SFP), a capital investment program for which I observe how school boards allocate the marginal dollar within district. Instrumental variables estimates show that an additional Hispanic school board member increases SFP-funded investments at high-Hispanic schools within the district by 69 percent, with significantly lower effects at low-Hispanic schools. High-Hispanic schools also exhibit gains in student achievement of 0.08 standard deviations. I attribute this improved performance broadly to increased investment in these schools: new instructor hiring at high-Hispanic schools decreases by 23 percent. These results provide the first causal evidence that school board politics—and, specifically, school board ethnic composition—shapes education finance policy at the local level. I conclude that enhancing minority representation on school boards could help combat disparities in education finance and achievement.

Efficient computational algorithms for bootstrapping linear regression models with clustered data are discussed. For ordinary least squares (OLS) regression, a new algorithm is provided for the pairs cluster bootstrap, along with two algorithms for the wild cluster bootstrap. One of these is a new way to express an existing method. For instrumental variables (IV) regression, an efficient algorithm is provided for the wild restricted efficient cluster (WREC) bootstrap. All computations are based on matrices and vectors that contain sums of squares and cross-products for the observations within each cluster, which have to be computed just once before the bootstrap loop begins. Monte Carlo experiments are used to study the finite-sample properties of bootstrap Wald tests for OLS regression and of WREC bootstrap tests for IV regression.

Structural equation models (SEMs) are widely used to handle multiequation systems that involve latent variables, multiple indicators, and measurement error. Maximum likelihood (ML) and diagonally weighted least squares (DWLS) dominate the estimation of SEMs with continuous or categorical endogenous variables, respectively. When a model is correctly specified, ML and DWLS function well. But, in the face of incorrect structures or nonconvergence, their performance can seriously deteriorate. Model implied instrumental variable, two stage least squares (MIIV-2SLS) estimates and tests individual equations, is more robust to misspecifications, and is noniterative, thus avoiding nonconvergence. This article is an overview and tutorial on MIIV-2SLS. It reviews the six major steps in using MIIV-2SLS: (a) model specification; (b) model identification; (c) latent to observed (L2O) variable transformation; (d) finding MIIVs; (e) using 2SLS; and (f) tests of overidentified equations. Each step is illustrated using a running empirical example from Reisenzein's (1986) randomized experiment on helping behavior. We also explain and illustrate the analytic conditions under which an equation estimated with MIIV-2SLS is robust to structural misspecifications. We include additional sections on MIIV approaches using a covariance matrix and mean vector as data input, conducting multilevel SEM, analyzing categorical endogenous variables, causal inference, and extensions and applications. Online supplemental material illustrates input code for all examples and simulations using the R package MIIVsem. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Problem definition: We present a data-driven study of the secondary ticket market. In particular, we are primarily concerned with accurately estimating price sensitivity for listed tickets. In this setting, there are many issues including endogeneity, heterogeneity in price sensitivity for different tickets, binary outcomes, and nonlinear interactions between ticket features. Our secondary goal is to highlight how this estimation can be integrated into a prescriptive trading strategy for buying and selling tickets in an active marketplace. Academic/practical relevance: We present a novel method for demand estimation with heterogeneous treatment effect in the presence of confounding. In practice, we embed this method within an optimization framework for ticket reselling, providing the ticket reselling platform with a new framework for pricing tickets on its platform. Methodology: We introduce a general double/orthogonalized machine learning method for classification problems. This method allows us to isolate the causal effects of price on the outcome by removing the conditional effects of the ticket and market features. Furthermore, we introduce a novel loss function that can be easily incorporated into powerful, off-the-shelf machine learning algorithms, including gradient boosted trees. We show how, in the presence of hidden confounding variables, instrumental variables can be incorporated. Results: Using a wide range of synthetic data sets, we show this approach beats state-of-the-art machine learning and causal inference approaches for estimating treatment effects in the classification setting. Furthermore, using National Basketball Association ticket listings from the 2014–2015 season, we show that probit models with instrumental variables, previously used for price estimation of tickets in the resale market, are significantly less accurate and potentially misspecified relative to our proposed approach. Through pricing simulations, we show our proposed method can achieve an 11% return on investment by buying and selling tickets, whereas existing techniques are not profitable. Managerial implications: The knowledge of how to price tickets on its platform offers a range of potential opportunities for our collaborator, both in terms of understanding sellers on their platform and in developing new products to offer them. History: This paper has been accepted as part of the 2019 Manufacturing & Service Operations Management Practice-Based Research Competition. Funding: This work was supported by the National Science Foundation [Grant CMMI-1563343]. Supplemental Material: The online appendices are available at https://doi.org/10.1287/msom.2021.1065 .

