Model Specification Research Articles

Impact of agricultural land ownership on child nutrition in rural Sudan: an investigation across gender

Purpose In light of the inequality in access to farming land and the high prevalence of child malnutrition in Sudan, there is a lack of empirical research on the relationship between land ownership and child nutritional status. This study aims to examine the influence of agricultural landholding on the nutritional status of children under the age of five in rural Sudan.Design/methodology/approachThe study utilizes data from Sudan’s 2014 Multiple Indicator Cluster Survey (MICS), covering a sample of 10,753 rural children. The empirical analysis uses the two-stage least squares (2SLS) approach, adopting various estimation methods and model specifications for robustness check and comparison.Findings The results demonstrate that agricultural land has a positive and significant effect on reducing child malnutrition, signifying that children from families with agricultural land are less susceptible to malnutrition in Sudan. When examining the male and female sub-samples separately, the findings indicate a positive influence of land ownership on child malnutrition in the female sub-sample, while no significant impact is observed in the male sub-sample. This indicates a gender disparity in the effects of land ownership on child nutrition, with girls benefiting more from access to agricultural land compared to boys.Originality/value The study has several significant contributions. First, this is the sole study that examines the impact of agricultural land ownership on child malnutrition in Sudan. Second, considering the gender variations in nutritional status, investigating the influence of land ownership on child nutrition across genders addresses a significant gap in the current literature. Finally, the findings resulting from this study can contribute to achieving the United Nations Sustainable Development Goals (SDGs) to be achieved by 2030, precisely focusing on SDG2 Goal 2: Zero hunger and SDG 10: Goal 10: Reduced inequalities.

Business and financial cycle across regimes: Does financial stress matter?

Identifying the business and financial cycles and their regimes is crucial for understanding the economy's state and financial market dynamics. Using a bivariate four-regime Markov-switching framework, we assess the accuracy of a model that identifies the business cycle by combining financial and real variables and compare it to a model that only uses real variables. We find that a model that incorporates information from a financial stress index outperforms a model based solely on real variables, not only during a financial crisis, but also, and more interestingly, during economic downturns. The empirical evidence provides insights for policymakers and investors to improve economic policy formulation, investment strategies, strategic decision-making, and proactive risk management. The results are robust to various model specifications.

A comprehensive survey of UPPAAL‐assisted formal modeling and verification

AbstractUPPAAL is a formal modeling and verification tool based on timed automata, capable of effectively analyzing real‐time software and hardware systems. In this article, we investigate research on UPPAAL‐assisted formal modeling and verification. First, we propose four research questions considering tool characteristics, modeling methods, verification means and application domains. Then, the state‐of‐the‐art methods for model specification and verification in UPPAAL are discussed, involving model transformation, model repair, property specification, as well as verification and testing methods. Next, typical application cases of formal modeling and verification assisted by UPPAAL are analyzed, spanning across domains such as network protocol, multi‐agent system, cyber‐physical system, rail traffic and aerospace systems, cloud and edge computing systems, as well as biological and medical systems. Finally, we address the four proposed questions based on our survey and outline future research directions. By responding to these questions, we aim to provide summaries and insights into potential avenues for further exploration in this field.

Automated Machine Learning and Asset Pricing

We evaluate whether machine learning methods can better model excess portfolio returns compared to the standard regression-based strategies generally used in the finance and econometric literature. We examine 17 benchmark factor model specifications based on Expected Utility Theory and theory drawn from behavioural finance. We assess whether machine learning can identify features of the data-generating process undetected by standard methods and rank the best-performing algorithms. Our tests use 95 years of CRSP data, from 1926 to 2021, encompassing the price history of the broad US stock market. Our findings suggest that machine learning methods provide more accurate models of stock returns based on risk factors than standard regression-based methods of estimation. They also indicate that certain risk factors and combinations of risk factors may be more attractive when more appropriate account is taken of the non-linear properties of the underlying assets.

