Social Sciences, Mathematical Methods

Article Economics

Time series analysis of COVID-19 infection curve: A change-point perspective

Feiyu Jiang, Zifeng Zhao, Xiaofeng Shao

Summary: In this paper, a piecewise linear trend model is used to model the trajectory of COVID-19 cumulative confirmed cases and deaths. The model captures the phase transitions of the epidemic growth rate and provides interpretability due to its semiparametric nature. The self-normalization technique is advanced for testing and estimation of change-points in the linear trend of a nonstationary time series. Multiple change-point estimation is achieved through the combination of SN-based change-point test and the NOT algorithm. The proposed method is applied to analyze the trajectory of COVID-19 cases and deaths for 30 major countries, revealing interesting patterns and potential implications for pandemic responses.

JOURNAL OF ECONOMETRICS (2023)

Article Mathematics, Interdisciplinary Applications

Interpreting Interaction Effects in Generalized Linear Models of Nonlinear Probabilities and Counts

Connor J. McCabe, Max A. Halvorson, Kevin M. King, Xiaolin Cao, Dale S. Kim

Summary: Psychology research often involves studying probabilities and counts using generalized linear models (GLMs). Interactions in GLMs describing probabilities and counts are not equal to product terms between predictor variables, requiring nontraditional approaches to accurately interpret these effects. This paper introduces the use of partial derivatives and discrete differences to quantify and interpret interaction effects in GLMs, and provides guidelines and simulated examples for estimating and interpreting these effects on probability and count scales.

MULTIVARIATE BEHAVIORAL RESEARCH (2022)

Article Social Sciences, Mathematical Methods

Using Interviews to Understand Why: Challenges and Strategies in the Study of Motivated Action

Mario L. Small, Jenna M. Cook

Summary: This article examines the challenges in interview research of assessing whether what people say motivated their actions actually did so. It identifies at least five challenges and more than a dozen strategies that have been deployed to address them. The article argues that researchers need to consider each challenge, use appropriate strategies, and evaluate their effectiveness to uncover motivation. This work helps strengthen the scientific foundations of in-depth interview research.

SOCIOLOGICAL METHODS & RESEARCH (2023)

Article Social Sciences, Mathematical Methods

Spatial Regression Models: A Systematic Comparison of Different Model Specifications Using Monte Carlo Experiments

Tobias Ruttenauer

Summary: This study summarizes the commonly used spatial regression models, comparing their performance through Monte Carlo experiments. It finds that spatial Durbin specifications (SDM and SDEM) and simple spatial lag of X (SLX) provide more accurate estimates of direct impacts compared to spatial autoregressive and spatial error specifications, even in cases of misspecification. Additionally, the study reveals that in certain realistic scenarios, SLX outperforms the more complex SDM and SDEM specifications for indirect spillover effects.

SOCIOLOGICAL METHODS & RESEARCH (2022)

Article Social Sciences, Mathematical Methods

How and Why Interviews Work: Ethnographic Interviews and Meso-level Public Culture

Rachel Rinaldo, Jeffrey Guhin

Summary: Recent debates on qualitative methods have examined the limitations and contributions of interviews compared to surveys and participant observation. However, little consideration has been given to how ethnographers themselves use interviews in their work. This article argues that Lizardo's discussion of the three modes of culture can help us better understand the distinct contributions of observation and interviews, with ethnographic interviews being particularly valuable for accessing different cultural modes. The authors also propose dividing Lizardo's conception of public culture into meso- and macrolevels, which helps highlight the varying contributions of interviews within and outside an ethnographic context. Drawing on ethnographic research and analysis, the article demonstrates how using ethnographic interviews can enhance sociologists' understanding of the interaction between these four cultural modes.

