A novel scaling methodology to reduce the biases associated with missing data from commercial activity monitors

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

A novel scaling methodology to reduce the biases associated with missing data from commercial activity monitors. / O’Driscoll, R.; Turicchi, J.; Duarte, C.; Michalowska, J.; Larsen, S. C.; Palmeira, A. L.; Heitmann, B. L.; Horgan, G. W.; Stubbs, R. J.

I: PLoS ONE, Bind 15, Nr. 6, e0235144, 2020.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

O’Driscoll, R, Turicchi, J, Duarte, C, Michalowska, J, Larsen, SC, Palmeira, AL, Heitmann, BL, Horgan, GW & Stubbs, RJ 2020, 'A novel scaling methodology to reduce the biases associated with missing data from commercial activity monitors', PLoS ONE, bind 15, nr. 6, e0235144. https://doi.org/10.1371/journal.pone.0235144

APA

O’Driscoll, R., Turicchi, J., Duarte, C., Michalowska, J., Larsen, S. C., Palmeira, A. L., Heitmann, B. L., Horgan, G. W., & Stubbs, R. J. (2020). A novel scaling methodology to reduce the biases associated with missing data from commercial activity monitors. PLoS ONE, 15(6), [e0235144]. https://doi.org/10.1371/journal.pone.0235144

Vancouver

O’Driscoll R, Turicchi J, Duarte C, Michalowska J, Larsen SC, Palmeira AL o.a. A novel scaling methodology to reduce the biases associated with missing data from commercial activity monitors. PLoS ONE. 2020;15(6). e0235144. https://doi.org/10.1371/journal.pone.0235144

Author

O’Driscoll, R. ; Turicchi, J. ; Duarte, C. ; Michalowska, J. ; Larsen, S. C. ; Palmeira, A. L. ; Heitmann, B. L. ; Horgan, G. W. ; Stubbs, R. J. / A novel scaling methodology to reduce the biases associated with missing data from commercial activity monitors. I: PLoS ONE. 2020 ; Bind 15, Nr. 6.

Bibtex

@article{7af511c29a534dd7a0064caeb0dfe6ce,
title = "A novel scaling methodology to reduce the biases associated with missing data from commercial activity monitors",
abstract = "Background Commercial physical activity monitors have wide utility in the assessment of physical activity in research and clinical settings, however, the removal of devices results in missing data and has the potential to bias study conclusions. This study aimed to evaluate methods to address missingness in data collected from commercial activity monitors. Methods This study utilised 1526 days of near complete data from 109 adults participating in a European weight loss maintenance study (NoHoW). We conducted simulation experiments to test a novel scaling methodology (NoHoW method) and alternative imputation strategies (overall/individual mean imputation, overall/individual multiple imputation, Kalman imputation and random forest imputation). Methods were compared for hourly, daily and 14-day physical activity estimates for steps, total daily energy expenditure (TDEE) and time in physical activity categories. In a second simulation study, individual multiple imputation, Kalman imputation and the NoHoW method were tested at different positions and quantities of missingness. Equivalence testing and root mean squared error (RMSE) were used to evaluate the ability of each of the strategies relative to the true data. Results The NoHoW method, Kalman imputation and multiple imputation methods remained statistically equivalent (p<0.05) for all physical activity metrics at the 14-day level. In the second simulation study, RMSE tended to increase with increased missingness. Multiple imputation showed the smallest RMSE for Steps and TDEE at lower levels of missingness (<19%) and the Kalman and NoHoW methods were generally superior for imputing time in physical activity categories. Conclusion Individual centred imputation approaches (NoHoW method, Kalman imputation and individual Multiple imputation) offer an effective means to reduce the biases associated with missing data from activity monitors and maximise data retention.",
author = "R. O{\textquoteright}Driscoll and J. Turicchi and C. Duarte and J. Michalowska and Larsen, {S. C.} and Palmeira, {A. L.} and Heitmann, {B. L.} and Horgan, {G. W.} and Stubbs, {R. J.}",
year = "2020",
doi = "10.1371/journal.pone.0235144",
language = "English",
volume = "15",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "6",

}

RIS

TY - JOUR

T1 - A novel scaling methodology to reduce the biases associated with missing data from commercial activity monitors

AU - O’Driscoll, R.