The role of local institutional quality for the digital and environmental transitions in Italy

In this paper we analyze the effect of institutional quality on the so-called Twin transition at provincial level in Italy. To carry out the analysis, we use two proxies for the ecological transition, namely waste management and air pollution, and two proxies for the digital transition, namely ultra-wide band connections and provincial innovative start-ups. All the models are estimated on a panel of 103 provinces with a time dimension that varies for the different dependent variables. We employ Spatial Durbin Model estimator to take into account spatial dependence across provinces. Our findings indicate that the quality of local institutions may have an important role for the ecological transition, but not for the digital transition. Higher levels of institutional quality increase the performance in waste management and reduce the level of local air pollution. Conversely, the estimated coefficient of institutional quality is not statistically significant neither for ultra-wide band nor for innovative start-ups. Institutional quality turns to be significant but negative for the digital transition when dummy variable controlling for the presence of science-oriented university is added in the model specification. These results confirm that the green transition is largely policy-driven and the local ‘institutional environment’ is an essential ingredient for its effectiveness. The driving forces of the digital transition, instead, can be better found in socio-economic factors that depend on the ‘economic quality’ of the local system and its propensity to innovate within larger-scale innovation trajectories.

Assessing the impact of energy R&D on green growth in OECD countries: a CS-ARDL analysis

AbstractSince the introduction of the OECD innovation and green growth strategies in 2007 and 2011, respectively, the OECD countries have been actively engaged in supporting green energy R&D to accelerate the development of clean energy technologies. Specifically, the OECD recognizes that both renewable energy R&D and energy efficiency R&D are key components of a low-carbon and sustainable energy system. This study aims to assess the impact of disaggregated energy R&D on green growth in 21 high-income OECD countries, from 1990 to 2021. Two key green growth indicators, namely energy productivity and CO2 productivity, are used as response variables. The long-run CS-ARDL model results show that renewable energy R&D and fossil fuel R&D have a positive and significant impact on energy productivity in all model specifications, with renewable energy R&D exhibiting a relatively stronger impact compared to fossil fuel R&D. The long-run effects of the disaggregated energy R&D variables on CO2 productivity align with the results of the energy productivity model. Based on the study's findings, policymakers should consider reallocating the energy R&D budget towards renewable energy R&D, fostering international collaboration between OECD countries in renewable energy R&D, and implementing technology-specific policies to encourage investment in renewable energy technologies.

Pay talk in contemporary workplaces

Abstract Drawing on a unique survey of US workers with information about their employers’ policies on pay discussions and whether workers engage in such talk with their coworkers, we provide the most comprehensive investigation into pay talk in workplaces to date. Unlike existing treatments, we focus on core organizational and relational factors that influence whether workers talk about pay. We theorize pay talk as a challenge to managerial discretion, and we hypothesize that organizational attributes related to pay-setting influence workers’ willingness to discuss wages and salaries with colleagues. Managers, in turn, combat such challenges to their discretion by instituting pay secrecy rules. Particular relational factors within organizations are related to workers’ violations of these rules. Findings indicate that the likelihood of pay discussions varies by workplace pay secrecy rules, managerial relations within organizations, and, in certain model specifications, sector and career turning points. Among status characteristics, only age is associated with discussing pay, with younger workers significantly more likely to talk about pay and to violate organizational rules meant to suppress pay discussions.

Reducing costs or increasing efficiency? Unveiling the effects and mechanisms of the digital economy on sustained green innovation

This study examines the impact of the digital economy on sustainable green innovation in China, with a focus on the mediating roles of debt financing costs and resource allocation efficiency. Leveraging a comprehensive dataset of 24,741 firm-year observations from 2008 to 2022, we utilize fixed-effects regression models to analyze the relationships between the digital economy, debt financing costs, resource allocation efficiency, and sustainable green innovation. The results demonstrate that the digital economy positively influences sustainable green innovation, with this effect being partially mediated by reductions in debt financing costs and improvements in resource allocation efficiency. Specifically, the digital economy lowers financing costs and optimizes resource allocation, which collectively enhances green innovation sustainability. The findings remain consistent across various endogeneity and robustness checks, including instrumental variable approach, lagged effects, heckman two-stage method, sample adjustments, alternative measures, and model specifications. Additionally, heterogeneity tests reveal that the digital economy's positive effect is stronger for firms in the early and middle stages of their life cycle and for those operating in less-polluting industries. These insights contribute to the growing literature on digital technologies and sustainable development, offering valuable implications for managers and policymakers aiming to harness the digital economy for advancing sustainable green innovation.

