Article
Social Sciences, Mathematical Methods
Tonmoy Chatterjee, Ghirmai Tesfamariam Teame, Sharmi Sen
Summary: This paper empirically investigates the long-term impact of income inequality on health and education in Africa. The study finds that income inequality has negative effects on both health and education outcomes, both in the short term and in the long term. However, efficient state interventions, such as investments in health and education, can lead to significant improvements in these areas in the long run, despite the persistent issue of income disparity in the short term.
JOURNAL OF COMPUTATIONAL SOCIAL SCIENCE
(2023)
Article
Economics
Frederique Bec, Alain Guay, Heino Bohn Nielsen, Sarra Saidi
Summary: This paper proposes a new unit root test method that does not require a proper specification of the alternative model and has good power properties in finite sample. Based on a large simulation study, it is found that this method performs well regardless of the alternative under consideration.
STUDIES IN NONLINEAR DYNAMICS AND ECONOMETRICS
(2023)
Article
Economics
Enzo D'Innocenzo, Andre Lucas, Anne Opschoor, Xingmin Zhang
Summary: We propose an empirical spatial modeling framework that incorporates both heterogeneity and dynamics in economic network connections. By establishing the model's properties and showing its invertible filter, we demonstrate its applicability and flexibility in estimating Eurozone sovereign credit risk. Accounting for both heterogeneity and time-variation is empirically important and enables the discovery of intuitive patterns that may otherwise be overlooked in traditional models.
JOURNAL OF APPLIED ECONOMETRICS
(2023)
Article
Economics
Alyssa Carlson, Riju Joshi
Summary: We propose a parametric estimation procedure for linear panel data models with sample selection and heterogeneous coefficients. Our two-step estimation procedure addresses endogeneity issues caused by the selection process and the correlation between individual unobserved heterogeneity and observed covariates using control function methods. We establish a tractable approach based on conditional linear projections that builds upon the original Heckman correction for sample selection. Monte Carlo simulations demonstrate that our proposed estimator has better finite sample properties compared to standard estimators. In an application to gender differences in high-stakes time-constrained decisions using Elo ratings data from the World Chess Federation, we find a larger gender skill gap and substantial gender differences in strategically selecting into time-constrained matches when considering both sources of endogeneity.
JOURNAL OF APPLIED ECONOMETRICS
(2023)
Article
Social Sciences, Mathematical Methods
Francesca Beccacece, Marco Licalzi
Summary: This paper proposes a minimal set of commonly acceptable principles for formulating consistent amortization schedules based on different contractual clauses. The goal is to clarify implicit premises that have gained wide consensus in practice. Examples are provided to demonstrate how these principles can be applied to manage risk, financial innovations, and unforeseen contingencies.
DECISIONS IN ECONOMICS AND FINANCE
(2023)
Article
Public, Environmental & Occupational Health
Patty Jansen, Chris Snijders, Martijn C. Willemsen
Summary: The study examines the determinants of smoke alarm ownership and intention to purchase, and tests the effectiveness of different messages in increasing smoke alarm ownership. The results show that emphasizing strong predictors significantly increased smoke alarm ownership, while emphasizing typical predictors did not have a significant effect.
Article
Economics
Davide Delle Monache, Andrea De Polis, Ivan Petrella
Summary: This study models the permanent and transitory changes of the predictive density of U.S. GDP growth. It finds a significant increase in downside risk to U.S. economic growth over the last 30 years, particularly during the long-run growth slowdown since the early 2000s. Conditional skewness exhibits a cyclical pattern, with negatively skewed predictive densities preceding and during recessions, often associated with deteriorating financial conditions. In contrast, expansions are characterized by positively skewed distributions. The modeling framework ensures robustness to extreme events, allows for flexible predictor designs, and provides competitive out-of-sample forecasts (point, density, and tail) compared to standard benchmarks.
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
(2023)
Article
Economics
Xiaorong Yang, Jia Chen, Degui Li, Runze Li
Summary: This article considers estimating functional-coefficient models in panel quantile regression with individual effects, allowing the cross-sectional and temporal dependence for large panel observations. A latent group structure is imposed on the heterogeneous quantile regression models so that the number of nonparametric functional coefficients to be estimated can be reduced considerably. The developed methodologies and theory are verified through a simulation study and showcased with an application to house price data from U.K. local authority districts, which reveals different homogeneity structures at different quantile levels.
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
(2023)
Article
Business, Finance
Mathias Beiglboeck, George Lowther, Gudmund Pammer, Walter Schachermayer
Summary: The research focuses on constructing martingales, called fake Brownian motions, with one-dimensional Brownian marginals that differ from Brownian motion. The study provides examples of continuous Markov martingales that miss out only on the strong Markov property, while satisfying marginal constraints imposed by market data.