SOCIOLOGICAL METHODS & RESEARCH (2022)

Article Public, Environmental & Occupational Health

Adoption of a Data-Driven Bayesian Belief Network Investigating Organizational Factors that Influence Patient Safety

Mecit Can Emre Simsekler, Abroon Qazi

Summary: Medical errors pose high risks to patients. Limited research is available regarding the probabilistic interdependencies between organizational factors and patient safety errors. This study uses a data-driven Bayesian Belief Network (BBN) model to explore the relationships between organizational factors and patient safety errors, and identifies health and well-being and bullying and harassment in the work environment as the two leading factors influencing patient safety.

RISK ANALYSIS (2022)

Article Mathematics, Interdisciplinary Applications

Recovering Within-Person Dynamics from Psychological Time Series

Jonas M. B. Haslbeck, Oisin Ryan

Summary: Idiographic modeling is gaining popularity for accessing within-person dynamics in psychological phenomena, but making inferences to underlying systems from time series models is challenging, and insufficient sampling frequency can impact recovery of dynamics of interest. However, global characteristics of the system can still be reliably recovered.

MULTIVARIATE BEHAVIORAL RESEARCH (2022)

Article Economics

Surveying business uncertainty

David Altig, Jose Maria Barrero, Nicholas Bloom, Steven J. Davis, Brent Meyer, Nicholas Parker

Summary: This study elicits subjective probability distributions from business executives about their own-firm outcomes in the future. The results show that firm-level growth expectations are highly predictive of realized growth rates. Furthermore, firm-level subjective uncertainty predicts the magnitudes of future forecast errors and revisions. The study also finds that subjective uncertainty increases with the firm's absolute growth rate in the previous year and recent revisions to its expected growth rate. The researchers construct monthly indices of business expectations and uncertainty for the U.S. private sector.

JOURNAL OF ECONOMETRICS (2022)

Article Mathematics, Interdisciplinary Applications

Sequential Gibbs Sampling Algorithm for Cognitive Diagnosis Models with Many Attributes

Juntao Wang, Ningzhong Shi, Xue Zhang, Gongjun Xu

Summary: In this study, a computationally efficient sequential Gibbs sampling method is proposed for estimating cognitive diagnosis models, which outperforms existing methods.

MULTIVARIATE BEHAVIORAL RESEARCH (2022)

Article Economics

Economic impact of the most drastic lockdown during COVID-19 pandemic-The experience of Hubei, China

Xiao Ke, Cheng Hsiao

Summary: This paper evaluates the economic consequences of the 76-day lockdown policy in Hubei Province during the COVID-19 pandemic. The strict lockdown had a significant negative impact on the economy, but it also effectively controlled the spread of the virus. After the lockdown was lifted, the economy in Hubei quickly recovered, with the exception of the passenger transportation sector.

JOURNAL OF APPLIED ECONOMETRICS (2022)

Article Social Sciences, Mathematical Methods

Fixed Effects Individual Slopes: Accounting and Testing for Heterogeneous Effects in Panel Data or Other Multilevel Models

Tobias Ruttenauer, Volker Ludwig

Summary: Fixed effects (FE) panel models have been widely used in research to control for stable heterogeneity between units. However, conventional FE models may produce biased results when there are heterogeneous slopes or growth curves related to the parameter of interest. This study introduces fixed effects individual slope (FEIS) models to overcome this issue and proposes two versions of the Hausman test to detect misspecification in FE models.

SOCIOLOGICAL METHODS & RESEARCH (2023)

Article Social Sciences, Mathematical Methods

Critical Tension: Sufficiency and Parsimony in QCA

Adrian Dusa

Summary: The objective of qualitative comparative analysis is to find solutions that meet the conditions for a desired outcome, while being as simple as possible. Different search strategies lead to different types of solutions, and there is an ongoing debate on which type is closest to the true causal structure. This article introduces the logics behind each simplification system, explores the concept of robust sufficiency, and provides improved procedures to measure correctness.