Gaps in the usage and reporting of multiple imputation for incomplete data: findings from a scoping review of observational studies addressing causal questions

BackgroundMissing data are common in observational studies and often occur in several of the variables required when estimating a causal effect, i.e. the exposure, outcome and/or variables used to control for confounding. Analyses involving multiple incomplete variables are not as straightforward as analyses with a single incomplete variable. For example, in the context of multivariable missingness, the standard missing data assumptions (“missing completely at random”, “missing at random” [MAR], “missing not at random”) are difficult to interpret and assess. It is not clear how the complexities that arise due to multivariable missingness are being addressed in practice. The aim of this study was to review how missing data are managed and reported in observational studies that use multiple imputation (MI) for causal effect estimation, with a particular focus on missing data summaries, missing data assumptions, primary and sensitivity analyses, and MI implementation.MethodsWe searched five top general epidemiology journals for observational studies that aimed to answer a causal research question and used MI, published between January 2019 and December 2021. Article screening and data extraction were performed systematically.ResultsOf the 130 studies included in this review, 108 (83%) derived an analysis sample by excluding individuals with missing data in specific variables (e.g., outcome) and 114 (88%) had multivariable missingness within the analysis sample. Forty-four (34%) studies provided a statement about missing data assumptions, 35 of which stated the MAR assumption, but only 11/44 (25%) studies provided a justification for these assumptions. The number of imputations, MI method and MI software were generally well-reported (71%, 75% and 88% of studies, respectively), while aspects of the imputation model specification were not clear for more than half of the studies. A secondary analysis that used a different approach to handle the missing data was conducted in 69/130 (53%) studies. Of these 69 studies, 68 (99%) lacked a clear justification for the secondary analysis.ConclusionEffort is needed to clarify the rationale for and improve the reporting of MI for estimation of causal effects from observational data. We encourage greater transparency in making and reporting analytical decisions related to missing data.

Line‐item vetoes as a coordination mechanism

AbstractAlthough presidential vetoes are central to the legislative process, the role of total versus line item vetoes (LIV) is largely unclear. While total vetoes are a sign of conflict between the branches, as the literature has emphasized, we argue that LIV function as a negative agenda setting mechanism that enables presidents to coordinate within their coalition. To test our argument, we use an original dataset on all statutes and executive decrees approved and vetoed in Brazil for the period 1988–2010. In both, statutes and decrees, we show that while total vetoes occur when conflict between branches is stronger, LIV happen when such conflict is minimal and presidents have tight control over their coalition. The results are robust across dependent variables, model specifications, and estimation strategies. Our findings highlight that while the total veto is a blunt bargaining mechanism, the LIV provides a scalpel, a much finer tool that helps presidents manage and sustain their congressional coalition.

Mortality (Dis)Similarities in the Context of Demographic Aging: The Countries of Ex-Yugoslavia

Generally, mortality declines at all ages, with varying intensities, as a result of heterogeneous factors affecting human lifespan. This paper considers switching regression estimation for six ex-Yugoslavian countries with the specification of a time-varying transition probability model of crude death rate. A two-state Markov switching means VAR estimates are used in which the mean growth rate of crude death rate is subject to regime switching, where the errors follow a constant transition probability. The UN data were employed consisting of the crude mortality rate series containing the log difference of yearly crude mortality rate in the six countries of ex-Yugoslavia for 1990–2021. The results show that the estimates of coefficients on the intercept in the mean equation both differ from zero in Bosnia & Herzegovina, Serbia, Montenegro, and Slovenia and are with opposite and statistically significant signs only for Montenegro and Slovenia. The transition probability summaries show a higher probability of remaining in the first high regime state for Macedonia, Serbia, and Bosnia & Herzegovina (0.96, 0.94, and 0.87, respectively). The higher probability of remaining in the second low-medium regime state was found in Slovenia, Croatia, and Montenegro (0.96, 0.87, and 0.56, respectively). The appropriate expected durations in the first regime are approximately 26.41, 16.19, and 7.78 years for Macedonia, Serbia, and Bosnia & Herzegovina, and 28.30, 7.80, and 2.28 years were the corresponding expected durations in the second regime for Slovenia, Croatia, and Montenegro.