Generation X directors are slowly replacing Baby Boomers on U.S. corporate boards and will eventually dominate corporate boardrooms in the U.S. and around the world. We provide the first robust evidence of a significantly positive effect of Generation X directors on corporate performance. The positive effect is not driven by other director attributes such as age, sex, ethnicity, or professional expertise, and is robust to endogeneity checks using instrumental variables. Part of the improvement in firm performance can be attributed to the commitment of Generation X directors to corporate social responsibility and to the inclusion of women on corporate boards.

This paper studies second-order properties of the many instruments robust t -ratios based on the limited information maximum likelihood and Fuller estimators for instrumental variable regression models with homoskedastic errors under the many instruments asymptotics, where the number of instruments may increase proportionally with the sample size n , and proposes second-order refinements to the t -ratios to improve the size and power properties. Based on asymptotic expansions of the null and non-null distributions of the t -ratios derived under the many instruments asymptotics, we show that the second-order terms of those expansions may have non-trivial impacts on the size as well as the power properties. Furthermore, we propose adjusted t -ratios whose approximation errors for the null rejection probabilities are of order O ( n − 1 ) in contrast to the ones for the unadjusted t -ratios of order O ( n − 1 / 2 ) , and show that these adjustments induce some desirable power properties in terms of the local maximinity. Although these results are derived under homoskedastic errors, we also establish a stochastic expansion for a heteroskedasticity robust t -ratio, and propose an analogous adjustment under slight deviations from homoskedasticity.

The existing framework of Mendelian randomization (MR) infers the causal effect of one or multiple exposures on one single outcome. It is not designed to jointly model multiple outcomes, as would be necessary to detect causes of more than one outcome and would be relevant to model multimorbidity or other related disease outcomes. Here, we introduce Multi-response Mendelian randomization (MR2), a novel MR method specifically designed for multiple outcomes to identify exposures that cause more than one outcome or, conversely, exposures that exert their effect on distinct responses. MR2uses a sparse Bayesian Gaussian copula regression framework to detect causal effects while estimating the residual correlation between summary-level outcomes, i.e., the correlation that cannot be explained by the exposures, andviceversa. We show both theoretically and in a comprehensive simulation study how unmeasured shared pleiotropy induces residual correlation. We also reveal how non-genetic factors that affect more than one outcome contribute to their correlation. We demonstrate that by accounting for residual correlation, MR2has higher power to detect shared exposures causing more than one outcome. It also provides more accurate causal effect estimates than existing methods that ignore the dependence between related responses. Finally, we illustrate how MR2detects shared and distinct causal exposures for five cardiovascular diseases in two applications considering cardiometabolic and lipidomic exposures and uncovers residual correlation between summary-level outcomes reflecting known relationships between cardiovascular diseases.

This paper explores the role of cash usage in feeding the underground economy by using a unique dataset that combines, at province level, official estimates of Italian firms’ underreporting with data on cash transactions drawn from the aggregate anti-money laundering reports filed to the Italian Financial Intelligence Unit (UIF) by banks. In order to derive causal evidence, we apply two different econometric strategies: an instrumental variable approach and a difference-in-difference approach, which exploits the change in the maximum threshold for cash transactions introduced in 2016, thereby providing a measure of the effect of such policy on tax evasion. We find that an increase in cash usage translates, other things being equal, into a higher level of underreporting by firms, and that raising the cash threshold in 2016 – a measure motivated by the objective of boosting spending – had the side effect of leading to a larger underground economy.

We quantify the relationship between the response of output to monetary policy shocks and the share of liquidity-constrained households. We do so in the context of the euro area, using a Local Projections Instrumental Variables estimation. We construct an instrument for changes in interest rates from changes in overnight indexed swap rates in a narrow time window around ECB announcements. Monetary policy shocks have heterogeneous effects on output across countries. Using micro data, we show that the elasticity of output to monetary policy shocks is larger in countries that have a larger fraction of households that are liquidity constrained. (JEL E23, E43, E52, F33, F45, G51)

This paper considers the problem of variable selection for a class of linear regression models with instrumental variables. We focus on the case that the covariates are endogenous variables, and some auxiliary instrumental variables are available. An instrumental variable based variable selection procedure is proposed by using a modified smooth-threshold estimating equations (SEE). The proposed method can attenuate the effect of endogeneity of covariates, and can avoid the convex optimization problem. Hence, it is flexible and easy to implement. Simulation results indicate that the proposed variable selection method is workable.

Firms sharing a board member with a media company receive more news coverage. This in turn affects those firms’ financing choices: they issue more bonds, rely less on bank loans, and have lower blockholder ownership. These findings are consistent with media coverage acting as an external governance mechanism that substitutes for monitoring by banks and equity blockholders. The effect of media-linked directors on financing is evident in panel and time series analyses and using two different instrumental variable analyses, suggesting a causal relation.

