2021
DOI: 10.1186/s12874-021-01321-x
|View full text |Cite
|
Sign up to set email alerts
|

Risk prediction in multicentre studies when there is confounding by cluster or informative cluster size

Abstract: Background Clustered data arise in research when patients are clustered within larger units. Generalised Estimating Equations (GEE) and Generalised Linear Models (GLMM) can be used to provide marginal and cluster-specific inference and predictions, respectively. Methods Confounding by Cluster (CBC) and Informative cluster size (ICS) are two complications that may arise when modelling clustered data. CBC can arise when the distribution of a predicto… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(4 citation statements)
references
References 29 publications
0
4
0
Order By: Relevance
“…To minimize selection bias, the patient's clinical details were collected, and PSM with a sensitivity analysis was performed. Moreover, considering that a patient may have multiple correlated implants, we adopted GLMM (de Melo et al., 2022; Pavlou et al., 2021) with random effects to assure the independence of the observations assumption.…”
Section: Discussionmentioning
confidence: 99%
“…To minimize selection bias, the patient's clinical details were collected, and PSM with a sensitivity analysis was performed. Moreover, considering that a patient may have multiple correlated implants, we adopted GLMM (de Melo et al., 2022; Pavlou et al., 2021) with random effects to assure the independence of the observations assumption.…”
Section: Discussionmentioning
confidence: 99%
“…[ 1 - 4 ]. Examining the correlation coefficient between the outcome and cluster size is a common approach to detect ICS [ 5 - 7 ] as well as testing for the effect of cluster size in a model that regresses the outcome against cluster size and other predictors [ 5 , 6 ]. To handle ICS, Seaman et al summarized a number of methods based on GLMM and GEE [ 8 ].…”
Section: Introductionmentioning
confidence: 99%
“…That is, the analysis might be affected by unmeasured hospital‐level confounding, which also causes ICS. Any of these three issues will lead to invalid statistical inference 7‐9 . Our goal is to develop a statistical method that can simultaneously address all three challenges.…”
Section: Introductionmentioning
confidence: 99%
“…Any of these three issues will lead to invalid statistical inference. [7][8][9] Our goal is to develop a statistical method that can simultaneously address all three challenges.…”
Section: Introductionmentioning
confidence: 99%