House prices and credit as transmission channels from monetary policy to inequality: Evidence from OECD countries

Using a panel vector autoregressive model, this paper assesses the impact of monetary policy on the Gini coefficient of disposable income for 30 OECD countries between 1995Q1 and 2019Q4. We assume house prices and household credit as transmission channels, representing households’ financial balance. To capture the effect of the financial crisis, the analysis further distinguishes the period that started in 2008Q4. We find that a contractionary monetary policy increases the Gini coefficient in a moderate way. For the entire period, house prices are an effective transmission channel, a positive shock decreasing inequality, while credit is not statistically significant. Following the crisis credit stands out as the transmission mechanism, a positive credit shock reducing the Gini coefficient, while house prices lose relevance. These results are robust to different model specifications.

The relationships between Urban Tree Canopy Cover and Crime in São Paulo City, Brazil

Prior research has indicated lower crime rates in areas with greater tree canopy cover predominantly in the Global North. There are few studies from the Global South, and more specifically in Latin America. Given the high prevalence of crime in Latin American cities, the need to address social and environmental inequalities using nature-based solutions is urgent. This study examines crime and tree canopy cover through a series of spatial analyses for São Paulo city, Brazil, while controlling for potential confounders. We tested six levels of data aggregation that were combined with three different crime types and two denominators of crime, to account for spurious findings from Modifiable Areal Unit Problems (MAUP). Of the 36 models, a majority of 27 models (75 %) indicate a negative relationship between crime and tree cover canopy, while 4 models (11 %) show a positive correlation, and 5 models (14 %) suggest no statistically significant relationship. Our best models allow us to infer that 10 % greater tree canopy cover is associated with a 1.20 % fewer property, personal and total reported crimes, with statistical significance at the p < 0.001 level. These findings support our hypothesis that there is a negative relationship between tree canopy cover and crime, with a stronger association observed for property crime than personal or total crime. The negative relationship persisted independently of the level of data aggregation, crime types, crime denominator and spatial models specifications (lag and SARMA), avoiding statistical bias of MAUP. The results follow the literature that have observed tree cover associated with lower crime rates, for different types of crime, while adding a new climatic and cultural context to the evidence base.

Market perceptions of distress and its impact on returns: evidence from the U.S. commercial real estate market

ABSTRACT This paper examines the relationship between market participants’ sentiment regarding distress in the real estate market, captured through internet search queries, and the U.S. commercial real estate market. We use Google search frequency to construct a measure of market perception of distress, the Market Distress Perception Index (MDP Index), and determine the extent to which this index can help predict future private commercial real estate returns in the U.S. The results show that our pessimistic sentiment index predicts returns of commercial real estate up to three quarters in advance. These results hold at the national, regional, and state levels and are robust across various model specifications. The predictability of the sentiment index is especially pronounced during recessionary periods. We also analyse different property sectors and find that the inverse relationship between the MDP Index and future private commercial real estate returns persists across all sectors except the industrial sector. The relationship is strongest for the office sector.

External costs of high-voltage overhead transmission lines: Evidence from a causal approach in rural France

In light of climatic change and global warming, electricity transmission networks need to be developed for the integration of renewable sources. In North America and Europe, to achieve renewable electricity goals, massive investments in electricity transport infrastructure are planned to connect solar and wind generation sites to the grid network. However, local opposition to new installations of high-voltage overhead transmission lines (HVOTLs) is causing delays and cost overruns. Visual nuisance is an important basis of local stakeholders' opposition to a new project. Estimations of the local economic impact of HVOTLs can help in identifying the external costs of the electricity supply industry to improve both efficiency in electricity pricing and fairness in defining provision for host community compensation. Prior research has provided evidence that existing HVOTLs have negative but not substantial effects on their immediate neighbourhoods. However, these studies have applied a correlational approach. This paper revisits the external effects of HVTOLs, exploring the case of a 225 kV line connecting two medium-size cities (Saint-Privat-d'Allier to Saint-Etienne) in France. We take advantage of the public disclosure in 2009 of undergrounding 8 km out of a total of 87 km lines as a result of a network upgrade project, to develop a difference-in-difference specification of a hedonic regression model, by comparing house sale prices at different distances from existing pylons, before and after the announcement of the decision to upgrade the line. We show that undergrounding was accompanied by an increase of about 38% in the price of treated houses located within 200 m of old pylons. The implied environmental costs of proximity to high-voltage pylons are substantial and their reduction is internalized into house prices as soon as the decision to go underground is announced.

