Average Effect Research Articles

When does adjusting covariate under randomization help? A comparative study on current practices

PurposeWe aim to thoroughly compare past and current methods that leverage baseline covariate information to estimate the average treatment effect (ATE) using data from of randomized clinical trials (RCTs). We especially focus on their performance, efficiency gain, and power.MethodsWe compared 6 different methods using extensive Monte-Carlo simulation studies: the unadjusted estimator, i.e., analysis of variance (ANOVA), the analysis of covariance (ANCOVA), the analysis of heterogeneous covariance (ANHECOVA), the inverse probability weighting (IPW), the augmented inverse probability weighting (AIPW), and the overlap weighting (OW) as well as the augmented overlap weighting (AOW) estimators. The performance of these methods is assessed using the relative bias (RB), the root mean square error (RMSE), the model-based standard error (SE) estimation, the coverage probability (CP), and the statistical power.ResultsEven with a well-executed randomization, adjusting for baseline covariates by an appropriate method can be a good practice. When the outcome model(s) used in a covariate-adjusted method is closer to the correctly specified model(s), the efficiency and power gained can be substantial. We also found that most covariate-adjusted methods can suffer from the high-dimensional curse, i.e., when the number of covariates is relatively high compared to the sample size, they can have poor performance (along with lower efficiency) in estimating ATE. Among the different methods we compared, the OW performs the best overall with smaller RMSEs and smaller model-based SEs, which also result in higher power when the true effect is non-zero. Furthermore, the OW is more robust when dealing with the high-dimensional issue.ConclusionTo effectively use covariate adjustment methods, understanding their nature is important for practical investigators. Our study shows that outcome model misspecification and high-dimension are two main burdens in a covariate adjustment method to gain higher efficiency and power. When these factors are appropriately considered, e.g., performing some variable selections if the data dimension is high before adjusting covariate, these methods are expected to be useful.

Self-Efficacy, Patient Activation, and the Burden of Inflammatory Bowel Disease on Patients' Daily Lives.

The effective management of inflammatory bowel disease (IBD) requires complex self-management behaviors. Both patient activation (the degree to which patients are willing and able to engage in care) and self-efficacy (one's confidence in performing certain behaviors) are thought to play an important role in chronic disease self-management, but patient activation is a broad concept that can be more difficult to precisely target than self-efficacy. We aimed to describe the relationship between patient activation, self-efficacy, and the burden of IBD on patients' daily lives. Patients with IBD were recruited from a single center to complete a survey including the Patient Activation Measure (PAM-13®), the IBD Self-Efficacy Scale (IBD-SES), and an IBD-specific patient-reported outcome measure. Using multivariable linear regression, we examined the relationship between IBD burden, self-efficacy, and patient activation, adjusting a priori for age, gender, IBD type, IBD medications, active corticosteroid use, anxiety, and depression. We performed a post-hoc mediation analysis to examine self-efficacy as a potential mediator in the relationship between patient activation and the burden of IBD on patient's daily lives. A total of 132 patients with IBD completed the survey (59% Crohn's disease, 41% ulcerative colitis, 52% female). Higher levels of patient activation and higher levels of self-efficacy were each associated with lower IBD burden (patient activation: ß = -1.9, p < 0.001, self-efficacy: ß = -2.6, p < 0.001). Post hoc mediation analysis confirmed that the relationship between patient activation and daily IBD burden was mediated by self-efficacy (Average Causal Mediation Effect = -1.00, p < 0.001, proportion mediated = 0.62, p < 0.001). The relationship between patient activation and IBD burden is highly mediated by self-efficacy, suggesting that self-efficacy could be a more precise target for intervention. Future studies could focus on targeting self-efficacy to build individuals' confidence in IBD self-management and testing of IBD-tailored self-management programs to ultimately improve disease outcomes.

The relationship between health literacy and healthy lifestyle behaviors: A meta-analysis.

