Methods For Mediation Analysis Research Articles

The association between telomere length and blood lipids: a bidirectional two-sample Mendelian randomization study

BackgroundObservational studies suggest an association between telomere length (TL) and blood lipid (BL) levels. Nevertheless, the causal connections between these two traits remain unclear. We aimed to elucidate whether genetically predicted TL is associated with BL levels via Mendelian randomization (MR) and vice versa.MethodsWe obtained genetic instruments associated with TL, triglycerides (TG), low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C), apolipoprotein A-1 (ApoA-1) and apolipoprotein B (ApoB) from large-scale genome-wide association studies (GWASs). The causal relationships between TL and BL were investigated via bidirectional MR, multivariable MR and mediation analysis methods. The inverse variance weighted (IVW) method was employed as the principal methodology, complemented by several other estimators to enhance the robustness of the analysis.ResultsIn the forward MR analyses, we identified significant positive correlation between genetically predicted TL and the levels of TG (β=0.04, 95% confidence interval [CI]: 0.01 to 0.06, p = 0.003). In the reverse MR analysis, TG (β=0.02, 95% CI: 0.01 to 0.03, p = 0.004), LDL-C (β=0.03, 95% CI: 0.01 to 0.04, p = 0.001) and ApoB (β=0.03, 95% CI: 0.01 to 0.04, p = 9.71×10–5) were significantly positively associated with TL, although this relationship was not observed in the multivariate MR analysis. The mediation analysis via two-step MR showed no significant mediation effects acting through obesity-related phenotypes in analysis of TL with TG, while the effect of LDL-C on TL was partially mediated by body mass index (BMI) in the reverse direction, with mediated proportion of 12.83% (95% CI: 0.62% to 25.04%).ConclusionsOur study indicated that longer TL were associated with higher TG levels, while conversely, higher TG, LDL-C, and ApoB levels predicted longer TL, with BMI partially mediating these effects. Our findings present valuable insights into the development of preventive strategies and interventions that specifically target TL-related aging and age-related diseases.

Causal mediation analysis with a three-dimensional image mediator.

Causal mediation analysis is increasingly abundant in biology, psychology, and epidemiology studies and so forth. In particular, with the advent of the big data era, the issue of high-dimensional mediators is becoming more prevalent. In neuroscience, with the widespread application of magnetic resonance technology in the field of brain imaging, studies on image being a mediator emerged. In this study, a novel causal mediation analysis method with a three-dimensional image mediator is proposed. We define the average casual effects under the potential outcome framework, explore several sufficient conditions for the valid identification, and develop techniques for estimation and inference. To verify the effectiveness of the proposed method, a series of simulations under various scenarios is performed. Finally, the proposed method is applied to a study on the causal effect of mother's delivery mode on child's IQ development. It is found that cesarean section may have a negative effect on intellectual performance and that this effect is mediated by white matter development. Additional prospective and longitudinal studies may be necessary to validate these emerging findings.

Bayesian Mediation Analysis with an Application to Explore Racial Disparities in the Diagnostic Age of Breast Cancer

A mediation effect refers to the effect transmitted by a mediator intervening in the relationship between an exposure variable and a response variable. Mediation analysis is widely used to identify significant mediators and to make inferences on their effects. The Bayesian method allows researchers to incorporate prior information from previous knowledge into the analysis, deal with the hierarchical structure of variables, and estimate the quantities of interest from the posterior distributions. This paper proposes three Bayesian mediation analysis methods to make inferences on mediation effects. Our proposed methods are the following: (1) the function of coefficients method; (2) the product of partial difference method; and (3) the re-sampling method. We apply these three methods to explore racial disparities in the diagnostic age of breast cancer patients in Louisiana. We found that African American (AA) patients are diagnosed at an average of 4.37 years younger compared with Caucasian (CA) patients (57.40 versus 61.77, p< 0.0001). We also found that the racial disparity can be explained by patients’ insurance (12.90%), marital status (17.17%), cancer stage (3.27%), and residential environmental factors, including the percent of the population under age 18 (3.07%) and the environmental factor of intersection density (9.02%).

