Statistical Inference in Redundancy Analysis: A Direct Covariance Structure Modeling Approach.

Redundancy analysis (RA) is a multivariate method that maximizes the mean variance of a set of criterion variables explained by a small number of redundancy variates (i.e., linear combinations of a set of predictor variables). However, two challenges exist in RA. First, inferential information for the RA estimates might not be readily available. Second, the existing methods addressing the dimensionality problem in RA are limited for various reasons. To aid the applications of RA, we propose a direct covariance structure modeling approach to RA. The proposed approach (1) provides inferential information for the RA estimates, and (2) allows the researcher to use a simple yet practical criterion to address the dimensionality problem in RA. We illustrate our approach with an artificial example, validate some standard error estimates by simulations, and demonstrate our new criterion in a real example. Finally, we conclude with future research topics.

Agreement Between Automated and Manual MRI Volumetry in Alzheimer's Disease: A Systematic Review and Meta-Analysis.

BACKGROUND: Automated magnetic resonance imaging (MRI) volumetry is a promising tool to evaluate regional brain volumes in dementia and especially Alzheimer's disease (AD). PURPOSE: To compare automated methods and the gold standard manual segmentation in measuring regional brain volumes on MRI across healthy controls, patients with mild cognitive impairment, and patients with dementia due to AD. STUDY TYPE: Systematic review and meta-analysis. DATA SOURCES: MEDLINE, Embase, and PsycINFO were searched through October 2021. FIELD STRENGTH: 1.0 T, 1.5 T, or 3.0 T. ASSESSMENT: Two review authors independently identified studies for inclusion and extracted data. Methodological quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). STATISTICAL TESTS: Standardized mean differences (SMD; Hedges' g) were pooled using random-effects meta-analysis with robust variance estimation. Subgroup analyses were undertaken to explore potential sources of heterogeneity. Sensitivity analyses were conducted to examine the impact of the within-study correlation between effect estimates on the meta-analysis results. RESULTS: Seventeen studies provided sufficient data to evaluate the hippocampus, lateral ventricles, and parahippocampal gyrus. The pooled SMD for the hippocampus, lateral ventricles, and parahippocampal gyrus were 0.22 (95% CI -0.50 to 0.93), 0.12 (95% CI -0.13 to 0.37), and -0.48 (95% CI -1.37 to 0.41), respectively. For the hippocampal data, subgroup analyses suggested that the pooled SMD was invariant across clinical diagnosis and field strength. Subgroup analyses could not be conducted on the lateral ventricles data and the parahippocampal gyrus data due to insufficient data. The results were robust to the selected within-study correlation value. DATA CONCLUSION: While automated methods are generally comparable to manual segmentation for measuring hippocampal, lateral ventricle, and parahippocampal gyrus volumes, wide 95% CIs and large heterogeneity suggest that there is substantial uncontrolled variance. Thus, automated methods may be used to measure these regions in patients with AD but should be used with caution. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 3.

Synthesizing Indirect Effects in Mediation Models With Meta-Analytic Methods.

AIMS: A mediator is a variable that explains the underlying mechanism between an independent variable and a dependent variable. The indirect effect indicates the effect from the predictor to the outcome variable via the mediator. In contrast, the direct effect represents the predictor's effort on the outcome variable after controlling for the mediator. METHODS: A single study rarely provides enough evidence to answer research questions in a particular domain. Replications are generally recommended as the gold standard to conduct scientific research. When a sufficient number of studies have been conducted addressing similar research questions, a meta-analysis can be used to synthesize those studies' findings. RESULTS: The main objective of this paper is to introduce two frameworks to integrating studies using mediation analysis. The first framework involves calculating standardized indirect effects and direct effects and conducting a multivariate meta-analysis on those effect sizes. The second one uses meta-analytic structural equation modeling to synthesize correlation matrices and fit mediation models on the average correlation matrix. We illustrate these procedures on a real dataset using the R statistical platform. CONCLUSION: This paper closes with some further directions for future studies.