Health literacy and healthy lifestyle behaviors are both pivotal elements for public health improvement. This meta-analysis aims to scrutinize studies investigating the nexus between health literacy and healthy lifestyle behaviors and to examine the correlation between health literacy and such behaviors. Studies conducted from 2013 to 2023 exploring the association between health literacy and healthy lifestyle behaviors, as well as the impact of gender and chronic disease status on health literacy, were included. The selection criteria for the meta-analysis involved a literature search utilizing databases such as PubMed, Google Academic, Web of Science, and the National Thesis Center. The keywords "health literacy" and "healthy lifestyle behaviors" were employed, identifying 206 studies. Subsequently, 53 studies meeting predetermined criteria were deemed suitable for inclusion in the meta-analysis. The analysis of the relationship between health literacy and healthy lifestyle behaviors revealed no publication bias. Despite heterogeneity among the studies, the correlation effect size was determined to be 0.278 using the random effect model. In the meta-analysis examining the effect of gender on health literacy, no publication bias was detected. Since there was heterogeneity among the studies, the average effect size was calculated as 0.078 according to the random effect model. Regarding the meta-analysis on the effect of chronic disease status on health literacy, no publication bias was observed, and due to homogeneity between the studies, the average effect size was determined to be -0.098 using the fixed effect model. A positive yet weak relationship was identified between health literacy and healthy lifestyle behaviors. Notably, gender was a significant sociodemographic factor affecting health literacy, with higher levels observed in women. Moreover, individuals without chronic diseases exhibited higher mean health literacy scores than those with chronic diseases.

PENGEMBANGAN E-COMIC BERBASIS PROBLEM BASED LEARNING (PBL) MATERI SISTEM EKSKRESI MANUSIA UNTUK MENINGKATKAN HASIL BELAJAR SISWA

This research was conducted because E-comic learning media based on Problem Based Learning material on the human excretory system was not yet available at Lolowau 2 State Junior High School and student learning outcomes did not meet the Minimum Completeness Criteria. The research applied is development research (Development Research) with the four D model. The results of the research obtained an average validity test score of 89.52%, practicality test by teachers 3.50 while students 3.57 and an average effectiveness test score 90.14 so it can be concluded that E-comic learning media can be applied in the learning process of human excretory system material in class Vlll.

Heterogeneity in the Effect of Early Goal-Directed Therapy for Septic Shock: A Secondary Analysis of Two Multicenter International Trials.

The optimal approach for resuscitation in septic shock remains unclear despite multiple randomized controlled trials (RCTs). Our objective was to investigate whether previously uncharacterized variation across individuals in their response to resuscitation strategies may contribute to conflicting average treatment effects in prior RCTs. We randomly split study sites from the Australian Resuscitation of Sepsis Evaluation (ARISE) and Protocolized Care for Early Septic Shock (ProCESS) trials into derivation and validation cohorts. We trained machine learning models to predict individual absolute risk differences (iARDs) in 90-day mortality in derivation cohorts and tested for heterogeneity of treatment effect (HTE) in validation cohorts and swapped these cohorts in sensitivity analyses. We fit the best-performing model in a combined dataset to explore roles of patient characteristics and individual components of early goal-directed therapy (EGDT) to determine treatment responses. Eighty-one sites in Australia, New Zealand, Hong Kong, Finland, Republic of Ireland, and the United States. Adult patients presenting to the emergency department with severe sepsis or septic shock. EGDT vs. usual care. A local-linear random forest model performed best in predicting iARDs. In the validation cohort, HTE was confirmed, evidenced by an interaction between iARD prediction and treatment (p < 0.001). When patients were grouped based on predicted iARDs, treatment response increased from the lowest to the highest quintiles (absolute risk difference [95% CI], -8% [-19% to 4%] and relative risk reduction, 1.34 [0.89-2.01] in quintile 1 suggesting harm from EGDT, and 12% [1-23%] and 0.64 [0.42-0.96] in quintile 5 suggesting benefit). Sensitivity analyses showed similar findings. Pre-intervention albumin contributed the most to HTE. Analyses of individual EGDT components were inconclusive. Treatment response to EGDT varied across patients in two multicenter RCTs with large benefits for some patients while others were harmed. Patient characteristics, including albumin, were most important in identifying HTE.

