A practical guide to multilevel modeling

Peugh, James

doi:10.1016/j.jsp.2009.09.002

Cited by 1,083 publications

(839 citation statements)

References 17 publications

Supporting

Mentioning

789

Contrasting

Unclassified

Order By: Relevance

“…In the first analysis, the intra-class correlation (ICC) of country was examined. The ICC was .06, indicating the proportion of total variance that occurred systematically between countries was trivial and multilevel analysis with country as Level-2 units was not necessary (Lee, 2000;Peugh, 2010). Second, the standard errors of the regression models conducted with and without multilevel analyses were compared.…”

Section: Data Analysesmentioning

confidence: 99%

Do girls and boys perceive themselves as equally engaged in school? The results of an international study from 12 countries

Lam

Jimerson

Kikas

et al. 2012

Journal of School Psychology

244

173

View full text Add to dashboard Cite

This study examined gender differences in student engagement and academic performance in school. Participants included 3420 students (7th, 8th, and 9th graders) from Austria, Canada, China, Cyprus, Estonia, Greece, Malta, Portugal, Romania, South Korea, the United Kingdom, and the United States. The results indicated that, compared to boys, girls reported higher levels of engagement in school and were rated higher by their teachers in academic performance. Student engagement accounted for gender differences in academic performance, but gender did not moderate the associations among student engagement, academic performance, or contextual supports. Analysis of multiple-group structural equation modeling revealed that perceptions of teacher support and parent support, but not peer support, were related indirectly to academic performance through student engagement. This partial mediation model was invariant across gender. The findings from this study enhance the understanding about the contextual and personal factors associated with girls' and boys' academic performance around the world.peer-reviewe

show abstract

Section: Data Analysesmentioning

confidence: 99%

Do girls and boys perceive themselves as equally engaged in school? The results of an international study from 12 countries

Lam

Jimerson

Kikas

et al. 2012

Journal of School Psychology

244

173

View full text Add to dashboard Cite

show abstract

“…Furthermore, the development of trait and state anxiety was plotted over the course of chemotherapy treatment. Repeated measurements of anxiety and symptom severity at different time points resulted in a nested data set, calling for an analysis approach that accounts for this higher level clustering of individuals' ratings by time to avoid type I errors and biased parameter estimations (Peugh, 2010;Shek and Ma, 2011). Therefore, longitudinal mixed model analyses were used to answer our three research questions as stated above.…”

Section: Analysesmentioning

confidence: 99%

Trajectories and predictors of state and trait anxiety in patients receiving chemotherapy for breast and colorectal cancer: Results from a longitudinal study

Schneider

Kotronoulas

Papadopoulou

et al. 2016

European Journal of Oncology Nursing

View full text Add to dashboard Cite

“…The best-known and most frequently used method for parameter estimation is the maximum likelihood function. Furthermore, the likelihood function can be used for the calculation of the deviance, which is used for comparison of nested models (Peugh, 2010). In addition, nested or non-nested models can be compared using the Akaike information criterion ( AIC ) and the Bayesian information criterion ( BIC ) (Kwok et al, 2008).…”

Section: Methodsmentioning

confidence: 99%

“…There are no straightforward effect sizes in MLA, but generally accepted indices like the coefficient of determination Pseudo R 2 can be computed (Raudenbush & Bryk, 2002). Pseudo R 2 gives the variance explanation by adding one or more predictors compared to a more restrictive model (Peugh, 2010). …”

Section: Methodsmentioning

confidence: 99%

“…The assumptions of the MLA are that the drop-out has to be missing at random (MAR) (Kwok et al, 2008), the deviations of the individual means around the grand-mean ( μ 0j ) have to be normally distributed and the individual error ( r ij ) has to be independent of the random effects between individuals ( μ 0j ) (Peugh, 2010), that were checked before the analysis.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multidisciplinary treatment for traumatized refugees in a naturalistic setting: symptom courses and predictors

Stammel

Knaevelsrud

Schock³

et al. 2017

European Journal of Psychotraumatology

View full text Add to dashboard Cite

Background: Multidisciplinary treatment approaches are commonly used in specialized psychosocial centres for the treatment of traumatized refugees, but empirical evidence for their efficacy is inconsistent. Objective: In order to obtain more evidence on the development of mental health and well-being of traumatized refugees who receive multidisciplinary treatment, symptom courses of posttraumatic stress disorder (PTSD), anxiety, depression and somatoform symptoms as well as in the subjective quality of life were investigated in the course of a multidisciplinary treatment. In addition, it was analysed if sociodemographic variables were predictors for possible changes in symptomatology and quality of life. Method: N = 76 patients of the outpatient clinic of a psychosocial centre for traumatized refugees receiving regular multidisciplinary treatment were surveyed using standardized questionnaires at three measurement points (at the beginning of treatment, and after an average of 7 and 14 months of treatment) in a single-group design. Results: Multilevel analysis showed significant improvements of symptoms of PTSD (p < .001), depression (p < .001), anxiety (p < .001), and somatoform symptoms (p = .002) as well as of the subjective quality of life (p < .001) over time. Among the tested predictors (gender, age, country of origin), age was a significant predictor for the course of somatoform symptoms (p < .05). Younger patients showed greater improvements in symptomatology over time than older ones. Conclusions: The results suggest that the received multidisciplinary treatment had a positive effect on trauma-related symptoms as well as on quality of life of traumatized refugees. There was no indication that sociodemographic characteristics predicted the symptom courses of the patients, except for somatoform symptoms. Younger patients benefitted more from multidisciplinary treatment than older ones.

show abstract

A practical guide to multilevel modeling

Cited by 1,083 publications

References 17 publications

Do girls and boys perceive themselves as equally engaged in school? The results of an international study from 12 countries

Do girls and boys perceive themselves as equally engaged in school? The results of an international study from 12 countries

Trajectories and predictors of state and trait anxiety in patients receiving chemotherapy for breast and colorectal cancer: Results from a longitudinal study

Multidisciplinary treatment for traumatized refugees in a naturalistic setting: symptom courses and predictors

Contact Info

Product

Resources

About