Two-year community colleges enroll nearly half of all first-time undergraduates in the United States, but to ambiguous effect: low persistence rates and the potential for diverting students from four-year institutions cast ambiguity over two-year colleges’ contributions to upward mobility. This paper develops a new instrumental variables approach to identifying causal effects along multiple treatment margins, and applies it to linked education and earnings registries to disentangle the net impacts of two-year college access into two competing causal margins: significant value added for two-year entrants who otherwise would not have attended college, but negative impacts on students diverted from immediate four-year entry. (JEL I23, I26, I28, J24, J31)

This paper estimates wider economic impacts related to productivity from transport networks in Hong Kong in 2016. Specifically, we use an instrumental variable approach to identify the causal effect of transport network centralities on productivity measured by gross value added. Our identification strategy largely relies on the exogenous variations from historical planned and existing transport networks. To the best of our knowledge, this is the first paper that makes use of complex network science indicators of accessibility combining urban rail, road network, and pedestrian network in capturing wider economic impacts. Our results confirm that pedestrian and rail networks can statistically significantly increase productivity in Hong Kong while roads play a less significant but still meaningful role. The research suggests a key planning policy implication: place-based policies in a dense city require a combination of local and global transport accessibility improvement which facilitates both agglomeration and decentralization.

This paper re-examines the problem of estimating risk premia in unconditional linear factor pricing models. Typically, the data used in the empirical literature are characterized by weakness of some pricing factors, strong cross-sectional dependence in the errors, and (moderately) high cross-sectional dimensionality. Using an asymptotic framework where the number of assets/portfolios grows with the time span of the data while the risk exposures of weak factors are local-to-zero, we show that the conventional two-pass estimation procedure delivers inconsistent estimates of the risk premia. We propose a new estimation procedure based on sample-splitting instrumental variables regression. The proposed estimator of risk premia is robust to weak included factors and to the presence of strong unaccounted cross-sectional error dependence. We prove the consistency of the new estimator, establish asymptotically valid inferences using Wald statistics, verify performance of the new procedure in simulations, and revisit some empirical studies.

Poverty remains a substantial threat in rural areas of many developing countries, and solving this problem requires an in-depth understanding of the income generating capacity that determines poverty. This paper examines the impact of agricultural commercialisation on the capability of rural households to accumulate and productively use assets and reduce structural and multidimensional poverty. A longitudinal dataset of around 2000 households with a total of 9781 observations from five rural surveys undertaken in the period 2008–2017 in Vietnam is used. Results from a fixed effects regression with an instrumental variable and a control function approach show that agricultural commercialisation has a positive effect on the accumulation of assets and reduces multidimensional and structural poverty over time. However, the effect is not homogeneous and is larger for households that are not mainly engaged in rice commercialisation. This suggests that commercialisation can be a path out of poverty, especially if policy makers move towards utilising other crops instead of rice.

We examine the effect of health facility births on newborn mortality in Malawi using data from a unique survey of mothers in the Chimutu district, Malawi and data from the Malawi Demographic and Health Survey 2015. The study exploits two instrumental variables to overcome endogeneity of health facility births—labor contraction time and interaction of distance to health facilities and rainfall at birth. The results show that health facility births significantly reduce 7-day and 28-day mortality rates. We find suggestive evidence that readily available medical resources are the potential mechanisms through which health facility births reduce newborn mortality.

This paper analyzes whether money influences election outcomes. Using a new and more comprehensive dataset built from government sources, the paper shows that the relations between money and votes cast for major parties in elections for the U.S. Senate and House of Representatives from 1980 to 2018 are well approximated by straight lines. It then considers possible challenges to this “linear model” of money and elections on statistical grounds, resting on possible endogeneity arising from reciprocal causation between, for example, popularity and votes. The paper develops a spatial Bayesian latent instrumental variable model to tackle this much discussed problem. It checks its results by studying relations between changes in gambling odds and contributions in key elections. Both approaches suggest that reciprocal causation may happen to some degree, but that money’s independent influence on elections remains powerful.

We examine how online customer reviews for one generation of a product affect sales of another generation in the same product series. The main intriguing result is that previous generation valence has a positive impact on current generation sales; however, current generation valence has a negative impact on previous generation sales. The positive impact of previous generation valence becomes even stronger (1) as the uncertainty (standard deviation) in reviews for the current generation increases and (2) when the current generation valence is high. In contrast, it becomes weaker (1) as the uncertainty in reviews for the previous generation increases and (2) when the current generation has been on the market for a longer period of time. Other results are discussed. Our data consist of intergenerational pairs of point-and-shoot cameras on the largest online seller of such devices, Amazon.com. We estimate the current and previous generation models jointly, allowing for errors to be clustered at the daily and product levels. In addition, we address endogeneity concerns over the online word of mouth measures by using instrumental variables. This paper was accepted by Juanjuan Zhang, marketing.