A Primer on Meta-Analytic Structural Equation Modeling: the Case of Depression.

In this paper, we show how the methods of systematic reviewing and meta-analysis can be used in conjunction with structural equation modeling to summarize the results of studies in a way that will facilitate the theory development and testing needed to advance prevention science. We begin with a high-level overview of the considerations that researchers need to address when using meta-analytic structural equation modeling (MASEM) and then discuss a research project that brings together theoretically important cognitive constructs related to depression to (a) show how these constructs are related, (b) test the direct and indirect effects of dysfunctional attitudes on depression, and (c) test the effects of study-level moderating variables. Our results suggest that the indirect effect of dysfunctional attitudes (via negative automatic thinking) on depression is two and a half times larger than the direct effect of dysfunctional attitudes on depression. Of the three study-level moderators tested, only sample recruitment method (clinical vs general vs mixed) yielded different patterns of results. The primary difference observed was that the dysfunctional attitudes → automatic thoughts path was less strong for clinical samples than it was for general and mixed samples. These results illustrate how MASEM can be used to compare theoretically derived models and predictions resulting in a richer understanding of both the empirical results and the theories underlying them.

Evaluating FIML and multiple imputation in joint ordinal-continuous measurements models with missing data.

Missing data is a common occurrence in confirmatory factor analysis (CFA). Much work had evaluated the performance of different techniques when all observed variables were either continuous or ordinal. However, few have investigated these techniques when observed variables are a mix of continuous and ordinal variables. This study investigated the performance of four approaches to handling missing data in these models: a joint ordinal-continuous full information maximum likelihood (FIML) approach and three multiple imputation approaches (fully conditional specification, fully conditional specification with latent variable formulation, and expectation-maximization with bootstrapping) combined with the weighted least squares with mean and variance adjustment (WLSMV) estimator. In a Monte-Carlo simulation, the FIML approach produced unbiased estimations of factor loadings and standard errors in almost all conditions. Fully conditional specification combined with WLSMV was second best, producing accurate estimates when the sample size was large. However, FIML encountered slight non-convergence issues when certain ordinal categories have extremely low frequencies, which is typical of skewed data. If the sample is large, fully conditional specification combined with weighted least squares is recommended when the FIML approach is not feasible (e.g., non-convergence, impractical computation durations, and variables that predict missingness are not of interest to the analysis).

Resting-state functional connectivity in the idiopathic generalized epilepsies: A systematic review and meta-analysis of EEG and MEG studies.

For idiopathic generalized epilepsies (IGE), brain network analysis is emerging as a biomarker for potential use in clinical care. To determine whether people with IGE show alterations in resting-state brain connectivity compared to healthy controls, and to quantify these differences, we conducted a systematic review and meta-analysis of EEG and magnetoencephalography (MEG) functional connectivity and network studies. The review was conducted according to PRISMA guidelines. Twenty-two studies were eligible for inclusion. Outcomes from individual studies supported hypotheses for interictal, resting-state brain connectivity alterations in IGE patients compared to healthy controls. In contrast, meta-analysis from six studies of common network metrics clustering coefficient, path length, mean degree and nodal strength showed no significant differences between IGE and control groups (effect sizes ranged from -0.151 -1.78). The null findings of the meta-analysis and the heterogeneity of the included studies highlights the importance of developing standardized, validated methodologies for future research. Network neuroscience has significant potential as both a diagnostic and prognostic biomarker in epilepsy, though individual variability in network dynamics needs to be better understood and accounted for.

A Guide to Conducting a Meta-Analysis with Non-Independent Effect Sizes.