FINANCE AND STOCHASTICS
(2023)
Article
Mathematics, Interdisciplinary Applications
Sarah Depaoli, Sonja D. Winter, Haiyan Liu
Summary: By conducting a simulation study using confirmatory factor analysis, we extended current knowledge by examining the performance of several Bayesian model fit and comparison indices. Our findings provide practical advice for applied researchers on how to assess and compare models using these common indices implemented in the Bayesian framework.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2023)
Article
Social Sciences, Mathematical Methods
Briana J. K. Stephenson, Stephanie M. Wu, Francesca Dominici
Summary: Dietary assessments provide snapshots of population-based dietary habits, but their generalizability in national survey data is questionable due to disproportionate sampling of certain subgroups. In this study, a Bayesian overfitted latent class model was proposed to derive dietary patterns, taking into account survey design and sampling variability, and showed improved identifiability of the true population pattern and prevalence compared to standard approaches.
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETY
(2023)
Article
Social Sciences, Mathematical Methods
Zilong Xie, Yunxiao Chen, Matthias von Davier, Haolei Weng
Summary: International large-scale assessments (ILSAs) play a crucial role in educational research and policy making by collecting valuable data on education quality and performance. This study focuses on identifying non-cognitive variables associated with students' academic performance, considering the challenges of cognitive measurement, missing values, and multiple comparisons.
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETY
(2023)
Article
Management
Miriam Alvarado, Jo Garrett, James Fullam, Rebecca Lovell, Cornelia Guell, Tim Taylor, Ruth Garside, Marianne Zandersen, Benedict W. Wheeler
Summary: Causal loop diagrams play an important role in systems thinking and can guide subsequent empirical evaluations. By developing systems-informed research propositions, data collection, hypothesis testing, and interpretation can be conducted, leading to new insights for policy-relevant research.
SYSTEM DYNAMICS REVIEW
(2023)
Article
Mathematics, Interdisciplinary Applications
Pere J. Ferrando, Ana Hernandez-Dorado, Urbano Lorenzo-Seva
Summary: This article proposes a new approach to exploratory factor analysis (EFA) that allows for the modeling of correlated residuals without prior specification. Simulation studies and an illustrative example show that this approach works well.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2023)
Article
Mathematics, Interdisciplinary Applications
Timon Elmer
Summary: This paper discusses the maturity and development of Computational Social Science as a discipline. It suggests that CSS should embrace both passive and active measurement practices, and integrate practices and knowledge from other disciplines to achieve scientific rigor.
Article
Mathematics, Interdisciplinary Applications
Ming-Chi Tseng
Summary: This investigation suggests that researchers should prioritize the use of random intercept latent profile transition analysis (RI-LPTA) when constructing longitudinal models to reduce estimation bias in the parameters.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2023)
Article
Mathematics, Interdisciplinary Applications
Oh-Hyun Kwon, Inho Hong, Woo-Sung Jung, Hang-Hyun Jo
Summary: The gravity model of human mobility explains the deterrent effect of distance on travel in urban mobility patterns. This study examines whether distance exponents in a single city could also vary depending on the traffic volumes of the origin and destination regions. The analysis of travel data in twelve major cities in the United States reveals that the distance exponent governing travel deterrence varies significantly within a city based on traffic volumes.
Article
Economics
Jinwoong Lee
Summary: This study explores the main drivers of house price fluctuations in the USA and finds that credit shocks and housing supply shocks are the main contributors to long-term fluctuations in house prices.
EMPIRICAL ECONOMICS
(2023)
Article
Public, Environmental & Occupational Health
Chao-Chin Chang, Chia-Lin Chang
Summary: This study analyzed global data on epidemic control measures and economic conditions during different mutant strain epidemic periods. The findings suggest that the magnitude of the elasticity coefficient, representing the relationship between the change in screening tests and confirmed cases, is associated with a country's economic condition. The Omicron strain showed a higher elasticity coefficient compared to the Alpha and Delta strains. Further analysis revealed that the elasticity coefficient is significantly lower in middle and high-income countries compared to low-income countries. These results emphasize the importance of considering both epidemiological measures and economic conditions when formulating epidemic control strategies.
Article
Mathematics, Interdisciplinary Applications
Yuqi Gu
Summary: This article proposes a new family of DeepCDMs models that hunt for deep discrete diagnostic information using deep generative modeling. These models are identifiable, parsimonious, and interpretable. They have transparent identifiability conditions, Bayesian formulations, and efficient sampling algorithms.