This study addresses the ubiquitous challenge of using big observational data to identify heterogeneous treatment effects. This problem arises in precision medicine, targeted marketing, personalized education, and many other environments. Identifying heterogeneous treatment effects presents several analytical challenges including high dimensionality and endogeneity issues. We develop a new instrumental variable tree (IVT) approach that incorporates the instrumental variable method into a causal tree (CT) to correct for potential endogeneity biases that may exist in observational data. Our IVT approach partitions subjects into subgroups with similar treatment effects within subgroups and different treatment effects across subgroups. The estimated treatment effects are asymptotically consistent under a set of mild assumptions. Using simulated data, we show our approach has a better coverage rate and smaller mean-squared error than the conventional CT approach. We also demonstrate that an instrumental variable forest (IVF) constructed using IVTs has better accuracy and stratification than a generalized random forest. Finally, by applying the IVF approach to an empirical assessment of laparoscopic colectomy, we demonstrate the importance of accounting for endogeneity to make accurate comparisons of the heterogeneous effects of the treatment (teaching hospitals) and control (nonteaching hospitals) on different types of patients. This paper was accepted by J. George Shanthikumar, big data analytics.

By providing quick and easy access to credit, online lending platforms may help borrowers overcome financial setbacks and/or refinance high-interest debt, thereby decreasing bankruptcy filings. On the other hand, these platforms may cause borrowers to overextend themselves financially, leading to a “debt trap” and increasing bankruptcy filings. To investigate the impact of online lending on bankruptcy filings, we leverage variation in when state regulators granted approval for a major online lending platform—Lending Club—to issue peer-to-peer loans. Using a difference-in-differences approach, we find that state approval of Lending Club led to an increase in bankruptcy filings. A complementary instrumental variables analysis using loan-level data yields similar results. We find suggestive evidence that the ease of receiving a Lending Club loan causes some borrowers to overextend themselves financially, leading to bankruptcy. Our results suggest that recent initiatives from online lending platforms to control how borrowers use loans, such as Lending Club’s “balance transfer loans” that send loan funds directly to creditors, can help these platforms provide safe and affordable credit. Our study adds to the literature that examines how online platforms influence society and the economy; it contributes to the literature that examines how financial products, services, and regulations influence bankruptcy filings; and it has policy implications for online lending design and regulation. This paper was accepted by Lorin Hitt, information systems.

Pharmaceutical firms typically enjoy market exclusivity for new drugs from concurrent protection of the underlying invention (through patents) and the clinical trials data submitted for market approval (through data exclusivity). Patent invalidation during drug development renders data exclusivity the sole source of protection and shifts the period of market exclusivity at the project level. Patent invalidation therefore constitutes a natural experiment that allows us to causally identify how the duration of market exclusivity affects firms' incentives to innovate. In instrumental variables regressions we quantify the effect of a one-year reduction in expected market exclusivity on the likelihood of drug commercialization. We provide first estimates of the responsiveness of R&D investments to market exclusivity expectations and hereby inform the ongoing policy debate on the regulation of intellectual property rights in the pharmaceutical industry.

Bias correction in predictive regressions is known to reduce the empirical size problems of OLS-based predictability tests with persistent predictors. This paper shows that bias correction is also achieved in the context of the extended instrumental variable (IVX) predictability testing framework introduced by Kostakis et al. (2015). To be specific, new IVX-based statistics subject to a bias correction analogous to that proposed by Amihud and Hurvich (2004) are introduced. Four important contributions are provided: first, we characterize the effects that bias-reduction adjustments have on the asymptotic distributions of the IVX test statistics in a general context allowing for short-run dynamics and heterogeneity; second, we discuss the validity of the procedure when predictors are stationary as well as near-integrated; third, we conduct an exhaustive Monte Carlo analysis to investigate the small in- and out-of-sample properties of the test procedures and their sensitivity to distinctive features that characterize predictive regressions in practice, such as strong persistence, endogeneity, and non-Gaussian innovations; and fourth, we provide an analysis of real estate return and rent growth predictability in 19 OECD countries.

Assumptions of competitive structure are often crucial for marginal cost estimation and counterfactual predictions. This paper introduces tests for price competition among multi-product firms. The tests are based on the firm’s revealed preference (revealed profit function). In contrast to other approaches based on estimated demand functions such as conduct parameter estimation, the proposed tests do not require any instrumental variables, even though the models can accommodate structural error terms. In this paper, I employ a demand structure introduced by Nocke and Schutz (Econometrica 86(2):523–557, 2018. https://doi.org/10.3982/ECTA14720), the discrete/continuous choice model, which nests the multinomial logit demand and CES demand functions. Any price and quantity data can be rationalized by price competition under a discrete/continuous choice model and increasing marginal costs. Adding more assumptions to the demand functions, such as logit, CES, or the co-evolving and log-concave property produces some falsifiable restrictions.