Conventional meta-analytic procedures assume that effect sizes are independent. When effect sizes are not independent, conclusions based on these conventional procedures can be misleading or even wrong. Traditional approaches, such as averaging the effect sizes and selecting one effect size per study, are usually used to avoid the dependence of the effect sizes. These ad-hoc approaches, however, may lead to missed opportunities to utilize all available data to address the relevant research questions. Both multivariate meta-analysis and three-level meta-analysis have been proposed to handle non-independent effect sizes. This paper gives a brief introduction to these new techniques for applied researchers. The first objective is to highlight the benefits of using these methods to address non-independent effect sizes. The second objective is to illustrate how to apply these techniques with real data in R and Mplus. Researchers may modify the sample R and Mplus code to fit their data.

Four Covariance Structure Models for Canonical Correlation Analysis: A COSAN Modeling Approach.

The mathematical connection between canonical correlation analysis (CCA) and covariance structure analysis was first discussed through the Multiple Indicators and Multiple Causes (MIMIC) approach. However, the MIMIC approach has several technical and practical challenges. To address these challenges, a comprehensive COSAN modeling approach is proposed. Specifically, we define four COSAN-CCA models to correspond with four possible combinations of the data to be analyzed and the unique parameters to be estimated. In terms of the data, one can analyze either the unstandardized or standardized variables. In terms of the unique parameters, one can estimate either the weights or loadings. Besides the unique parameters of each COSAN-CCA model, all four COSAN-CCA models also estimate the canonical correlations as their common parameters. Taken together, the four COSAN-CCA models provide the correct point estimates and standard error estimates for all commonly used CCA parameters. Two numeric examples are used to compare the standard error estimates obtained from the MIMIC approach and the COSAN modeling approach. Moreover, the standard error estimates from the COSAN modeling approach are validated by a simulation study and the asymptotic theory. Finally, software implementation and future extensions are discussed.

Accounting for Missing Correlation Coefficients in Fixed-Effects MASEM.

Meta-analytic structural equation modeling (MASEM) is increasingly applied to advance theories by synthesizing existing findings. MASEM essentially consists of two stages. In Stage 1, a pooled correlation matrix is estimated based on the reported correlation coefficients in the individual studies. In Stage 2, a structural model (such as a path model) is fitted to explain the pooled correlations. Frequently, the individual studies do not provide all the correlation coefficients between the research variables. In this study, we modify the currently optimal MASEM-method to deal with missing correlation coefficients, and compare its performance with existing methods. This study is the first to evaluate the performance of fixed-effects MASEM methods under different levels of missing correlation coefficients. We found that the often used univariate methods performed very poorly, while the multivariate methods performed well overall.

Testing moderator hypotheses in meta-analytic structural equation modeling using subgroup analysis.

Meta-analytic structural equation modeling (MASEM) is a statistical technique to pool correlation matrices and test structural equation models on the pooled correlation matrix. In Stage 1 of MASEM, correlation matrices from independent studies are combined to obtain a pooled correlation matrix, using fixed- or random-effects analysis. In Stage 2, a structural model is fitted to the pooled correlation matrix. Researchers applying MASEM may have hypotheses about how certain model parameters will differ across subgroups of studies. These moderator hypotheses are often addressed using suboptimal methods. The aim of the current article is to provide guidance and examples on how to test hypotheses about group differences in specific model parameters in MASEM. We illustrate the procedure using both fixed- and random-effects subgroup analysis with two real datasets. In addition, we present a small simulation study to evaluate the effect of the number of studies per subgroup on convergence problems. All data and the R-scripts for the examples are provided online.

A Guide to Conducting a Meta-Analysis.

Meta-analysis is widely accepted as the preferred method to synthesize research findings in various disciplines. This paper provides an introduction to when and how to conduct a meta-analysis. Several practical questions, such as advantages of meta-analysis over conventional narrative review and the number of studies required for a meta-analysis, are addressed. Common meta-analytic models are then introduced. An artificial dataset is used to illustrate how a meta-analysis is conducted in several software packages. The paper concludes with some common pitfalls of meta-analysis and their solutions. The primary goal of this paper is to provide a summary background to readers who would like to conduct their first meta-analytic study.

