scholarly journals Evaluation of approaches for accommodating interactions and non‐linear terms in multiple imputation of incomplete three‐level data

2021 ◽  
Author(s):  
Rushani Wijesuriya ◽  
Margarita Moreno‐Betancur ◽  
John B. Carlin ◽  
Anurika P. De Silva ◽  
Katherine J. Lee
Keyword(s):  
Multiple Imputation ◽  
Level Data ◽  
Non Linear

Comparing multiple imputation methods for systematically missing subject-level data

2015 ◽  
Vol 8 (2) ◽  
pp. 136-148 ◽  
Author(s):  
David Kline ◽  
Rebecca Andridge ◽  
Eloise Kaizar
Keyword(s):  
Multiple Imputation ◽  
Imputation Methods ◽  
Level Data

Multiple imputation was an efficient method for harmonizing the Mini-Mental State Examination with missing item-level data

2011 ◽  
Vol 64 (7) ◽  
pp. 787-793 ◽  
Author(s):  
Richard A. Burns ◽  
Peter Butterworth ◽  
Kim M. Kiely ◽  
Allison A.M. Bielak ◽  
Mary A. Luszcz ◽  
...  
Keyword(s):  
Multiple Imputation ◽  
Efficient Method ◽  
Mental State ◽  
Mini Mental State Examination ◽  
Level Data ◽  
Item Level ◽  
Missing Item ◽  
State Examination

scholarly journals Multiple imputation for analysis of incomplete data in distributed health data networks

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Changgee Chang ◽  
Yi Deng ◽  
Xiaoqian Jiang ◽  
Qi Long
Keyword(s):  
Missing Data ◽  
Multiple Imputation ◽  
Incomplete Data ◽  
Health Data ◽  
Data Repository ◽  
Data Networks ◽  
Patient Privacy ◽  
Multiple Sources ◽  
Current State ◽  
Level Data

Abstract Distributed health data networks (DHDNs) leverage data from multiple sources or sites such as electronic health records (EHRs) from multiple healthcare systems and have drawn increasing interests in recent years, as they do not require sharing of subject-level data and hence lower the hurdles for collaboration between institutions considerably. However, DHDNs face a number of challenges in data analysis, particularly in the presence of missing data. The current state-of-the-art methods for handling incomplete data require pooling data into a central repository before analysis, which is not feasible in DHDNs. In this paper, we address the missing data problem in distributed environments such as DHDNs that has not been investigated previously. We develop communication-efficient distributed multiple imputation methods for incomplete data that are horizontally partitioned. Since subject-level data are not shared or transferred outside of each site in the proposed methods, they enhance protection of patient privacy and have the potential to strengthen public trust in analysis of sensitive health data. We investigate, through extensive simulation studies, the performance of these methods. Our methods are applied to the analysis of an acute stroke dataset collected from multiple hospitals, mimicking a DHDN where health data are horizontally partitioned across hospitals and subject-level data cannot be shared or sent to a central data repository.

scholarly journals Large scale simulation of pressure induced phase-field fracture propagation using Utopia

2021 ◽  
Author(s):  
Patrick Zulian ◽  
Alena Kopaničáková ◽  
Maria Giuseppina Chiara Nestola ◽  
Andreas Fink ◽  
Nur Aiman Fadel ◽  
...  
Keyword(s):  
Phase Field ◽  
Large Scale ◽  
Parallel Implementation ◽  
Fracture Propagation ◽  
Trust Region ◽  
Fracture Networks ◽  
Parallel Solution ◽  
Level Data ◽  
Non Linear ◽  
High Level

AbstractNon-linear phase field models are increasingly used for the simulation of fracture propagation problems. The numerical simulation of fracture networks of realistic size requires the efficient parallel solution of large coupled non-linear systems. Although in principle efficient iterative multi-level methods for these types of problems are available, they are not widely used in practice due to the complexity of their parallel implementation. Here, we present Utopia, which is an open-source C++ library for parallel non-linear multilevel solution strategies. Utopia provides the advantages of high-level programming interfaces while at the same time a framework to access low-level data-structures without breaking code encapsulation. Complex numerical procedures can be expressed with few lines of code, and evaluated by different implementations, libraries, or computing hardware. In this paper, we investigate the parallel performance of our implementation of the recursive multilevel trust-region (RMTR) method based on the Utopia library. RMTR is a globally convergent multilevel solution strategy designed to solve non-convex constrained minimization problems. In particular, we solve pressure-induced phase-field fracture propagation in large and complex fracture networks. Solving such problems is deemed challenging even for a few fractures, however, here we are considering networks of realistic size with up to 1000 fractures.

scholarly journals Software Application Profile: SUMnlmr, an R package that facilitates flexible and reproducible non-linear Mendelian randomisation analyses

2021 ◽  
Author(s):  
Amy M Mason ◽  
Stephen Burgess
Keyword(s):  
Linear Model ◽  
Piecewise Linear ◽  
R Package ◽  
Mendelian Randomisation ◽  
Software Application ◽  
Individual Level ◽  
Fractional Polynomial ◽  
Level Data ◽  
Non Linear ◽  
The Individual

Motivation Mendelian randomisation methods that estimate non-linear exposure-outcome relationships typically require individual-level data. This package implements non-linear Mendelian randomisation methods using stratified summarised data, facilitating analyses where individual-level data cannot easily be shared, and additionally increasing reproducibility as summarised data can be reported. Dependence on summarised data means the methods are independent of the form of the individual-level data, increasing flexibility to different outcome types (such as continuous, binary, or time-to-event outcomes). Implementation SUMnlmr is available as an R package (version 3.1.0 or higher). General features The package implements the previously proposed fractional polynomial and piecewise linear methods on stratified summarised data that can either be estimated from individual-level data using the package or supplied by a collaborator. It constructs plots to visualise the estimated exposure-outcome relationship, and provides statistics to assess preference for a non-linear model over a linear model. Availability The package is freely available from GitHub [ https://github.com/amymariemason/SUMnlmr].

scholarly journals Evaluation of approaches for multiple imputation of three-level data

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Rushani Wijesuriya ◽  
Margarita Moreno-Betancur ◽  
John B. Carlin ◽  
Katherine J. Lee
Keyword(s):  
Multiple Imputation ◽  
Level Data
Sign in / Sign up

Export Citation Format

Share Document