The return of university reputation in job applications: evidence from a field experiment in China

ABSTRACT It is crucial to understand the impact of education on labour market outcomes. Although previous literature has extensively documented the effect of university reputation on employees’ earnings, it lacks knowledge regarding the hiring process. This study aims to contribute to the existing literature by examining whether job applicants from reputable universities are more likely to receive interview invitations in China. To investigate this causal relationship, we conducted a field experiment by randomly generating and delivering fictitious resumes to employers. The results demonstrated that applicants graduating from reputable universities were more likely to obtain interview invitations, suggesting that the university reputation exerts a positive effect on the hiring process. We showed that these results were unlikely driven by model specifications, control variables or alternative explanations. Additionally, we examined the effect of the reputation of specialized majors and discovered that their influence is considerably less than that of university reputation. This study improves our understanding of the influence of education on labour market outcomes and offers practical advice for students facing a trade-off between university and major reputation.

Government debt and economic growth: heterogeneity, asymmetries, and the role of net debt

ABSTRACT Using data on 167 countries over 1970–2019, this study gathers new evidence about the government debt-growth relationship. We jointly address several features of the panel – foremost asymmetry, cointegration, endogeneity, country heterogeneity and cross-sectional dependence. We find that increases in per-worker debt are detrimental to the long-run dynamics of output, but our nonlinear estimates suggest that changes in government debt propagate their effects through different channels. Applying alternatively gross and net public debt as a measure of indebtedness yields different results too, as happens with the adoption of different estimators. The magnitude of the effects depends on the model specification, indicating that cross-country estimates of the debt-growth nexus require parsimonious interpretations.

An environmental Kuznets curve for global forests: An application of the mi-lasso estimator

In this study, we employ a Moran's i based Lasso (Mi-Lasso) methodology to address the spatial dependence of an unspecified functional form, investigating the association between a country's economic growth and the rate of deforestation. Our aim is to explore the existence of a forestry environmental Kuznets curve (EKC). Our approach to handling spatial dependence overcomes limitations identified in existing EKC literature. We estimate a series of cross-sectional data models spanning the period from 1990 to 2020 for 146 countries. Our findings indicate a non-linear relationship, revealing a change peak rate of deforestation over time. Additionally, we observe that the income threshold at which the deforestation rate begins to decrease changes over time with differences observed between model specifications. Crucially, our results highlight that failing to account for spatial dependence leads to a significant absolute upward bias in ordinary least squares (OLS) estimates of income and worse model fit.

Forecasting Lattice and Point Spatial Data: Comparison of Unilateral and Multilateral SAR Models

Spatial auto-regressive (SAR) models are widely used in geosciences for data analysis; their main feature is the presence of weight (W) matrices, which define the neighboring relationships between the spatial units. The statistical properties of parameter and forecast estimates strongly depend on the structure of such matrices. The least squares (LS) method is the most flexible and can estimate systems of large dimensions; however, it is biased in the presence of multilateral (sparse) matrices. Instead, the unilateral specification of SAR models provides triangular weight matrices that allow consistent LS estimates and sequential prediction functions. These two properties are strictly related and depend on the linear and recursive nature of the system. In this paper, we show the better performance in out-of-sample forecasting of unilateral SAR (estimated with LS), compared to multilateral SAR (estimated with maximum likelihood, ML). This conclusion is supported by numerical simulations and applications to real geological data, both on regular lattices and irregularly distributed points.

Does firm-level carbon assurance matter for trade credit?

We are among the first to examine the influence of carbon assurance on trade credit. Drawing on a sample of publicly listed U.S. firms, we document that firms with high carbon assurance obtain more trade credit from their suppliers. Our channel analysis tests show that high carbon assurance translates into higher trade credit by reducing risk and information asymmetry. Our results are robust with alternative model specifications, trade credit and carbon assurance measures, 2SLS IV analysis, PSM estimates, and Heckman-two stage approach to address possible endogeneity.