This paper proposes new jackknife IV estimators that are robust to the effects of many weak instruments and error heteroskedasticity in a cluster sample setting with cluster-specific effects and possibly many included exogenous regressors. The estimators that we propose are designed to properly partial out the cluster-specific effects and included exogenous regressors while preserving the re-centering property of the jackknife methodology. To the best of our knowledge, our proposed procedures provide the first consistent estimators under many weak instrument asymptotics in the setting considered. We also present results on the asymptotic normality of our estimators and show that t-statistics based on our estimators are asymptotically normal under the null and consistent under fixed alternatives. Our Monte Carlo results further show that our t-statistics perform better in controlling size in finite samples than those based on alternative jackknife IV procedures previously introduced in the literature.

Instrumental variable (IV) strategies are commonly used in political science to establish causal relationships, yet the identifying assumptions required by an IV design are demanding and it remains challenging for researchers to evaluate their plausibility. We replicate 61 papers published in three top journals in political science from the past decade (2011-2020) and document several troubling patterns: (1) researchers often miscalculate the first-stage F statistics, overestimating the strength of their IVs; (2) most researchers rely on classical asymptotic standard errors, which often severely underestimate the uncertainties around the two-stage-least-squared (2SLS) estimates; (3) in the majority of the replicated studies, the 2SLS estimates are much bigger than the ordinary-least-squared estimates, and their ratio is negatively correlated with the strength of the IVs in studies where the IVs are not experimentally generated, suggesting potential violations of the exclusion restriction; such a relationship is much weaker with experimentally generated IVs. To improve practice, we provide a checklist for researchers to avoid these pitfalls and recommend a zero-first-stage test and a local-to-zero procedure to guard against failure of the identifying assumptions.

In this paper, we show that trust favors specialization in complexity. U.S. states with a high level of generalized trust tend to specialize in industries involving more complex input-output relationships. This pattern is not driven by differences in the states’ other observable characteristics or unobservable time-varying industry- or state-specific factors and does not reflect selection by export destination. Although theoretical considerations suggest that trust may be endogenous to the location of complex industries, an instrumental variable strategy that leverages the impact of racial discrimination confirms that trust is a factor in the specialization of U.S. states in more complex industries.

This study shows that banking organization growth is associated with higher operational losses per dollar of total assets and incidence of tail risks. Event studies using M&A activity and instrumental variable regressions provide consistent evidence. The relationship between banking organization growth and operational risk varies by loss event types and balance sheet categories. We demonstrate that higher growth predicts worse operational risk realizations during the global financial crisis. These findings have implications for bank performance, risk management and supervision in a continually consolidating banking industry.

The increasing rate of obesity in the U.S., particularly among low-income households, necessitates a thorough understanding of the relationship between obesity and in-kind federal benefits such as the Supplemental Nutrition Assistance Program (SNAP), formerly the Food Stamp Program. However, when examining this relationship, the existing literature often ignores evidence that respondents frequently misreport their participation in SNAP. This paper studies the impact of such misreporting on the estimated average treatment effect (ATE) of SNAP participation on adult obesity. Our analysis also synthesizes the current empirical techniques available for estimating ATEs in light of misreported treatment participation, adopting a range of parametric analyses as well as nonparametric bounds. The results highlight the inherent bias of common point estimates when ignoring misreporting, with treatment effects from instrumental variable methods exceeding the nonparametric bounds by over 200% in some cases. Accounting for misreporting, the estimated effects of SNAP participation on obesity are largely inconclusive. We find a slight negative effect of SNAP participation on the probability of being overweight, but the results specific to gender remain inconclusive due to the high rates of misreporting, particularly among men.

We propose to examine the mortality consequences of receiving Supplemental Security Income (SSI). Relatedly, we will also examine whether decreasing administrative burden has mortality consequences through higher take-up rates. We leverage random assignment of a prior Social Security Administration demonstration field experiment, which exogenously increased take-up among eligible beneficiaries (Hemmeter et al. 2020), to causally identify the effect of SSI on mortality using mailed-letter assignment as an instrumental variable. The initial study identified over 4 million adults 65 or older who were potentially-eligible for SSI and randomly sent letters to 10 percent of them in September 2017, informing them of their potential eligibility. It found that these letters, a form of low-cost nudge that reduced learning costs, increased SSI applications by 600 percent (or 5.0 percentage points) and led to an increase in SSI awards of 340 percent (or 1.8 percentage points) over the study period. In this study, we take advantage of the random assignment to letters and use it as an exogenous leverage to estimate the effects of SSI award on recipient’s mortality in a two-stage estimation procedure.

This paper provides sufficient conditions for identification of a nonparametric regression model with an unobserved continuous regressor subject to nonclassical measurement error. The measurement error may be directly correlated with the latent regressor in the model. Our identification strategy does not require the availability of additional data information, such as a secondary measurement, an instrumental variable, or an auxiliary sample. Our main assumptions for nonparametric identification include monotonicity of the regression function, independence of the regression error, and completeness of the measurement error distribution. We also propose a sieve maximum likelihood estimator and investigate its finite sample property through Monte Carlo simulations.