Mediation analysis using incomplete information from publicly available data sources.

Our work was motivated by the question whether, and to what extent, well-established risk factors mediate the racial disparity observed for colorectal cancer (CRC) incidence in the United States. Mediation analysis examines the relationships between an exposure, a mediator and an outcome. All available methods require access to a single complete data set with these three variables. However, because population-based studies usually include few non-White participants, these approaches have limited utility in answering our motivating question. Recently, we developed novel methods to integrate several data sets with incomplete information for mediation analysis. These methods have two limitations: (i) they only consider a single mediator and (ii) they require a data set containing individual-level data on the mediator and exposure (and possibly confounders) obtained by independent and identically distributed sampling from the target population. Here, we propose a new method for mediation analysis with several different data sets that accommodates complex survey and registry data, and allows for multiple mediators. The proposed approach yields unbiased causal effects estimates and confidence intervals with nominal coverage in simulations. We apply our method to data from U.S. cancer registries, a U.S.-population-representative survey and summary level odds-ratio estimates, to rigorously evaluate what proportion of the difference in CRC risk between non-Hispanic Whites and Blacks is mediated by three potentially modifiable risk factors (CRC screening history, body mass index, and regular aspirin use).

Partner’s unemployment and subjective well-being: The mediating role of relationship functioning

Unemployment affects not only the subjective well-being of the individual, but also that of the partner. Based on the life course perspective and the spillover-crossover-model, we examine the mediating role of relationship functioning for such crossover effects of partner’s unemployment on subjective well-being. We also test whether gender differences in the mechanism of relationship functioning can explain the larger overall crossover effects on women compared to men. We use data from the German Family Panel pairfam (2008/09–2018/19), which provide more direct and comprehensive measures of relationship functioning than previous research, and allow us to examine couples’ communication and interactions, their conflict styles and behaviors, relationship satisfaction, and perceived relationship instability as mediators. To analyze the impact of the partner’s transition to unemployment on subjective well-being, we use fixed effects panel regression models and the product method of mediation analysis to estimate the indirect effects of relationship functioning. The results show that a partner’s transition to unemployment has a negative impact on one’s own well-being. The effects are more pronounced for women than men which can be partly explained by gender-specific effects of the partner’s unemployment on various aspects of relationship functioning, rather than by differential effects of the latter on one’s own well-being.

Methods for the Analysis of Multiple Epigenomic Mediators in Environmental Epidemiology.

Epigenetic changes can be highly influenced by environmental factors and have in turn been proposed to influence chronic disease. Being able to quantify to which extent epigenomic processes are mediators of the association between environmental exposures and diseases is of interest for epidemiologic research. In this review, we summarize the proposed mediation analysis methods with applications to epigenomic data. The ultra-high dimensionality and high correlations that characterize omics data have hindered the precise quantification of mediated effects. Several methods have been proposed to deal with mediation in high-dimensional settings, including methods that incorporate dimensionality reduction techniques to the mediation algorithm. Although important methodological advances have been conducted in the previous years, key challenges such as the development of sensitivity analyses, dealing with mediator-mediator interactions, including environmental mixtures as exposures, or the integration of different omic data should be the focus of future methodological developments for epigenomic mediation analysis.

