Conducting and Evaluating Multilevel Studies: Recommendations, Resources, and a Checklist

González-Romá, Vicente; Hernández, Ana

doi:10.1177/10944281211060712

Cited by 24 publications

(13 citation statements)

References 127 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, Model 5 added the country-level variables to examine the potential influence of a country's differences in objective economic inequality, human development, and aggregated values of PEI measures and attitudes toward inequality. Adding the country-level variables allows us to separate different sources of variance (within- and between-countries), which provides more information about the individual and contextual drivers of the variable under study (González-Romá & Hernández, 2022). The variables at the within-country level were country-mean centered and grand-mean centered at the between-country level.…”

Section: Methodsmentioning

confidence: 99%

Perceived Economic Inequality Measures and Their Association With Objective Inequality and Redistributive Preferences

et al. 2022

View full text Add to dashboard Cite

Abstract. Perceptions of economic inequality (PEI) play a central role in people’s responses to inequality. We aim to examine the consistency between different PEI measures (income gaps, diagrammatic figures, experienced downward and upward disparities), their relationship with objective inequality, and their association with redistributive preferences. Using data from the International Social Survey Programme 2019 ( N = 34,387, 22 countries), we performed multilevel regression analyses and found that PEI indicators were weakly and positively correlated, suggesting that they represent different dimensions of the same construct. Furthermore, objective inequality was not related to PEI measures. Finally, all PEI measures were positively associated with support for redistribution, except for experienced upward inequality. We discuss the multidimensional nature of PEI and its implications on redistributive preferences.

show abstract

Section: Methodsmentioning

confidence: 99%

Perceived Economic Inequality Measures and Their Association With Objective Inequality and Redistributive Preferences

et al. 2022

View full text Add to dashboard Cite

show abstract

“…All predictors were grand mean centered (cf. González-Romá & Hernández, 2022). The outcome variables were severity of workplace bullying from supervisors and coworkers, as collected in the survey.…”

Section: Discussionmentioning

confidence: 99%

Workplace bullying as an organizational problem: Spotlight on people management practices.

Tuckey¹,

Li²,

Neall³

et al. 2022

Journal of Occupational Health Psychology

View full text Add to dashboard Cite

Though workplace bullying is conceptualized as an organizational problem, there remains a gap in understanding the contexts in which bullying manifests-knowledge vital for addressing bullying in practice. In three studies, we leverage the rich content contained within workplace bullying complaint records to explore this issue then, based on our discoveries, investigate people management practices linked to bullying. First, through content analysis of 342 official complaints lodged with a state health and safety regulator (over 5,500 pages), we discovered that the risk of bullying primarily arises from ineffective people management in 11 different contexts (e.g., managing underperformance, coordinating working hours, and entitlements). Next, we developed a behaviorally anchored rating scale to measure people management practices within a refined set of nine risk contexts. Effective and ineffective behavioral indicators were identified through content analysis of the complaints data and data from 44 critical incident interviews with subject matter experts; indicators were then sorted and rated by two independent samples to form a risk audit tool. Finally, data from a multilevel multisource study of 145 clinical healthcare staff nested in 25 hospital wards showed that the effectiveness of people management practices predicts concurrent exposure to workplace bullying at individual level beyond established organizational antecedents, and at the team level beyond leading indicator psychosocial safety climate. Overall, our findings highlight where the greatest risk of bullying lies within organizational systems and identifies effective ways of managing people within those contexts to reduce the risk, opening new avenues for bullying intervention research and practice.

show abstract

“…MSEM uses structural equation modeling to partition observed variables into latent components at different levels of the design and subsequently tests mediation using these latent components [35,36]. Analogous to the relationship between linear regression and single-level structural equation modeling [41], MSEM represents a large-sample approach to multilevel mediation analysis that engenders greater modeling flexibility and produces more accurate effect estimates relative to MVM at the cost of higher standard errors and lower statistical power [35,[42][43][44].…”

Section: Mediation Analysis In Multilevel Studiesmentioning

confidence: 99%

Required sample size to detect mediation in 3-level implementation studies

et al. 2022

View full text Add to dashboard Cite

Background Statistical tests of mediation are important for advancing implementation science; however, little research has examined the sample sizes needed to detect mediation in 3-level designs (e.g., organization, provider, patient) that are common in implementation research. Using a generalizable Monte Carlo simulation method, this paper examines the sample sizes required to detect mediation in 3-level designs under a range of conditions plausible for implementation studies. Method Statistical power was estimated for 17,496 3-level mediation designs in which the independent variable (X) resided at the highest cluster level (e.g., organization), the mediator (M) resided at the intermediate nested level (e.g., provider), and the outcome (Y) resided at the lowest nested level (e.g., patient). Designs varied by sample size per level, intraclass correlation coefficients of M and Y, effect sizes of the two paths constituting the indirect (mediation) effect (i.e., X→M and M→Y), and size of the direct effect. Power estimates were generated for all designs using two statistical models—conventional linear multilevel modeling of manifest variables (MVM) and multilevel structural equation modeling (MSEM)—for both 1- and 2-sided hypothesis tests. Results For 2-sided tests, statistical power to detect mediation was sufficient (≥0.8) in only 463 designs (2.6%) estimated using MVM and 228 designs (1.3%) estimated using MSEM; the minimum number of highest-level units needed to achieve adequate power was 40; the minimum total sample size was 900 observations. For 1-sided tests, 808 designs (4.6%) estimated using MVM and 369 designs (2.1%) estimated using MSEM had adequate power; the minimum number of highest-level units was 20; the minimum total sample was 600. At least one large effect size for either the X→M or M→Y path was necessary to achieve adequate power across all conditions. Conclusions While our analysis has important limitations, results suggest many of the 3-level mediation designs that can realistically be conducted in implementation research lack statistical power to detect mediation of highest-level independent variables unless effect sizes are large and 40 or more highest-level units are enrolled. We suggest strategies to increase statistical power for multilevel mediation designs and innovations to improve the feasibility of mediation tests in implementation research.

show abstract

Conducting and Evaluating Multilevel Studies: Recommendations, Resources, and a Checklist

Cited by 24 publications

References 127 publications

Perceived Economic Inequality Measures and Their Association With Objective Inequality and Redistributive Preferences

Perceived Economic Inequality Measures and Their Association With Objective Inequality and Redistributive Preferences

Workplace bullying as an organizational problem: Spotlight on people management practices.

Required sample size to detect mediation in 3-level implementation studies

Contact Info

Product

Resources

About