Relative Importance of Predictors in Multilevel Modeling

Yan, Liu; Zumbo, Bruno D.; Wu, Amery D.

doi:10.22237/jmasm/1398916860

Cited by 35 publications

(30 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A hierarchical multiple regression analysis was used to determine the factors affecting the nurses' patient safety competency. Pratt indices were computed for the relative importance of factors affecting patient safety competence (Liu, Zumbo, & Wu, ; Ochieng & Zumbo, ).…”

Section: Methodsmentioning

confidence: 99%

Patient safety competency and the new nursing care delivery model

Jin

2019

J Nurs Manag

View full text Add to dashboard Cite

Aim To identify the factors affecting nurses' patient safety competency under the new nursing care delivery model. Background In Korea, a new model was introduced in 2013 to ensure that nursing personnel provided inpatients with care without relying on guardians. After the launch of this service, there continue to be nurse‐related patient safety incidents. Methods This is a descriptive study. Data from 132 general hospital nurses were collected during 15–24 February 2017 and analysed using hierarchical multiple regression. Results Participants' mean patient safety competency score was 3.82 (range 1–5). Clinical career (Pratt index = 47.3%), critical thinking disposition (30.4%), teamwork (24.1%) and critical thinking training experience (7.3%) were found to affect nurses' patient safety competency. Conclusion Under the new model, new nurses showed a low level of patient safety competency. Clinical career most influenced patient safety competency. Enhanced critical thinking and teamwork training are needed to improve patient safety competency among nurses. Implications for nursing management Nursing leaders must consider qualitative staffing mix involving appropriate placement of experienced nurses as well as quantitative staffing level to provide patients with high‐quality, safe care and to implement the new model successfully. Regular training on critical thinking and teamwork should be carried out.

show abstract

Section: Methodsmentioning

confidence: 99%

Patient safety competency and the new nursing care delivery model

Jin

2019

J Nurs Manag

View full text Add to dashboard Cite

show abstract

“…Numerous other approaches have been proposed as alternatives to measure relative importance (Budescu, 1993;Pratt, 1987;Thomas, Hughes, & Zumbo, 1998), although the extension of those methods to multilevel framework has been relatively scarce and has appeared in the literature only recently. For the current study, we used the Pratt index adapted for hierarchical linear modeling (HLM; Liu, Zumbo, & Wu, 2014) to evaluate the predictors' importance. In a randomintercept multilevel model, the index is simply calculated as…”

Section: Conditional Modelmentioning

confidence: 99%

Predictors of Language Gains Among School-Age Children With Language Impairment in the Public Schools

Justice

Jiang

Logan

et al. 2017

J Speech Lang Hear Res

View full text Add to dashboard Cite

show abstract

“…There are many variable importance methods which do not fall into the two categories described above. They include the relatively simple Pratt index which combines regression coefficients and correlations between predictors and the DV (Liu, Zumbo, & Wu, 2014;Pratt, 1987;Thomas, Hughes, & Zumbo, 1998;Zumbo, 2007) and several other mathematically challenging procedures which measure importance using effects averaged across all possible importance ordering sequences (Theil, 1987;Theil, & Chung, 1988). Among methods of measuring predictor importance, dominance analysis (DA) is probably one of the most respected these days which have been widely investigated and implemented (Azen, & Budescu, 2003;Azen, & Budescu, 2006;Azen, & Traxel, 2009;Budescu, 1993;Budescu, & Azen, 2004;Luo, & Azen, 2013).…”

Section: Evaluating Relative Importance Of Predictorsmentioning

confidence: 99%

Partial and Semi-Partial Correlations for Categorical Variables in Educational Research: Addressing Two Common Misconceptions

Yang¹,

Wong²,

Bradley³

et al. 2017

GLMJ

View full text Add to dashboard Cite

This article addresses two misconceptions that educational researchers have about partial and semi-partial correlations. To undo the two misconceptions, this article provides a detailed discussion of the two types of correlations under linear regression which includes multiple dummy indicator variables created for a categorical predictor. A numerical example is provided to demonstrate how the two correlations can be properly utilized to solve research questions in education: 1) Interpretation under the substantive problem and 2) assessment of relative importance of predictors in predicting the dependent variable (DV). The article concludes with a summary of findings and provides the SPSS code used so that interested readers may replicate the results.artial and semi-partial correlations (a.k.a., part correlations) have had a long history of being used questions in education can be analyzed under these two correlations. For example, it may be that ACT scores can be used to predict college GPA because those test scores provide much of the same information given by another excellent predictor, high school GPA. Then, the question might be asked, "Do ACT scores still predict college GPA if we look only at students with the same high school GPA?" Stated differently, the question is, "What would the relationship between ACT scores and college GPA have been if each student had the same high school GPA?" To answer this question, we need the partial correlation coefficient between college GPA and ACT scores that adjusts for high school GPA. Here, high school GPA has been held constant and thus removed as a source of variation from both college GPA and ACT scores. In another case, we may ask a similar, but different question, "Given that a

show abstract

Relative Importance of Predictors in Multilevel Modeling

Cited by 35 publications

References 23 publications

Patient safety competency and the new nursing care delivery model

Patient safety competency and the new nursing care delivery model

Predictors of Language Gains Among School-Age Children With Language Impairment in the Public Schools

Partial and Semi-Partial Correlations for Categorical Variables in Educational Research: Addressing Two Common Misconceptions

Contact Info

Product

Resources

About