SOCIOLOGICAL METHODS & RESEARCH (2022)

Article Social Sciences, Mathematical Methods

What Can You Do With a Single Case? How to Think About Ethnographic Case Selection Like a Historical Sociologist

Josh Pacewicz

Summary: This article analyzes the distinction between theoretically and empirically oriented ethnography in case selection and external validity claims. By examining several exemplary ethnographies, the study presents optimized strategies for each orientation.

SOCIOLOGICAL METHODS & RESEARCH (2022)

Article Economics

Sector connectedness in the Chinese stock markets

Ying-Ying Shen, Zhi-Qiang Jiang, Jun-Chao Ma, Gang-Jin Wang, Wei-Xing Zhou

Summary: This study reveals the risk-transmitting pathways within different economic sectors in China, identifying sectors that act as risk transmitters and risk takers. It also shows that during extreme risk events, such as the global financial crisis and the China-US trade war, the financial sectors play a crucial role in stabilizing the economic system.

EMPIRICAL ECONOMICS (2022)

Article Social Sciences, Mathematical Methods

Abductive Coding: Theory Building and Qualitative (Re)Analysis

Luis Vila-Henninger, Claire Dupuy, Virginie Van Ingelgom, Mauro Caprioli, Ferdinand Teuber, Damien Pennetreau, Margherita Bussi, Cal Le Gall

Summary: The study examines the use of abductive approach in qualitative secondary analysis, proposing new tactics for its concrete implementation. It focuses on the development of code equations as a key resource for qualitative analysts to build theory by operationalizing phenomena that span individual codes.

SOCIOLOGICAL METHODS & RESEARCH (2022)

Article Social Sciences, Mathematical Methods

Applying and Assessing Large-N QCA: Causality and Robustness From a Critical Realist Perspective

Roel Rutten

Summary: This article connects QCA's substantive-interpretation approach of causality to critical realism and validates the validity of causal claims in large-N QCA studies through robustness tests.

SOCIOLOGICAL METHODS & RESEARCH (2022)

Article Mathematics, Interdisciplinary Applications

Time to Intervene: A Continuous-Time Approach to Network Analysis and Centrality

Oisin Ryan, Ellen L. Hamaker

Summary: Network analysis of ESM data in clinical psychology is popular, with researchers using DT-VAR models to define network structure. However, VAR models have time-interval dependency issues. This paper proposes a CT network approach using CT-VAR models, introducing new centrality measures for intervention targeting.

PSYCHOMETRIKA (2022)

Article Economics

Machine Learning Time Series Regressions With an Application to Nowcasting

Andrii Babii, Eric Ghysels, Jonas Striaukas

Summary: This article introduces structured machine learning regressions for high-dimensional time series data, presenting the sparse-group LASSO estimator that can effectively utilize the data structure and outperform the unstructured LASSO. Empirical applications show that the estimator performs favorably compared to other alternatives, especially in predicting US GDP growth.

JOURNAL OF BUSINESS & ECONOMIC STATISTICS (2022)

Article Mathematics, Interdisciplinary Applications

Assessing Cutoff Values of SEM Fit Indices: Advantages of the Unbiased SRMR Index and Its Cutoff Criterion Based on Communality

Carmen Ximenez, Alberto Maydeu-Olivares, Dexin Shi, Javier Revuelta

Summary: The behavior of fit indices in CFA models depends on factors such as model size, sample size, and measurement quality. Biased estimators of fit indices result in unstable behavior with changing sample size, making it difficult to establish cutoff values. Unbiased estimators, on the other hand, match the behavior of population parameters and depend on the average R-2 of observed variables and model size.

STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL (2022)

Article Public, Environmental & Occupational Health

Assessing the Impacts of COVID-19 on the Industrial Sectors and Economy of China

Ling Tan, Xianhua Wu, Ji Guo, Ernesto D. R. Santibanez-Gonzalez

Summary: The article describes how to use a Computable General Equilibrium model to assess the potential impact of the COVID-19 epidemic on the Chinese economy and various sectors, and proposes corresponding measures and suggestions.

RISK ANALYSIS (2022)