Public firms have wide latitude to release descriptive research and development (R&D) information. Conceptually, a higher descriptive R&D intensity (DRDI) enables a more thorough assessment of a firm’s prospects and reduces information asymmetry. However, such disclosure may undermine the firm’s future competitive advantages by allowing competitors to observe the firm’s R&D efforts more closely. By analyzing the textual content of 23,269 annual reports and leveraging the staggered statewide rejection of the inevitable disclosure doctrine as our instrumental variable for DRDI, we find that DRDI positively affects firm value. We also find that the presence of Chief Innovation Officer and intangible know-how positively, while financial leverage and market turbulence negatively, moderate the effect of DRDI on firm value. Notably, although both DRDI and numerical R&D intensity (NRDI) deliver potentially valuable information about R&D activities, DRDI is distinct from and has a more significant explanatory power of firm value than NRDI.

Members of Congress represent geographically demarcated districts embedded in subnational policy environments. Drawing on policy feedback literature and literature on congressional representation, I argue that, because of this institutional configuration, subnational policy adoption can affect national representation. More specifically, policy reforms in the states they represent can increase pressures members face from organized groups and individuals in their constituencies to promote aligned federal policies. Empirically, I examine the effects of state marijuana legalization. The inferential design leverages differences across the states in statewide citizen initiative institutions, which provides exogenous variation in legalization. Instrumental variables analysis indicates legalization influenced pro-marijuana bill sponsorship and roll calls in the 116th Congress. The evidence points to growing influence of industry in legalizing states—including the ability to mobilize employees and customers—as the key mechanism, thus underscoring the importance of a political economy perspective for studying interdependencies in American federalism.

This paper studies endogenous treatment effect models in which individuals are classified into unobserved groups based on heterogeneous treatment choice rules. Such heterogeneity may arise, for example, when multiple treatment eligibility criteria and different preference patterns exist. Using a finite mixture approach, we propose a marginal treatment effect (MTE) framework in which the treatment choice and outcome equations can be heterogeneous across groups. Under the availability of valid instrumental variables specific to each group, we show that the MTE for each group can be separately identified using the local instrumental variable method. Based on our identification result, we propose a two-step semiparametric procedure for estimating the group-wise MTE parameters. We first estimate the finite-mixture treatment choice model by a maximum likelihood method and then estimate the MTEs using a series approximation method. We prove that the proposed MTE estimator is consistent and asymptotically normally distributed. We illustrate the usefulness of the proposed method with an application to economic returns to college education.

Intellectual property rights protection (IPP) at destination countries is an important determinant of exports, a result shown by the existing literature. This paper empirically examines the effect of the degree of IPP on export product quality at the origins, using firm-product level data from Chinese exporters and city-level statistics of IPP. To establish the causal relationship, we employ an instrumental variable (IV) approach. Our panel regression results from 2008 to 2013 show that the de facto IPP contributes to the export product quality upgrading and the result is robust against variations of IPP measures, IVs, and different combinations of control variables such as the firm and industry level subsidies. Our heterogeneity results indicate that the betterment of IPP favors less capital-intensive firms; foreign-owned firms relative to domestic-owned firms; and firms in innovation-intensive industries. The effect of IPP on export product quality is statistically insignificant in certain geographic regions (i.e., central and western regions) and trade mode (i.e., processing trade). In addition, we show that the channels through which IPP takes effect on product quality include strengthened R&D input, new product development, and mitigated financial constraints.

Much of the analysis of panel data has been based on an assumption of strict exogeneity. Distributions are specified for outcome variables conditional on a latent individual effect and conditional on observed predictor variables at all dates, with the future values of the predictor variables assumed to have no effect on the conditional distribution. The paper relaxes this assumption in order to allow for lagged dependent variables and, more generally, for feedback from lagged dependent variables to current values of the predictor variables. Such feedback would arise in an evaluation study if the treatment variable is randomly assigned only conditional on the individual effect and on previous outcomes. An information bound is derived for a semiparametric regression model with sequential moment restrictions, with the information set increasing over time. The bound is then applied to a model with a (scalar) multiplicative random effect. The mean of the random effect conditional on the predictor variables is not restricted, so that the random effect can control for various omitted variables. This conditional mean is the nonparametric component of the semiparametric regression model. There is a transformation that eliminates the random effect and leads to a set of sequential moment restrictions in which the moment function depends on only a finite-dimensional parameter. The information bound for this simpler problem coincides with that of the original problem. The form of the optimal instrumental variables is derived. The paper also considers the identification problems that arise when the random effect is a vector with two or more components.

