micemd (version 1.10.1)

IPDNa: A simulated Individual Patient Data (IPD) meta-analysis with missing values.

Description

This dataset is a simulated version of an IPD meta-analysis consisting of 28 studies focusing on risk factors in acute heart failure (GREAT, 2013). Each study includes a list of patient characteristics and potential risk factors. Each of them is incomplete, leading to sporadically missing values (Resche-Rigon, et al 2013). In addition, some variables have been collected on some studies only, leading to systematically missing values. More details on the original dataset are provided in Audigier et al. (2018). To mimic the real data, a general location model has been fitted on each study (Schafer, 1997). Then, each study has been generated according to the estimated parameters. Finally, missing values have been allocated similarly to the original dataset.

Usage

data("IPDNa")

Format

A data frame with 11685 observations on the following 10 variables.

centre

a numeric indexing the center where the study is conducted

gender

a factor with levels 0 1

bmi

a numeric vector indicating the body mass index

age

a numeric vector indicating the age

sbp

a numeric vector indicating the systolic blood pressure

dbp

a numeric vector indicating the diastolic blood pressure

hr

a numeric vector indicating the heart rate

lvef

a numeric vector indicating the ventricular ejection fraction

bnp

a numeric vector indicating the level of the brain natriuretic peptide biomarker

afib

a factor with levels 0 1 indicating the atrial fibrillation

Details

For more details, see Audigier et al. (2018)

References

Audigier, V., White, I. , Jolani ,S. Debray, T., Quartagno, M., Carpenter, J., van Buuren, S. and Resche-Rigon, M. Multiple imputation for multilevel data with continuous and binary variables (2018). Statistical Science. tools:::Rd_expr_doi("10.1214/18-STS646").

Resche-Rigon, M., White, I. R., Bartlett, J., Peters, S., Thompson, S., and on behalf of the PROG-IMT Study Group (2013). Multiple imputation for handling systematically missing confounders in meta-analysis of individual participant data. Statistics in Medicine, 32(28):4890-4905. tools:::Rd_expr_doi("10.1002/sim.5894")

Schafer, J. L. (1997) Analysis of Incomplete Multivariate Data. Chapman & Hall, Chapter 9.

Examples

data(IPDNa)

#summary
summary(IPDNa)

#summary per study
by(IPDNa, IPDNa$centre, summary)