The application of Bayesian method in estimating heterogeneity of treatment effect

It is well recognized that the benefit of medical interventions may not be distributed evenly in the target population due to patient heterogeneity, and conclusions based on traditional randomized clinical trials do not apply to everyone. Considering the increasing cost of randomized trials and difficulties in recruiting patients, there is an urgent need to develop analytical methods to estimate treatment effects in subgroups. In particular, due to limited sample sizes of subgroups, standard analysis tends to yield wide confidence intervals for the treatment effect, which are often uninformative. In this article, the superiority of the empirical Bayes estimate of the conditional average treatment effect is demonstrated by using a linear regression model to specifically represent treatment-covariate interactions. To obtain more accurate prior distributions and posterior estimates of treatment effects in subgroups, we utilize the covariate-dependent precision parameter across subgroups. Based on subgroup data obtained from clinical trials, the covariate-dependent precision parameter is used to assess the similarity of treatment effects across subgroups, which is an approach to obtain more reasonable prior information. To verify the validity of the empirical Bayes method, we evaluate it by a real clinical trial comparing insulin and metformin.

Effect of community – facility linked interventions on maternal health service utilization and newborn care in rural low-resource settings in Eastern Uganda

BackgroundImproving maternal and newborn care (MNC) in hard-to-reach areas is essential for accelerating progress towards sustainable development goals (SDGs). We implemented the “Communities in which Mothers and Newborns Thrive (COMONETH) project” in rural settings of eastern Uganda between 2017 and 2020 to reduce barriers to accessing MNC services. We evaluated the effect of the COMONETH intervention on enhancing the utilization of MNC services and the adoption of appropriate care practices in Luuka district, Uganda.MethodsWe used a pre- and post-comparison design to measure the effect of a demand-supply linked COMONETH intervention on MNC indicators. We trained Community Health Workers (CHW) to educate and refer expectant mothers to health facilities when needed. We also showed videos to pregnant women on identification of pregnancy danger signs, mentored and simulated health workers with PRONTO, and improved obstetric surgery at the referral facilities. We assessed antenatal care (ANC), facility delivery, postnatal care (PNC), and newborn care practices. We used optimal full propensity score matching, and weighted logistic regression and then estimated average treatment effect on the treated (ATT) of the intervention on MNC outcomes on the odds ratio scale.ResultsA total of 583 women at baseline and 619 at endline participated in the study. The intervention was associated with increased odds of attending 4 ANC visits (OR = 1.26, 95% CI = 1.07–1.49), 8 ANC visits (OR = 2.27, 95% CI = 1.06–4.82) and utilization of PNC services (OR = 1.40, 95% CI = 1.20–1.63). We did not observe a significant association between intervention and early ANC attendance (OR = 0.88, 95% CI 0.80–1.00) and facility deliveries (OR = 0.99, 95% CI = 0.93–1.06). The intervention strategy was associated with improvements in practices: delayed bathing (OR = 1.22, 95% CI = 1.06–1.40), putting nothing on the cord (OR = 1.42, 95% CI = 1.27–1.59) and wrapping of babies immediately (OR = 1.08, 95% CI = 1.03–1.14).ConclusionsThe findings demonstrated the potential of a demand-supply linked intervention to improve MNC outcomes in low-resource settings and should be promoted in similar settings. Interventions that strengthen the quality of care at health facilities and bridge demand-side gaps can improve MNC practices and reduce morbidity and mortality in rural settings.

Childbearing Histories and Midlife Cognition: Accounting for Early Life Factors.