Disparities in Cytomegalovirus Infection Rates by Race and Ethnicity among Pediatric Allogeneic Hematopoietic Cell Transplantation Recipients at a Single Center

Previous literature has reported cytomegalovirus (CMV) infection rate disparities among racial/ethnic groups of hematopoietic cell transplantation (HCT) recipients. Because race and ethnicity categorizations are social constructs unlikely to affect biological systems, it is likely there are covariates on the pathway to CMV detection, known as mediators, that can explain the observed disparity. Recent developments in mediation analysis methods enable the analysis of time-to-event outcomes, allowing an investigation of these disparities to also consider the timing of CMV infection detection relative to HCT. This study aimed to explore whether racial and ethnic CMV infection disparities existed within a population of HCT recipients at our center, and whether clinical covariates explained any observed association. The study cohort included all recipients of allogeneic HCT performed at the Children's Hospital of Philadelphia between January 2004 and April 2017 who were CMV PCR-negative pretransplantation, had known donor/recipient CMV serology, and were under blood CMV PCR surveillance. Subjects were followed for 100 days post-HCT. Accelerated failure time models using subject's reported race/ethnicity, dichotomized into non-Hispanic White (NHW) and non-NHW, and exposure and time to CMV detection as outcomes examined whether selected clinical factors-donor/recipient CMV serostatus, recipient age, indication for HCT, hematopoietic cell source, match quality-mediated any identified exposure-outcome association. The analysis included 348 HCTs performed in 335 subjects, with 86 episodes (24.7%) in which CMV was detected via PCR analysis. The accelerated failure time model without mediators estimated that non-NHW subjects had fewer CMV-free survival days (time ratio, .21; 95% confidence interval, .10 to .44). Any hypothesized mediator mediated at most 5% of the total association between race/ethnicity and time to CMV detection. Non-NHW HCT recipients had fewer CMV-free survival days than NHW recipients; none of the clinical factors hypothesized to mediate this association accounted for a significant component of total association. Further research should focus on nonclinical factors influenced by systemic racism to better understand their effect on CMV infection among HCT recipients.

Microbiome-enabled genomic selection improves prediction accuracy for nitrogen-related traits in maize.

Root-associated microbiomes in the rhizosphere (rhizobiomes) are increasingly known to play an important role in nutrient acquisition, stress tolerance, and disease resistance of plants. However, it remains largely unclear to what extent these rhizobiomes contribute to trait variation for different genotypes and if their inclusion in the genomic selection protocol can enhance prediction accuracy. To address these questions, we developed a microbiome-enabled genomic selection method that incorporated host SNPs and amplicon sequence variants from plant rhizobiomes in a maize diversity panel under high and low nitrogen (N) field conditions. Our cross-validation results showed that the microbiome-enabled genomic selection model significantly outperformed the conventional genomic selection model for nearly all time-series traits related to plant growth and N responses, with an average relative improvement of 3.7%. The improvement was more pronounced under low N conditions (8.4-40.2% of relative improvement), consistent with the view that some beneficial microbes can enhance N nutrient uptake, particularly in low N fields. However, our study could not definitively rule out the possibility that the observed improvement is partially due to the amplicon sequence variants being influenced by microenvironments. Using a high-dimensional mediation analysis method, our study has also identified microbial mediators that establish a link between plant genotype and phenotype. Some of the detected mediator microbes were previously reported to promote plant growth. The enhanced prediction accuracy of the microbiome-enabled genomic selection models, demonstrated in a single environment, serves as a proof-of-concept for the potential application of microbiome-enabled plant breeding for sustainable agriculture.

Multiply robust estimation of natural indirect effects withmultiple ordered mediators.

Multiple mediation analysis is a powerful methodology to assess causal effects in the presence of multiple mediators. Several methodologies, such as G-computation and inverse-probability-weighting, have been widely used to draw inferences about natural indirect effects (NIEs). However, a limitation of these methods is their potential for model misspecification. Although powerful semiparametric methods with high robustness and consistency have been developed for inferring average causal effects and for analyzing the effects of a single mediator, a comparably robust method for multiple mediation analysis is still lacking. Therefore, this theoretical study proposes a method of using multiply robust estimators of NIEs in the presence of multiple ordered mediators. We show that the proposed estimators not only enjoy the multiply robustness to model misspecification, they are also consistent and asymptotically normal under regular conditions. We also performed simulations for empirical comparisons of the finite-sample properties between our multiply robust estimators and existing methods. In an illustrative example, a dataset for liver disease patients in Taiwan is used to examine the mediating roles of liver damage and liver cancer in the pathway from hepatitis B/C virus infection to mortality. The model is implemented in the open-source R package "MedMR."