Explaining Differences in Subjective Well-Being Across 33 Nations Using Multilevel Models: Universal Personality, Cultural Relativity, and National Income.

This multinational study simultaneously tested three prominent hypotheses--universal disposition, cultural relativity, and livability--that explained differences in subjective well-being across nations. We performed multilevel structural equation modeling to examine the hypothesized relationships at both individual and cultural levels in 33 nations. Participants were 6,753 university students (2,215 men; 4,403 women; 135 did not specify), and the average age of the entire sample was 20.97 years (SD = 2.39). Both individual- and cultural-level analyses supported the universal disposition and cultural relativity hypotheses by revealing significant associations of subjective well-being with Extraversion, Neuroticism, and independent self-construal. In addition, interdependent self-construal was positively related to life satisfaction at the individual level only, whereas aggregated negative affect was positively linked with aggregate levels of Extraversion and interdependent self-construal at the cultural level only. Consistent with the livability hypothesis, gross national income (GNI) was related to aggregate levels of negative affect and life satisfaction. There was also a quadratic relationship between GNI and aggregated positive affect. Our findings reveal that universal disposition, cultural self-construal, and national income can elucidate differences in subjective well-being, but the multilevel analyses advance the literature by yielding new findings that cannot be identified in studies using individual-level analyses alone.

Fixed- and random-effects meta-analytic structural equation modeling: examples and analyses in R.

Meta-analytic structural equation modeling (MASEM) combines the ideas of meta-analysis and structural equation modeling for the purpose of synthesizing correlation or covariance matrices and fitting structural equation models on the pooled correlation or covariance matrix. Cheung and Chan (Psychological Methods 10:40-64, 2005b, Structural Equation Modeling 16:28-53, 2009) proposed a two-stage structural equation modeling (TSSEM) approach to conducting MASEM that was based on a fixed-effects model by assuming that all studies have the same population correlation or covariance matrices. The main objective of this article is to extend the TSSEM approach to a random-effects model by the inclusion of study-specific random effects. Another objective is to demonstrate the procedures with two examples using the metaSEM package implemented in the R statistical environment. Issues related to and future directions for MASEM are discussed.

The multifaceted role of emotion regulation in suicidality: Systematic reviews and meta-analytic evidence.

Despite the number of empirical contributions on the topic, scientists have offered contrasting perspectives on the role of adaptive versus maladaptive emotion regulation (ER) strategies in suicidality. Moreover, suicidal attempts and suicidal ideation are likely to be differentially related to single ER strategies. To provide more systematic knowledge that can be used to draw sound conclusions and formulate clinical indications, we carried out a systematic review and meta-analysis that we reported in compliance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards (Moher et al., 2009). From an initial pool of 16,530 articles retrieved from scientific databases (APA PsycInfo, APA PsycArticles, Medline, Scopus, Web of Science, and PubMed) and a search for gray literature, 226 articles were selected to perform 15 meta-analyses. In addition, metaregressions were carried out to test a series of moderators, including the type of suicidality investigated. Among adaptive strategies, results evidenced the role of reappraisal, mindfulness, and several aspects of problem solving. In contrast to our hypothesis, reflective attitude was positively associated with suicidality, calling into question the traditional distinction between adaptive and maladaptive strategies. Regarding maladaptive ER strategies, suppression, avoidance, rumination, brooding, negative problem orientation, and both impulsive and avoidant problem solving proved to be significantly associated with suicidality. Finally, several moderation effects involving age, gender composition, and type of suicidality were observed, supporting the importance of adopting a complex perspective when approaching the topic. Despite the interesting preliminary results, additional research is needed to provide a greater understanding of the interplay between the different ER strategies and suicidality and to develop effective protocols of intervention. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

A model-based approach to multivariate principal component regression: Selecting principal components and estimating standard errors for unstandardized regression coefficients.