Childbearing histories-for example, parity and age at first birth-matter for the health outcomes of mid- and later-life women. There is growing evidence that childbearing may shape cognitive outcomes. However, previous research is not definitive due to its inability to account for selection. Selection is critical to address given that multiple factors, including socioeconomic background and cognition in adolescence, place women at risk for both specific childbearing experiences and poor cognitive functioning. We analyze the 1979 National Longitudinal Survey of Youth (NLSY79) (N=3,668), a longitudinal nationally representative dataset from the US that began collecting data during respondents' late teens and early 20s. We estimate the average treatment effects (ATEs) of childbearing histories on midlife memory and cognition using propensity-score matching techniques that incorporate an expansive set of early-life factors. In models adjusting for early life covariates, we find that any births, high parity, and early first birth are associated with worse self-reported memory, but not cognitive functioning scores. After addressing the influence of early life factors through matching techniques, the only robust differences relate to any births and early first births with self-reported memory. Selection into specific childbearing experiences partially drives the link between childbearing and cognition at mid-life, with cascading implications into later life. We suggest incorporating childbearing and early life factors into models to identify social determinants of memory and cognitive functioning.

Kahoot! Game‐based digital learning platform: A comprehensive meta‐analysis

AbstractBackgroundIn recent years, the widespread use of technology in classrooms has encouraged the transition from traditional lecture methods to digital‐based learning environments. Technological game‐based learning platforms, such as Kahoot!, which are used to encourage students' active participation and interaction in learning environments, are used significantly by teachers and students in educational environments worldwide.ObjectivesThis article aims to examine the effects of Kahoot, a digital learning platform, on education through meta‐analysis. This meta‐analysis provides a holistic understanding of the potential impact of Kahoot on education by synthesizing the results of various experimental studies. This study evaluates the influence of Kahoot on key educational variables, such as academic achievement, retention, motivation, anxiety and attitude, which are essential for enhancing teaching methods and optimizing learning environments.MethodsThe study conducted a meta‐analysis following the guidelines outlined in the Preferred Reporting Items for Systematic Reviews and Meta‐Analysis (PRISMA). A total of 43 studies that met the specified criteria were included in the sample, providing a comprehensive overview of the impact of Kahoot across different contexts. The sample was n = 1706 for the experimental group and n = 1647 for the control group.Results and ConclusionThe findings from the meta‐analysis indicate that Kahoot has a significant moderate positive effect on academic achievement, with an average effect size of 0.772 (95%CI: 0.540–1.004). The analysis also shows a very large positive effect on retention, with an average effect size of 1.492, suggesting that students using Kahoot tend to have significantly higher retention compared with those who do not. For motivation, Kahoot demonstrates a large positive effect, with an average effect size of 0.960, indicating that students using Kahoot tend to be more motivated. The impact on anxiety is less clear, with a small negative effect size of −0.338, suggesting a moderate reduction in anxiety levels among students using Kahoot. Lastly, Kahoot appears to have a medium positive effect on students' attitudes towards learning, with an average effect size of 0.678.TakeawaysThese results underscore the potential of Kahoot as an effective educational tool. The results of this study provide valuable guiding information for educators and policy makers by helping to optimize teaching methods and learning environments through the effective use of digital tools, such as Kahoot. The findings suggest that Kahoot can increase academic achievement, retention, motivation and attitudes and potentially reduce anxiety, making it a promising digital tool for modern educational practice.

Model Averaging for Estimating Treatment Effects With Binary Responses

ABSTRACTIn this article, we present a novel approach for estimating the conditional average treatment effect in models with binary responses. Our proposed method involves model averaging, and we establish a weight choice criterion based on jackknife model averaging. We analyze the theoretical properties of this approach, including its asymptotic optimality in achieving the lowest possible squared error and the convergence rate of the weights assigned to correctly specified models. Additionally, we introduce a new matching method that combines partition and nearest neighbor pairing, leveraging the strengths of both techniques. To evaluate the performance of our method, we conduct comparisons with existing approaches via a Monte Carlo study and a real data analysis. Overall, our results demonstrate the effectiveness and practicality of our proposed approach for estimating the conditional average treatment effect in binary response models.