Potential causal links and mediation pathway between urban greenness and lung cancer mortality: Result from a large cohort (2009 to 2020)

Urban greenness, as a vital component of the urban environment, plays a critical role in mitigating the adverse effects of rapid urbanization and supporting urban sustainability. However, the causal links between urban greenness and lung cancer mortality and its potential causal pathway remain poorly understood. Based on a prospective community-based cohort with 581,785 adult participants in southern China, we applied a doubly robust Cox proportional hazard model to estimate the causal associations between urban greenness exposure and lung cancer mortality. A general multiple mediation analysis method was utilized to further assess the potential mediating roles of various factors including particulate matter (PM1, PM2.5–1, and PM10–2.5), temperature, physical activity, and body mass index (BMI). We observed that each interquartile range (IQR: 0.06) increment in greenness exposure was inversely associated with lung cancer mortality, with a hazard ratio (HR) of 0.89 (95 %CI: 0.83, 0.96). The relationship between greenness and lung cancer mortality might be partially mediated by particulate matter, temperature, and physical activity, yielding a total indirect effect of 0.826 (95 % CI: 0.769, 0.887) for each IQR increase in greenness exposure. Notably, the protective effect of greenness against lung cancer mortality could be achieved primarily by reducing the particulate matter concentration.

Living arrangements, activity participation and depression among older Chinese adults

ObjectivesWe examined the relationship among living arrangements, activity participation and depression and the mediating effects of activity participation on the relationship between living arrangements and depression. Study designThis was a cross-sectional study based on nationally representative data. Methods9647 older adults aged 60 years and over were recruited from the 2018 Chinese Longitudinal Healthy Longevity Survey. Three-step regression and mediation analysis methods were used. ResultsCompared with older adults living with family members, those living in institutions attended fewer activities and experienced higher depression rates, and those living alone attended more activities and experienced higher depression rates. In the group living with family members, living with a spouse was an important way to increase activity participation and reduce depression. Mediation analysis suggested that activity participation mediated the impact of living arrangements on depression. Attending more activities could alleviate depression for older adults who are living alone, living in institutions and living without a spouse. ConclusionOur findings suggest an emphasis on the role of spouses and activity participation during depression interventions among older adults.

Methods for mediation analysis with high-dimensional DNA methylation data: Possible choices and comparisons.

Epigenetic researchers often evaluate DNA methylation as a potential mediator of the effect of social/environmental exposures on a health outcome. Modern statistical methods for jointly evaluating many mediators have not been widely adopted. We compare seven methods for high-dimensional mediation analysis with continuous outcomes through both diverse simulations and analysis of DNAm data from a large multi-ethnic cohort in the United States, while providing an R package for their seamless implementation and adoption. Among the considered choices, the best-performing methods for detecting active mediators in simulations are the Bayesian sparse linear mixed model (BSLMM) and high-dimensional mediation analysis (HDMA); while the preferred methods for estimating the global mediation effect are high-dimensional linear mediation analysis (HILMA) and principal component mediation analysis (PCMA). We provide guidelines for epigenetic researchers on choosing the best method in practice and offer suggestions for future methodological development.

Causal moderated mediation analysis: Methods and software.