Principal component regression (PCR) is a popular technique in data analysis and machine learning. However, the technique has two limitations. First, the principal components (PCs) with the largest variances may not be relevant to the outcome variables. Second, the lack of standard error estimates for the unstandardized regression coefficients makes it hard to interpret the results. To address these two limitations, we propose a model-based approach that includes two mean and covariance structure models defined for multivariate PCR. By estimating the defined models, we can obtain inferential information that will allow us to test the explanatory power of individual PCs and compute the standard error estimates for the unstandardized regression coefficients. A real example is used to illustrate our approach, and simulation studies under normality and nonnormality conditions are presented to validate the standard error estimates for the unstandardized regression coefficients. Finally, future research topics are discussed.

A primer on synthesizing individual participant data obtained from complex sampling surveys: A two-stage IPD meta-analysis approach.

The increasing availability of individual participant data (IPD) in the social sciences offers new possibilities to synthesize research evidence across primary studies. Two-stage IPD meta-analysis represents a framework that can utilize these possibilities. While most of the methodological research on two-stage IPD meta-analysis focused on its performance compared with other approaches, dealing with the complexities of the primary and meta-analytic data has received little attention, particularly when IPD are drawn from complex sampling surveys. Complex sampling surveys often feature clustering, stratification, and multistage sampling to obtain nationally or internationally representative data from a target population. Furthermore, IPD from these studies is likely to provide more than one effect size. To address these complexities, we propose a two-stage meta-analytic approach that generates model-based effect sizes in Stage 1 and synthesizes them in Stage 2. We present a sequence of steps, illustrate their implementation, and discuss the methodological decisions and options within. Given its flexibility to deal with the complex nature of the primary and meta-analytic data and its ability to combine multiple IPD sets or IPD with aggregated data, the proposed two-stage approach opens up new analytic possibilities for synthesizing knowledge from complex sampling surveys. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Meta-analytic Gaussian Network Aggregation.

A growing number of publications focus on estimating Gaussian graphical models (GGM, networks of partial correlation coefficients). At the same time, generalizibility and replicability of these highly parameterized models are debated, and sample sizes typically found in datasets may not be sufficient for estimating the underlying network structure. In addition, while recent work emerged that aims to compare networks based on different samples, these studies do not take potential cross-study heterogeneity into account. To this end, this paper introduces methods for estimating GGMs by aggregating over multiple datasets. We first introduce a general maximum likelihood estimation modeling framework in which all discussed models are embedded. This modeling framework is subsequently used to introduce meta-analytic Gaussian network aggregation (MAGNA). We discuss two variants: fixed-effects MAGNA, in which heterogeneity across studies is not taken into account, and random-effects MAGNA, which models sample correlations and takes heterogeneity into account. We assess the performance of MAGNA in large-scale simulation studies. Finally, we exemplify the method using four datasets of post-traumatic stress disorder (PTSD) symptoms, and summarize findings from a larger meta-analysis of PTSD symptom.

Perceived behavioral control moderating effects in the theory of planned behavior: A meta-analysis.

