2018
DOI: 10.1002/sim.7944
|View full text |Cite
|
Sign up to set email alerts
|

Computationally efficient methods for fitting mixed models to electronic health records data

Abstract: Motivated by two case studies using primary care records from the Clinical Practice Research Datalink, we describe statistical methods that facilitate the analysis of tall data, with very large numbers of observations. Our focus is on investigating the association between patient characteristics and an outcome of interest, while allowing for variation among general practices. We explore ways to fit mixed-effects models to tall data, including predictors of interest and confounding factors as covariates, and in… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2019
2019
2019
2019

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 20 publications
0
2
0
Order By: Relevance
“…There is an increasing interest in developing meta‐analysis for applications in more complex pooling studies, beyond the now established extensions described in Section 4 . Emerging areas include investigations that apply two‐stage designs for the analysis of large datasets, where either the complexity of the first‐stage regression or the computational demand prevent the definition of a one‐stage model, and the partition of the analysis in two steps provides a feasible and efficient approach . However, the limitations of traditional meta‐analytical methods, requiring the estimation of single independent parameters from each subset, poses important constraints in this setting.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…There is an increasing interest in developing meta‐analysis for applications in more complex pooling studies, beyond the now established extensions described in Section 4 . Emerging areas include investigations that apply two‐stage designs for the analysis of large datasets, where either the complexity of the first‐stage regression or the computational demand prevent the definition of a one‐stage model, and the partition of the analysis in two steps provides a feasible and efficient approach . However, the limitations of traditional meta‐analytical methods, requiring the estimation of single independent parameters from each subset, poses important constraints in this setting.…”
Section: Discussionmentioning
confidence: 99%
“…4,72 Emerging areas include investigations that apply two-stage designs for the analysis of large datasets, where either the complexity of the first-stage regression or the computational demand prevent the definition of a one-stage model, and the partition of the analysis in two steps provides a feasible and efficient approach. 3,50,73 However, the limitations of traditional meta-analytical methods, requiring the estimation of single independent parameters from each subset, poses important constraints in this setting. In contrast, the model in Equation (1) offers flexibility in the definition of the two-stage analysis, allowing for instance repeated measurements in time or subgroups, hierarchies, and spatial or temporal clustering, and complex multiparameter effect estimates.…”
Section: Discussionmentioning
confidence: 99%