On the role of surrogates in the efficient estimation of treatment effects with limited outcome data

Abstract In many experimental and observational studies, the outcome of interest is often difficult or expensive to observe, reducing effective sample sizes for estimating average treatment effects (ATEs) even when identifiable. We study how incorporating data on units for which only surrogate outcomes not of primary interest are observed can increase the precision of ATE estimation. We refrain from imposing stringent surrogacy conditions, which permit surrogates as perfect replacements for the target outcome. Instead, we supplement the available, albeit limited, observations of the target outcome with abundant observations of surrogate outcomes, without any assumptions beyond unconfounded treatment assignment and missingness and corresponding overlap conditions. To quantify the potential gains, we derive the difference in efficiency bounds on ATE estimation with and without surrogates, both when an overwhelming or comparable number of units have missing outcomes. We develop robust ATE estimation and inference methods that realize these efficiency gains. We empirically demonstrate the gains by studying long-term-earning effects of job training.

A Meta-Analytic Evaluation: Investigating Evidence for the Validity of the Cognitive Abilities Test

Cognitive Abilities Test (CogAT) is one of the most frequently used gifted identification tools. In this meta-analytic study, we investigated empirical evidence of the validity of CogAT, in relation to different types of instruments. After reviewing 1,480 studies, a total of 24 with 33 effect sizes were included in the meta-analysis. According to our findings, the average effect size of r was found to be .63 with a 95% confidence interval [.57, .69]. Based on the heterogeneity test, significant variation due to the systematic between-study differences exists among the included correlations. Egger’s test for funnel plot asymmetry also indicates that no obvious publication bias exists in our study pool, which indicates there might not be a serious threat to alter the obtained results with publication bias. The moderator analysis revealed Lohman’s authorship and publication type influenced the effect size differences among studies. CogAT’s overall correlation with other identification tools (.63) might suggest using at least one more identification tool besides CogAT.

HIGHLY ADAPTIVE LASSO: MACHINE LEARNING THAT PROVIDES VALID NONPARAMETRIC INFERENCE IN REALISTIC MODELS.

Understanding treatment effects on health-related outcomes using real-world data requires defining a causal parameter and imposing relevant identification assumptions to translate it into a statistical estimand. Semiparametric methods, like the targeted maximum likelihood estimator (TMLE), have been developed to construct asymptotically linear estimators of these parameters. To further establish the asymptotic efficiency of these estimators, two conditions must be met: 1) the relevant components of the data likelihood must fall within a Donsker class, and 2) the estimates of nuisance parameters must converge to their true values at a rate faster than . The Highly Adaptive LASSO (HAL) satisfies these criteria by acting as an empirical risk minimizer within a class of càdlàg functions with a bounded sectional variation norm, which is known to be Donsker. HAL achieves the desired rate of convergence, thereby guaranteeing the estimators' asymptotic efficiency. The function class over which HAL minimizes its risk is flexible enough to capture realistic functions while maintaining the conditions for establishing efficiency. Additionally, HAL enables robust inference for non-pathwise differentiable parameters, such as the conditional average treatment effect (CATE) and causal dose-response curve, which are important in precision health. While these parameters are often considered in machine learning literature, these applications typically lack proper statistical inference. HAL addresses this gap by providing reliable statistical uncertainty quantification that is essential for informed decision-making in health research.