OBJECTIVE: According to the theory of planned behavior, individuals are more likely to act on their behavioral intentions, and report intentions aligned with their attitudes and subjective norm, when their perceived behavioral control (PBC) is high. We tested these predictions meta-analytically by estimating the moderating effect of PBC on the attitude-intention, subjective norm-intention, and the intention-behavior relations in studies applying the theory in the health behavior domain. METHOD: We conducted a preregistered secondary analysis of studies (k = 39, total N = 13,121) from two programs of research. Each study measured participants' attitude, subjective norms, PBC, and intentions in relation to health behaviors, and most (k = 36) measured health behavior at follow-up. Data were analyzed using meta-analytic structural equation modeling. Behavior type, scale score coverage, sample age, and publication states were included as moderators of model effects. RESULTS: PBC moderated the intention-behavior relation but not the attitude-intention and subjective norm-intention relations. All moderation effects exhibited significant heterogeneity. Analysis of moderators indicated that the PBC moderation effects on intention varied according to scale score coverage but not by the other moderator variables tested. CONCLUSIONS: Results support moderation of the intention-behavior relation by PBC in health behaviors. However, substantial unresolved heterogeneity in the effect across studies remained. Further, these effects may not generalize to other populations and moderator analyses were confined to broad categories. More research that tests these moderation effects in health behavior contexts and reports sufficient data necessary for conducting a meta-analysis is needed to enable moderator analyses with greater fidelity. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Is high homocysteine level a risk factor for cognitive decline in elderly? A systematic review, meta-analysis, and meta-regression.

OBJECTIVE: [corrected] High homocysteine (Hct) has been causatively linked to Alzheimer disease (AD) and vascular dementia (VaD) in old age, but research methodologies and outcome measures are heterogeneous. It remains unclear whether the findings can be generalized across studies. METHODS: Random-effects meta-analyses were conducted on studies examining the relationship between Hct level and risk of developing dementia/cognitive decline between comparison groups. Meta-regression identified patient- and trial-related factors, which may contribute to heterogeneity. RESULTS: Seventeen relevant studies (6,122 participants; 13 cross-sectional and fourprospective studies) were included. Compared with controls, Hct was significantly elevated in AD (pooled standardized mean difference [SMD]: 0.59; 95% confidence interval [CI]: 0.38-0.80; significant heterogeneity: τ = 0.105) and VaD (pooled SMD: 1.30; 95% CI: 0.75-1.84; significant heterogeneity: τ = 0.378). Meta-regression identified mean age as significant moderator for AD versus controls and mean age and mean folate levels as significant moderators for VaD versus controls. Hct was significantly higher in VaD relative to AD (pooled SMD: 0.48; 95% CI: 0.23-0.73; moderately significant heterogeneity: τ = 0.076); proportion of men and mean folate levels were significant moderators. High-Hct level was not associated with risk of developing dementia in prospective studies (pooled odds ratio: 1.34; 95% CI: 0.94-1.91, nonsignificant heterogeneity: τ = 0.048). CONCLUSION: Individuals with AD and VaD have higher Hct levels than controls; however, a causal relationship between high-Hct level and risk of developing dementia is not supported. More prospective studies and randomized controlled trials are required to test the therapeutic benefits of lowering Hct levels.

Network models of posttraumatic stress disorder: A meta-analysis.

Posttraumatic stress disorder (PTSD) researchers have increasingly used psychological network models to investigate PTSD symptom interactions, as well as to identify central driver symptoms. It is unclear, however, how generalizable such results are. We have developed a meta-analytic framework for aggregating network studies while taking between-study heterogeneity into account and applied this framework in the first-ever meta-analytic study of PTSD symptom networks. We analyzed the correlational structures of 52 different samples with a total sample size of n = 29,561 and estimated a single pooled network model underlying the data sets, investigated the scope of between-study heterogeneity, and assessed the performance of network models estimated from single studies. Our main findings are that: (a) We identified large between-study heterogeneity, indicating that it should be expected for networks of single studies to not perfectly align with one-another, and meta-analytic approaches are vital for the study of PTSD networks. (b) While several clear symptom-links, interpretable clusters, and significant differences between strength of edges and centrality of nodes can be identified in the network, no single or small set of nodes that clearly played a more central role than other nodes could be pinpointed, except for the symptom "amnesia" that was clearly the least central symptom. (c) Despite large between-study heterogeneity, we found that network models estimated from single samples can lead to similar network structures as the pooled network model. We discuss the implications of these findings for both the PTSD literature as well as methodological literature on network psychometrics. (PsycInfo Database Record (c) 2021 APA, all rights reserved).