Research questions regarding how, for whom, and where a treatment achieves its effect on an outcome have become increasingly valued in substantive research. Such questions can be answered by causal moderated mediation analysis, which assesses the heterogeneity of the mediation mechanism underlying the treatment effect across individual and contextual characteristics. Various moderated mediation analysis methods have been developed under the traditional path analysis/structural equation modeling framework. One challenge is that the definitions of moderated mediation effects depend on statistical models of the mediator and the outcome, and no solutions have been provided when either the mediator or the outcome is binary, or when the mediator or outcome model is nonlinear. In addition, it remains unclear to empirical researchers how to make causal arguments of moderated mediation effects due to a lack of clarifications of the underlying assumptions and methods for assessing the sensitivity to violations of the assumptions. This article overcomes the limitations by developing general definition, identification, estimation, and sensitivity analysis for causal moderated mediation effects under the potential outcomes framework. We also developed a user-friendly R package moderate.mediation ( https://cran.r-project.org/web/packages/moderate.mediation/index.html ) that allows applied researchers to easily implement the proposed methods and visualize the initial analysis results and sensitivity analysis results. We illustrated the application of the proposed methods and the package implementation with a re-analysis of the National Evaluation of Welfare-to-Work Strategies (NEWWS) Riverside data.

Caring load and family caregivers' burden in China: the mediating effects of social support and social exclusion.

Caring for older adults with disabilities is a source of stress for family caregivers, and the lack of social support and the pressure of social exclusion might aggravate family caregiver burden. This study aimed to examine the association between caring load and family caregivers' burden, as well as the mediating effects of social support and social exclusion. Data used in this study was derived from the nationally representative database of the aged population in China, and 3,125 households with disabled old adults and their home-bound caregivers were eventually selected for this analysis. Regression methods and mediation analysis methods were employed in this study. The results indicated that there was a significant positive association between caring load and the caregiver burden, and specifically, social support intensity (rather than social support breadth) and passive social exclusion (rather than active social exclusion) played partial mediating effects. Furthermore, the contributions of mediating effects of social support intensity and passive social exclusion were 13-15 and 27-29%, respectively, and the total contribution of mediating effects was about 35-38%. Family caregivers' burden should be paid more attention to in the large population with rapidly aging speed like China, and more guidance services as well as support should be provided to family caregivers. In addition, it is crucial to focus on the community's social support and social exclusion in public policy innovation.

Hypertension and Stroke as Mediators of Air Pollution Exposure and Incident Dementia

Fine particulate matter air pollution (PM2.5) has been consistently associated with cardiovascular disease, which, in turn, is associated with an increased risk of dementia. As such, vascular dysfunction might be a mechanism by which PM2.5 mediates dementia risk, yet few prior epidemiological studies have examined this potential mechanism. To investigate whether hypertension and stroke serve as mediators and modifiers of the association of PM2.5 with incident dementia. As part of the Environmental Predictors of Cognitive Health and Aging (EPOCH) Project, this cohort study used biennial survey data collected between 1998 and 2016 from respondents of the Health and Retirement Study (HRS), a nationally representative, population-based, cohort in the US. Eligible participants were those over 50 years of age who were free of dementia at baseline and had complete exposure, mediator, outcome, and demographic data from the HRS. Data analysis was conducted from August to November 2022. Exposure to PM2.5, calculated for the 10 years preceding each person's baseline examination according to residential histories and spatiotemporal models. Incident dementia was identified using a validated algorithm based on cognitive testing and informant reports. The 4-way decomposition causal mediation analysis method was used to quantify the degree to which hypertension and stroke mediated or modified the association of PM2.5 with incident dementia after adjustment for individual-level and area-level covariates. Among 27 857 participants (mean [SD] age at baseline, 61 [10] years; 15 747 female participants [56.5%]; 19 249 non-Hispanic White participants [69.1%]), 4105 (14.7%) developed dementia during the follow-up period (mean [SD], 10.2 [5.6] years). Among participants with dementia, 2204 (53.7%) had a history of hypertension at baseline and 386 (9.4%) received a diagnosis of hypertension during the follow up. A total of 378 participants (9.2%) had a history of stroke at baseline and 673 (16.4%) developed stroke over the follow-up period. The IQR of baseline PM2.5 concentrations was 10.9 to 14.9 μg/m3. In fully adjusted models, higher levels of PM2.5 (per IQR) were not associated with increased risk of incident dementia (HR, 1.04; 95% CI, 0.98 to 1.11). Although there were positive associations of prevalent stroke (HR, 1.67; 95% CI, 1.48 to 1.88) and hypertension (HR, 1.15; 95% CI, 1.08 to 1.23) with incident dementia compared with those free of stroke and hypertension during follow-up, there was no statistically significant association of PM2.5 with stroke (odds ratio per IQR increment in PM2.5, 1.08; 95%CI, 0.91 to 1.29) and no evidence of an association of PM2.5 with hypertension (odds ratio per IQR increment in PM2.5, 0.99; 95%CI, 0.92 to 1.07). Concordantly, there was no evidence that hypertension or stroke acted as mediators or modifiers of the association of PM2.5 with incident dementia. Although the nonmediated interaction between PM2.5 and hypertension accounted for 39.2% of the total excess association (95% CI, -138.5% to 216.9%), the findings were not statistically significant. These findings suggest that although hypertension may enhance the susceptibility of individuals to air pollution, hypertension and stroke do not significantly mediate or modify the association of PM2.5 with dementia, indicating the need to investigate other pathways and potential mediators of risk.