Visual SLAM system based on dynamic semantic features

Aiming at the problem that dynamic objects (such as pedestrians, vehicles, and animals) in real scenes affect the positioning and mapping accuracy of visual SLAM (Simultaneous Localization and Mapping), a YOLOv3-ORB-SLAM3 algorithm is proposed based on ORB-SLAM3 (Oriented FAST and Rotated BRIEF-Simultaneous Localization and Mapping 3). The algorithm adds a semantic thread on the basis of ORB-SLAM3, and adopts a dual-thread mechanism for dynamic and static scene feature extraction: the semantic thread uses YOLOv3 to perform semantic recognition target detection on dynamic objects in the scene, and removes outliers from the extracted dynamic area feature points; the tracking thread extracts scene area features through ORB features, and obtains static scene features combined with semantic information and sends them to the backend, thereby eliminating the interference of dynamic scenes on the system and improving the positioning accuracy of the visual SLAM algorithm. Verified using the TUM (Technical University of Munich) dataset, the results show that the ATE (Average Treatment Effect) index of the YOLOv3-ORB-SLAM3 algorithm in the monocular mode is about 30% lower than that of the ORB-SLAM3 algorithm, and the ATE index of the dynamic sequence in the RGB-D (Red, Green and Blue-Depth) mode is reduced 10%, while the static sequence has no significant decrease.

Inference in Experiments with Matched Pairs and Imperfect Compliance

This paper studies inference for the local average treatment effect in randomized controlled trials with imperfect compliance where treatment status is determined according to “matched pairs.” By “matched pairs,” we mean that units are sampled i.i.d. from the population of interest, paired according to observed, baseline covariates and finally, within each pair, one unit is selected at random for treatment. Under weak assumptions governing the quality of the pairings, we first derive the limit distribution of the usual Wald (i.e., two-stage least squares) estimator of the local average treatment effect. We show further that conventional heteroskedasticity-robust estimators of the Wald estimator’s limiting variance are generally conservative, in that their probability limits are (typically strictly) larger than the limiting variance. We therefore provide an alternative estimator of the limiting variance that is consistent. Finally, we consider the use of additional observed, baseline covariates not used in pairing units to increase the precision with which we can estimate the local average treatment effect. To this end, we derive the limiting behavior of a two-stage least squares estimator of the local average treatment effect which includes both the additional covariates in addition to pair fixed effects, and show that its limiting variance is always less than or equal to that of the Wald estimator. To complete our analysis, we provide a consistent estimator of this limiting variance. A simulation study confirms the practical relevance of our theoretical results. Finally, we apply our results to revisit a prominent experiment studying the effect of macroinsurance on microenterprise in Egypt.

Design-Based Theory for Lasso Adjustment in Randomized Block Experiments and Rerandomized Experiments

Blocking, a special case of rerandomization, is routinely implemented in the design stage of randomized experiments to balance the baseline covariates. This study proposes a regression adjustment method based on the least absolute shrinkage and selection operator (Lasso) to efficiently estimate the average treatment effect in randomized block experiments with high-dimensional covariates. We derive the asymptotic properties of the proposed estimator and outline the conditions under which this estimator is more efficient than the unadjusted one. We provide a conservative variance estimator to facilitate valid inferences. Our framework allows one treated or control unit in some blocks and heterogeneous propensity scores across blocks, thus including paired experiments and finely stratified experiments as special cases. We further accommodate rerandomized experiments and a combination of blocking and rerandomization. Moreover, our analysis allows both the number of blocks and block sizes to tend to infinity, as well as heterogeneous treatment effects across blocks without assuming a true outcome data-generating model. Simulation studies and two real-data analyses demonstrate the advantages of the proposed method.

Uncovering the drivers of food insecurity in Cameroon: insights from a nationwide cross-sectional analysis