AU - Turicchi, J.

AU - Duarte, C.

AU - Michalowska, J.

AU - Larsen, S. C.

AU - Palmeira, A. L.

AU - Heitmann, B. L.

AU - Horgan, G. W.

AU - Stubbs, R. J.

PY - 2020

Y1 - 2020

N2 - Background Commercial physical activity monitors have wide utility in the assessment of physical activity in research and clinical settings, however, the removal of devices results in missing data and has the potential to bias study conclusions. This study aimed to evaluate methods to address missingness in data collected from commercial activity monitors. Methods This study utilised 1526 days of near complete data from 109 adults participating in a European weight loss maintenance study (NoHoW). We conducted simulation experiments to test a novel scaling methodology (NoHoW method) and alternative imputation strategies (overall/individual mean imputation, overall/individual multiple imputation, Kalman imputation and random forest imputation). Methods were compared for hourly, daily and 14-day physical activity estimates for steps, total daily energy expenditure (TDEE) and time in physical activity categories. In a second simulation study, individual multiple imputation, Kalman imputation and the NoHoW method were tested at different positions and quantities of missingness. Equivalence testing and root mean squared error (RMSE) were used to evaluate the ability of each of the strategies relative to the true data. Results The NoHoW method, Kalman imputation and multiple imputation methods remained statistically equivalent (p<0.05) for all physical activity metrics at the 14-day level. In the second simulation study, RMSE tended to increase with increased missingness. Multiple imputation showed the smallest RMSE for Steps and TDEE at lower levels of missingness (<19%) and the Kalman and NoHoW methods were generally superior for imputing time in physical activity categories. Conclusion Individual centred imputation approaches (NoHoW method, Kalman imputation and individual Multiple imputation) offer an effective means to reduce the biases associated with missing data from activity monitors and maximise data retention.

AB - Background Commercial physical activity monitors have wide utility in the assessment of physical activity in research and clinical settings, however, the removal of devices results in missing data and has the potential to bias study conclusions. This study aimed to evaluate methods to address missingness in data collected from commercial activity monitors. Methods This study utilised 1526 days of near complete data from 109 adults participating in a European weight loss maintenance study (NoHoW). We conducted simulation experiments to test a novel scaling methodology (NoHoW method) and alternative imputation strategies (overall/individual mean imputation, overall/individual multiple imputation, Kalman imputation and random forest imputation). Methods were compared for hourly, daily and 14-day physical activity estimates for steps, total daily energy expenditure (TDEE) and time in physical activity categories. In a second simulation study, individual multiple imputation, Kalman imputation and the NoHoW method were tested at different positions and quantities of missingness. Equivalence testing and root mean squared error (RMSE) were used to evaluate the ability of each of the strategies relative to the true data. Results The NoHoW method, Kalman imputation and multiple imputation methods remained statistically equivalent (p<0.05) for all physical activity metrics at the 14-day level. In the second simulation study, RMSE tended to increase with increased missingness. Multiple imputation showed the smallest RMSE for Steps and TDEE at lower levels of missingness (<19%) and the Kalman and NoHoW methods were generally superior for imputing time in physical activity categories. Conclusion Individual centred imputation approaches (NoHoW method, Kalman imputation and individual Multiple imputation) offer an effective means to reduce the biases associated with missing data from activity monitors and maximise data retention.

U2 - 10.1371/journal.pone.0235144

DO - 10.1371/journal.pone.0235144

M3 - Journal article

C2 - 32579613

AN - SCOPUS:85087098805

VL - 15

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 6

M1 - e0235144

ER -

ID: 244994783