Search

Multiple imputation is a recommended technique to deal with missing data. We study the problem where the investigator has already created imputations before the arrival of the next wave of data. The newly arriving data contain missing values that need to be imputed. The standard method (RE-IMPUTE) is to combine the new and old data before imputation, and re-impute all missing values in the combined data. We study the properties of two methods that impute the missing data in the new part only, thus preserving the historic imputations. Method NEST multiply imputes the new data conditional on each filled-in old data m 2 > 1 times. Method APPEND is the special case of NEST with m 2 = 1 , thus appending each filled-in data by single imputation. We found that NEST and APPEND have the same validity as RE-IMPUTE for monotone missing data-patterns. NEST and APPEND also work well when relations within waves are stronger than between waves and for moderate percentages of missing data. We do not recommend the use of NEST or APPEND when relations within time points are weak and when associations between time points are strong.

Background: Respiratory syncytial virus (RSV) infection is an important cause of infant mortality. Here, we estimated the potential impact of maternal vaccination against RSV on life-threatening RSV infection in infants., Methods: We developed a mathematical model for maternal vaccine-induced antibody dynamics and used characteristics of a maternal RSV vaccine currently in phase 3 of clinical development. The model was applied to data from two cohorts of children younger than 12 months with RSV-related paediatric intensive care unit (PICU) admission in the United Kingdom (n = 370) and the Netherlands (n = 167), and a cohort of 211 children younger than 12 months with RSV-related in-hospital death from 20 countries worldwide., Results: Our model predicted that, depending on vaccine efficiency, maternal vaccination at 30 weeks' gestational age could have prevented 62-75% of RSV-related PICU admissions in the United Kingdom and 76-87% in the Netherlands. For the global mortality cohort, the model predicted that maternal vaccination could have prevented 29-48% of RSV-related in-hospital deaths. Preterm children and children with comorbidities were predicted to benefit less than (healthy) term children., Conclusions: Maternal vaccination against RSV may substantially decrease life-threatening RSV infections in infants., (Copyright © 2018 The Author(s). Published by Elsevier Ltd.. All rights reserved.)