Residential electricity consumption in China experienced a boom in recent years and may increase faster in the future. To reduce residential electricity consumption, China has adopted Increasing Block Tariffs (IBT) since 2012. The previous work mainly used regional level aggregated data to assess the impact. Few studies using household level data did not overcome the endogeneity problem. Based on the instrumental variable method, this paper found that commonly used OLS estimation gave unreasonable results and instrumental variable method is appropriate and effective in this study. The IBT was found to significantly reduce residential electricity consumption in high-income group, which achieving the initial goal of China's IBT. Lastly, this paper proposed to generate more publicity of the IBT policy and increase the electricity price of second or third tier.

Green innovation can assist firms in achieving corporate social responsibility legitimacy among their stakeholders. However, we have limited knowledge about how to encourage firms toward it. Using a sample of Chinese firms, we examine the effect of executive equity incentive plans (EEIPs) on green innovation. Our baseline results indicate that EEIPs promote firms' green innovation and the importance of green patents in their patent portfolio. This positive effect is mainly exists in restricted stocks, rather than stock options. After addressing potential endogeneity problems by adopting instrumental variable regression method, difference-in-differences method and an entropy-balanced sample research design, we find a causal effect of EEIPs on green innovation. This positive effect is pronounced in firms facing greater environmental risks. Further analysis suggests that green innovation helps in promoting the firm's environmental outcomes, without an adverse effect on performance.

This study investigates the effects of social trust on corporate leverage in China with the data of listed companies and Chinese General Social Survey. Results reveal that social trust has a positive impact on corporate leverage, and this result remains robust when terrain is used as an instrumental variable. Social trust also further affects corporate leverage in central cities with high gross domestic product per capita, indicating that the impacts of social trust depend on local development as well. Social trust has similar impacts on long- and short-term leverage, but it does not affect commercial credit leverage like how it affects bank credit leverage. The possible channels are through the corporate responsibility to shareholder and local financial development. Another impact of social trust on leverage is through that of liabilities. Furthermore, improving local formal institutions may change the effects of social trust. Our results remain unchanged after robustness checks.

This paper analyzes the effects of exchange rate volatility on exports and imports of a range of goods between Russia and its 70 trading partners from 2004 until 2018. The goods in question fall into eight product categories, as follows: (i) agricultural raw materials­; (ii) chemicals; (iii) food; (iv) fuels; (v) manufactured goods; (vi) ores and metals­; (vii) textiles; and (viii) machinery and transport equipment. Exchange rate volatility­ is measured using the standard deviation of the first difference in the logarithmic daily nominal exchange rate. The paper concludes that exchange rate volatility had a negative impact on exports of agricultural raw materials, manufactured goods, and machinery and transport equipment. In contrast, it was found to have a positive and significant impact on trade in fuels and imports of chemicals and textiles.

Retail distribution is one of the major challenges in emerging economies. These economies are volatile and filled with inefficiencies, and the representativeness of unstructured retail increases the complexity of distribution systems for consumer packaged-goods companies. We analyze 644 brands to extend the existing literature by modeling the retail distribution and market share in an emerging market according to the type of retail channel (full- and self-service channels), moderated by economic fluctuations and the market position of a brand (high- and low-share brands). Our model controls for endogeneity using instrumental variables (IVs) and accommodates heterogeneity across brands and categories by means of a fixed-effects robust regression. Our study highlights that the relationship between distribution and market share exhibits greater convexity in the self-service channel than in the full-service channel. Further, we contribute to the existing research in distribution effectiveness in emerging markets by showing the convex effect of distribution on market share could vary when the economy changes. Distribution gains are more effective in the self-service channel than in the full-service channel in times of economic decline. Also, the results indicate the higher degree of convexity in the relationship between distribution and market share for the self-service channel compared with the full-service channel is increased further for high-share brands than for low-share brands.

This study explores the impacts of migrants’ remittances and institutional quality on financial development in developing countries, and further tests the hypothesis that institutional quality influences the impact of remittances on financial development. Applying an unobserved dynamic factor model to 46 countries for the period of 1996 to 2016, a composite institutional quality index is first estimated that represents national institutional quality. Using fixed- and random-effects instrumental variable (IV) estimations, evidence is then provided that demonstrates that remittances and institutional quality promote financial development, and more importantly, that institutional quality can play a significant role in enhancing the impact of remittances on financial development, especially when institutional quality attains a certain high level. These results suggest that in countries with stronger institutions, remittances are transmitted more effectively and efficiently to promote financial development than in countries with weaker institutions. Moreover, in accordance with previous literature, financial openness and trade openness are shown to be critical for financial development.

The green economy is particularly important in China's pursuit of high-quality economic growth. Adopting China's provincial balance panel data from 2000 to 2017, this article attempts to reveal the impact of polycentric agglomeration on green total factor productivity, its action path, and the synergistic effect of market integration by employing instrumental variable estimation and a mediating effect model. A significant inverted U-shaped relationship is found between polycentric agglomeration and green total factor productivity, and the polycentric agglomeration in most provinces has not exceeded the inflection point. Furthermore, the mediating effect shows that functional urban specialization and technological innovation are effective paths through which polycentric agglomeration enhances green total factor productivity. Finally, market integration contributes to green total factor productivity, and a significant positive synergistic effect exists between market integration and polycentric agglomeration. Therefore, this paper argues that China should continue to develop polycentric agglomeration and accelerate the process of market integration to promote green economic efficiency.