The path analysis of entrepreneurship impacts on circular economy in emerging markets: a mediating role of digital technology

PurposeThe purpose of this article is to explore the impact of the firm's entrepreneurship for the transformation of circular economy (CE). The role of entrepreneurship is thought to be important for the process of four Rs in the CE, and the authors have tried to study the role and impact path of entrepreneurship in CE.Design/methodology/approachEmpirical data from Chinese listed firms are collected, and a measure of digital technology is constructed by text mining method. Mediation analysis method is used to test the proposed hypothesis.FindingsThe results show that the innovation entrepreneurship has a significant positive impact upon the CE and digital technology is playing a mediating role in the impact path. However, the business entrepreneurship is negatively affecting the CE adoption. Also, the proportion of shares hold by the institution has a heterogenous influence for the innovation entrepreneurship.Practical implicationsThis study guides policy makers about the role of entrepreneurship and the mediating effect of digital technology and to encourage the adoption of CE for firms.Originality/valueThis study reveals the mediation effect of digital technology in the impact of entrepreneurship on CE in the emerging market. The heterogeneity of the proportion of shares hold by the institutions is also analyzed in the empirical study.

Environmental stressors altered the groundwater microbiome and nitrogen cycling: A focus on influencing mechanisms and pathways

Nitrogen cycling, as an important biogeochemical process in groundwater, strongly impacts the energy and matter flow of groundwater ecology. Phthalate esters (PAEs) were screened as key environmental stressors in the groundwater of Beijing, contributing to the alteration of microbial community structure and functions; thus, it could be deduced that these stressors might influence nitrogen cycling that is almost exclusively mediated by microorganisms. Identification of the influences of PAEs on groundwater nitrogen cycling and exploration of the potential influence mechanisms and pathways are vital but still challenging. This study explored the influence mechanisms and pathways of the environmental stressor PAE on nitrogen cycling in groundwater collected from a typical monitoring station in Beijing based on high-throughput sequencing and bioinformatics analysis combined with mediation analysis methods. The results suggested that among the 5 detected PAEs, dimethyl phthalate and diethyl phthalate significantly negatively impacted nitrogen cycling processes, especially nitrogen fixation and denitrification processes (p < 0.05), in groundwater. Their influences were fully or partially mediated by functional microorganisms, particularly assigned keystone genera (such as Dechloromonas, Aeromonas and Noviherbaspirillum), whose abundance was significantly inhibited by these PAEs via dysregulation of carbohydrate metabolism and activation of defense mechanisms. These findings confirmed that the influences of environmental stressors PAEs on nitrogen cycling in groundwater might be mediated by the “PAE stress–groundwater microbiome–nitrogen cycling alteration” pathway. This study may advance the understanding of the consequences of environmental stressors on groundwater ecology and support the ecological hazard assessment of groundwater stressors.

