Strategies for Dealing with Missing Accelerometer Data

Samantha Stephens; Joseph Beyene; Mark S Tremblay; Guy Faulkner; Eleanor Pullnayegum; Brian M Feldman

doi:10.1016/j.rdc.2018.01.012

Strategies for Dealing with Missing Accelerometer Data

Rheum Dis Clin North Am. 2018 May;44(2):317-326. doi: 10.1016/j.rdc.2018.01.012. Epub 2018 Feb 21.

Authors

Samantha Stephens¹, Joseph Beyene², Mark S Tremblay³, Guy Faulkner⁴, Eleanor Pullnayegum⁵, Brian M Feldman⁶

Affiliations

¹ Neurosciences and Mental Health, Pediatric M.S., Neuroinflammatory Disorders Program, Center for Brain and Mental Health, Peter Gilgan Centre for Research and Learning, The Hospital for Sick Children, 686 Bay Street, Room 8.9830, Toronto, Ontario M5G 0A4, Canada. Electronic address: Samantha.stephens@sickkids.ca.
² Department of Clinical Epidemiology and Biostatistics, 208 Michael G. DeGroote Centre for Learning, McMaster University, 1280 Main Street W., Hamilton, Ontario L8S 4K1, Canada.
³ Children's Hospital of Eastern Ontario Research Institute, University of Ottawa, Ottawa, Ontario, Canada.
⁴ Canadian Institutes of Health Research, Public Health Agency of Canada, Applied Public Health, University of British Columbia, D. H. Copp Building, Room 4606 2146 Health Sciences Mall, Vancouver, BC V6T1Z3, Canada.
⁵ Child Health Evaluative Sciences, The Hospital for Sick Children, Public Health Sciences, The University of Toronto, Toronto, Ontario, Canada.
⁶ Child Health Evaluative Sciences, The Hospital for Sick Children, Department of Pediatrics, Institute of Health Policy Management and Evaluation, The Dalla Lana School of Public Health, The University of Toronto, Toronto, Ontario, Canada.

PMID: 29622298
DOI: 10.1016/j.rdc.2018.01.012

Abstract

Missing data is a universal research problem that can affect studies examining the relationship between physical activity measured with accelerometers and health outcomes. Statistical techniques are available to deal with missing data; however, available techniques have not been synthesized. A scoping review was conducted to summarize the advantages and disadvantages of identified methods of dealing with missing data from accelerometers. Missing data poses a threat to the validity and interpretation of trials using physical activity data from accelerometry. Imputation using multiple imputation techniques is recommended to deal with missing data and improve the validity and interpretation of studies using accelerometry.

Keywords: Data; Imputation; Measurement; Missing; Physical activity.

Publication types

Review

MeSH terms

Accelerometry*
Biomedical Research / standards*
Data Collection / standards*
Exercise*
Humans
Reproducibility of Results