Renewable energy markets have recently emerged in countries participating in the Belt and Road Initiative (BRI). Despite having abundant renewable energy resources, these countries contribute only a small share of global renewable energy investment. This study examines the nexus between governance, renewable energy investment, and trade openness for a sample of 51 BRI countries from 1996 to 2017. Specifically, the gravity model of trade is used to develop an instrumental variable for trade openness. The empirical findings reveal that political stability, the rule of law, regulatory quality, and corruption control are statistically significant factors that influence renewable energy investments in BRI countries. Moreover, this relationship seems to depend on the degree of trade openness. Our results are robust to various econometric specifications.

Household education expenditure has grown manifold over the past few years, underscores an increased demand for education and the availability of private institutions. Hitherto, studies have analyzed this trend mainly at the individual level, however, the present study examines the inter-state disparities in the spending and how it influences the educational status of India at the state level, using National Sample Survey data (1987–2014). The conceptualization of this study is anchored in the theoretical framework of Education Production Function and General Earnings Function of Mincer. Based on Instrumental Variable Regression and Generalized Method of Moments, our empirical estimates reveal that geographical location of states matters as much as income in educational attainment and household expenditure serves as a crucial input for educational attainment. Given the stark inter-state variations in educational input and output, a differential approach is essential while devising policies to tide over perpetual educational backwardness across the states.

We use an instrumental variables (IV) approach to examine the effects of dynamic endogeneity when estimating the relationship between mutual fund flows and performance. Unlike the one-stage estimation approach commonly used in prior research, the IV approach allows us to address reverse causality between flow and performance. Through rigorous exclusion tests, we conclude that fund media coverage, risk ranking, and management structure win in a horse race as exogenous instruments for fund flow, while the fund turnover ratio and institutional share perform best as instruments for fund performance. We then demonstrate that endogeneity bias leads to inaccurate inferences in one-stage estimates, as evidenced by the reversals of the signs of flow and performance coefficient estimates when we switch to the IV approach. We find that careful attention to model specification allows us to resolve several widespread inconsistencies in the literature that were likely driven by model misspecification.

Mendelian randomization (MR) is often used to estimate effects of time-varying exposures on health outcomes using observational data. However, MR studies typically use a single measurement of exposure and apply conventional instrumental variable (IV) methods designed to handle time-fixed exposures. As such, MR effect estimates for time-varying exposures are often biased, and interpretations are unclear. We describe the instrumental conditions required for IV estimation with a time-varying exposure, and the additional conditions required to causally interpret MR estimates as a point effect, a period effect or a lifetime effect depending on whether researchers have measurements at a single or multiple time points. We propose methods to incorporate time-varying exposures in MR analyses based on g-estimation of structural mean models, and demonstrate its application by estimating the period effect of alcohol intake, high-density lipoprotein (HDL) cholesterol and low-density lipoprotein (LDL) cholesterol on intermediate coronary heart disease (CHD) outcomes using data from the Framingham Heart Study. We use this data example to highlight the challenges of interpreting MR estimates as causal effects, and describe other extensions of structural mean models for more complex data scenarios.

This study examines how an increase in home value affects fertility decisions of homeowners in China by exploiting regional heterogeneity in housing markets driven by local regulatory and geographic land constraints. In sharp contrast to the literature on developed countries, our instrumental variable results show a negative fertility response to house value growth driven by the recent housing boom in China, where a 100,000-yuan increase in lagged home values—about 43% of the average housing wealth at baseline—results in a 14% decrease in the likelihood of home-owning women giving birth. Further evidence suggests that underdeveloped credit markets may suppress the positive wealth effect of house value growth on childbearing.

L’objectif de cet article est de reexaminer la relation entre les investissements verts des entreprises et la performance financiere, car aucun resultat concluant n’a ete obtenu jusqu’a present. Nous utilisons un echantillon d’entreprises europeennes cotees appartenant a 11 pays de la zone euro sur la periode 2005-2017. Nous appliquons une approche de regression quantile a variable instrumentale pour les donnees de panel avec effet fixe non additif. Cette approche, recemment developpee par Powell (2016), permet de controler le biais d’endogeneite potentiel et l’heterogeneite des variables. Les resultats prouvent que l’impact de l’investissement vert des entreprises sur la performance financiere n’est pas fixe a travers les quantiles et donc que la relation entre les deux variables n’est pas monotone et lineaire. Cet article demontre que les influences de l’investissement vert des entreprises sur la performance financiere prennent des effets differents le long des quantiles refletant la distribution conditionnelle de la variable dependante.