Causal Mediation Analysis for an Ordinal Outcome with Multiple Mediators

Causal mediation analysis is a popular approach for investigating whether the effect of an exposure on an outcome is through a mediator to better understand the underlying causal mechanism. In recent literature, mediation analysis with multiple mediators has been proposed for continuous and dichotomous outcomes. In contrast, methods for mediation analysis for an ordinal outcome are still underdeveloped. In this paper, we first review mediation analysis methods with a continuous mediator for an ordinal outcome and then develop mediation analysis with a binary mediator for an ordinal outcome. We further consider multiple mediators for an ordinal outcome in the counterfactual framework and provide identification assumptions for identifying the mediation effects. Under the identification assumptions, we propose a regression-based method to estimate the mediation effects through multiple mediators while allowing the presence of exposure-mediator interactions. The closed-form expressions of mediation effects are also obtained for three scenarios: multiple continuous mediators, multiple binary mediators, and multiple mixed mediators. We conduct simulation studies to assess the finite sample performance of our new methods and present the biases, standard errors, and confidence intervals to demonstrate that our proposed estimators perform well in a wide range of practical settings. Finally, we apply our proposed methods to assess the mediation effects of candidate DNA methylation CpG sites in the causal pathway from socioeconomic index to body mass index.

A brief primer on conducting regression-based causal mediation analysis.

We provide an overview of regression-based causal mediation analysis in the field of traumatic stress and guidance on how to conduct mediation analysis using our R package regmedint. We discuss the causal interpretations of the quantities that causal mediation analysis estimates, including total, direct, and indirect effects, especially when the interaction between exposure and mediator is permitted. We discuss the assumptions that must be fulfilled for mediation analyses to validly estimate these causal quantities, discuss suitable study designs for assessing mediation, and describe how causal mediation analysis differs from traditional methods of mediation. To illustrate how to conduct and interpret mediation analysis using our R package regmedint, we use data from a published longitudinal study to assess the extent to which children's externalizing behavior mediates changes in parental negative feelings during the COVID-19 lockdown. We compare the results to those obtained using traditional methods, thus illustrating the importance of accounting for exposure-mediator interaction when an interaction may be present. When the exposure and the mediator interact, traditional methods can provide estimates of direct and indirect effects that differ from those provided by more flexible causal mediation methods. When the exposure and the mediator do not interact, traditional methods and causal mediation method may estimate similar direct and indirect effects depending on the model specification. In contrast to traditional methods of mediation analysis, regression-based causal mediation methods seek to estimate specific interventional quantities, not mere associations, and the causal methods explicitly allow for exposure-mediator interactions. We recommend using these methods by default rather than using more restrictive traditional methods. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Sustainable urbanization and vulnerability to climate change in Africa: Accounting for digitalization and institutional quality

AbstractThis study empirically examines the effect of sustainable urbanization on vulnerability to climate change over a sample of 52 African countries from 1996 to 2019. We use the two‐stage system generalized method of moments (GMM) empirical strategy and mediation analysis to assess direct and indirect impacts, respectively. The results of the direct analysis reveal that sustainable urbanization reduces vulnerability to climate change. The results of the indirect analysis also show that sustainable urbanization significantly reduces vulnerability to climate change through the channels of digitalization and institutional quality. The results also highlight that considering the direct effect of sustainable urbanization alone underestimates the impact of reducing vulnerability to climate change. The results are robust to an alternative indicator of vulnerability to climate and other estimation techniques. These results have important policy implications and provide evidence for the improvement of sustainable urbanization in terms of access to basic services or reduction of vulnerability to climate change.