BackgroundDespite global efforts to achieve zero hunger, food insecurity remains a critical challenge in several African countries, including Cameroon. This study aims to identify sociodemographic predictors of food insecurity across Cameroon through a comprehensive, nationwide cross-sectional analysis.MethodsData for this study were drawn from the 2018 Cameroon Demographic and Health Survey (CDHS). Food insecurity levels were evaluated using the Food Insecurity Experience Scale (FIES). To estimate the probabilities of moderate and severe food insecurity among different sociodemographic groups, logistic regression models were applied, with results expressed as average marginal effects (AME).ResultsThe findings reveal that approximately 24.86% of participants experienced moderate food insecurity, while 28.96% faced severe food insecurity. Among men, the proportion experiencing severe food insecurity was 38.8%, compared to 24.3% for women. Multivariable regression analysis showed that severe food insecurity was less likely among women [AME = 0.84, 95% CI = 0.83,0.86], Muslims [AME = 0.91, 95%CI = 0.90,0.93], individuals with higher education levels (secondary education: AME = 0.93, 95%CI = 0.90,0.95; higher education: AME = 0.87, 95%CI = 0.85,0.90), those owning land (either alone or jointly) [AME = 0.92, 95%CI = 0.89,0.96], wealthiest households (moderate food insecurity: AME = 0.91, 95%CI = 0.88,0.93; severe food insecurity: AME = 0.73, 95%CI = 0.70,0.75), female-headed households [AME = 0.97, 95%CI = 0.96,0.99], and rural residents [AME = 0.97, 95%CI = 0.95,0.98].ConclusionsThese findings underscore that food insecurity affects a substantial portion of the Cameroonian population, with certain sociodemographic groups more vulnerable than others. This study proposes targeted policy recommendations to address food insecurity in Cameroon, including social assistance programs for at-risk groups, investments in socioeconomic empowerment, improvements in agricultural productivity, and ongoing research to guide evidence-based interventions.

Does Employing Skilled Immigrants Enhance Competitive Performance? Evidence from European Football Clubs

We investigate the effect of employing skilled immigrants on the competitive performance of organizations by studying European football (soccer) clubs in Germany, Italy, France, England, and Spain from 1990 to 2020. Microdata from this setting offers unusual transparency about players’ birthplaces and their contributions to organizational performance. Further, country-level rules govern how many immigrant players clubs can deploy. Using changes to these rules as the basis for instrumental variables, we find that the number of immigrant players in the club’s starting lineup has a positive local average treatment effect on the club’s performance. We show that this occurs for two related reasons. First, immigrants exhibit higher individual talent. Second, immigrants play a coordinating role that enables the organization to broaden the variety of on-field strategies and actions it uses to outperform rivals. The latter mechanism is novel to the literature. This paper was accepted by Olav Sorenson, organizations. Funding: F. Morales acknowledges research funding from Agencia Nacional de Investigación y Desarrollo, Chile (Fondecyt de Iniciación) [Grant 11200342]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2021.03356 .

International spillovers of unconventional monetary policy: A meta-analysis

AbstractThe impacts of the unconventional monetary policy measures adopted by central banks after the 2007 financial crisis have been the focus of an increasing number of empirical studies. While some studies have focused on the impacts on the domestic economy, others have examined the international spillover effects of the policies adopted by the major central banks. The latter studies have, however, reported heterogeneous results. In this paper, we develop a meta-analysis of the empirical literature that examines the spillover effects of unconventional monetary policy on international capital flows. We find that, while the global average effect is not statistically different from zero, there are specific effects that vary significantly according to the development level of the destination country, the nature of the capital flow, the Central Bank that adopts the UMP, and the type and year of implementation of the UMP measure.

Nonseparable panel models with index structure and correlated random effects

. To facilitate semiparametric estimation of general discrete-choice, censored, sample selection, and other complex panel data models, we study identification and estimation of nonseparable multiple-index models in panel data with correlated random effects and a fixed number of time periods. The parameter vectors of interest are shown to be identified up to multiplicative constants and the average marginal effects are identified under the assumption that the distribution of individual effects depends on the explanatory variables only through their averages across time. Under this assumption, we propose to estimate the unknown parameters by the generalized method of moments based on the average and outer product of the difference of derivatives of the regression function. The rate of convergence and asymptotic distribution is established both for the proposed parameter estimates and the average marginal effects. We conduct Monte Carlo simulation studies to assess finite-sample performance of the proposed estimator. We also use it to model dynamic earnings of women, and using our general identification results, we find a negative effect of the number of children not only on the selection into employment as usual, but also on the average earnings.