2010
DOI: 10.1177/0003122409359166
|View full text |Cite
|
Sign up to set email alerts
|

Influential Cases in Multilevel Modeling: A Methodological Comment

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

3
109
1
1

Year Published

2014
2014
2021
2021

Publication Types

Select...
6
2
2

Relationship

1
9

Authors

Journals

citations
Cited by 188 publications
(115 citation statements)
references
References 6 publications
3
109
1
1
Order By: Relevance
“…One way of testing the robustness of analyses with a rather small number of cases is by testing for influential cases which could bias our results and may lead to false assumptions. We estimated Cooks Distance (CooksD) as well as dfBetas for our models (see van der Meer et al, 2010).…”
Section: Resultsmentioning
confidence: 99%
“…One way of testing the robustness of analyses with a rather small number of cases is by testing for influential cases which could bias our results and may lead to false assumptions. We estimated Cooks Distance (CooksD) as well as dfBetas for our models (see van der Meer et al, 2010).…”
Section: Resultsmentioning
confidence: 99%
“…Firstly, it has been shown that doctor-patient communication is affected by patient's SES in the sense that doctors convey less information and directions to patients from the lower social strata of a society, deploy a more directive consulting style, and give patients fewer positive socio-emotional responses (Willems et al, 2005). Secondly, aspects of doctor-patient relationships have been shown to be related to outcomes such as patient satisfaction, coping with disease, and recall and understanding of information received from the physician (Ong et al, 1995), as well as to self-reported and objective health measures (Griffin et al, 2004;Stewart, 1995a). However, there has been little research connecting the two issues of the SES-health gradient and SES differences in the doctor-patient relationship.…”
Section: Melinda Mills Is Nuffieldmentioning
confidence: 99%
“…In social science applications of mixed models the testing for influential data is especially important, since these models are frequently based on large numbers of observations at the individual level while the number of higher level groups is relatively small. For instance, Van der Meer, te Grotenhuis, and Pelzer (2010) were unable to find any country-level comparative studies involving more than 54 countries. With such a relatively low number of countries, a single country can easily be overly influential on the parameter estimates of one or more of the country-level variables.…”
mentioning
confidence: 99%