Properties of bootstrap tests for N-of-1 studies

Authors: Lin, S., Morrison, L., Smith, P., Hargood, C., Weal, M. and Yardley, L.

http://eprints.bournemouth.ac.uk/26575/

Journal: British Journal of Mathematical and Statistical Psychology

DOI: 10.1111/bmsp.12071

N-of-1 study designs involve the collection and analyses of repeated measures data from an individual not using an intervention and using an intervention. This study explores the use of semi-parametric and parametric bootstrap tests in the analysis of N-of-1 studies under a single time series framework in the presence of autocorrelation. When the Type I error rates of bootstrap tests are compared to Wald tests, our results show the bootstrap tests have more desirable properties. We compare the results for normally distributed errors with those for contaminated normally distributed errors and find that, except for when there is relatively large autocorrelation, there is little difference between the power of the parametric and semi-parametric bootstrap tests. We also experiment with two intervention designs: ABAB and AB, and show the ABAB design has more power. The results provide guidelines for designing N-of-1 studies, in the sense of how many observations and how many intervention changes are needed to achieve a certain level of power and which test should be performed.

This data was imported from PubMed:

Authors: Lin, S.X., Morrison, L., Smith, P.W.F., Hargood, C., Weal, M. and Yardley, L.

http://eprints.bournemouth.ac.uk/26575/

Journal: Br J Math Stat Psychol

Volume: 69

Issue: 3

Pages: 276-290

eISSN: 2044-8317

DOI: 10.1111/bmsp.12071

N-of-1 study designs involve the collection and analysis of repeated measures data from an individual not using an intervention and using an intervention. This study explores the use of semi-parametric and parametric bootstrap tests in the analysis of N-of-1 studies under a single time series framework in the presence of autocorrelation. When the Type I error rates of bootstrap tests are compared to Wald tests, our results show that the bootstrap tests have more desirable properties. We compare the results for normally distributed errors with those for contaminated normally distributed errors and find that, except when there is relatively large autocorrelation, there is little difference between the power of the parametric and semi-parametric bootstrap tests. We also experiment with two intervention designs: ABAB and AB, and show the ABAB design has more power. The results provide guidelines for designing N-of-1 studies, in the sense of how many observations and how many intervention changes are needed to achieve a certain level of power and which test should be performed.

This source preferred by Charlie Hargood

This data was imported from Scopus:

Authors: Lin, S.X., Morrison, L., Smith, P.W.F., Hargood, C., Weal, M. and Yardley, L.

http://eprints.bournemouth.ac.uk/26575/

Journal: British Journal of Mathematical and Statistical Psychology

Volume: 69

Issue: 3

Pages: 276-290

eISSN: 2044-8317

ISSN: 0007-1102

DOI: 10.1111/bmsp.12071

© 2016 The Authors British Journal of Mathematical and Statistical Psychology published by John Wiley & Sons Ltd on behalf of British Psychological Society N-of-1 study designs involve the collection and analysis of repeated measures data from an individual not using an intervention and using an intervention. This study explores the use of semi-parametric and parametric bootstrap tests in the analysis of N-of-1 studies under a single time series framework in the presence of autocorrelation. When the Type I error rates of bootstrap tests are compared to Wald tests, our results show that the bootstrap tests have more desirable properties. We compare the results for normally distributed errors with those for contaminated normally distributed errors and find that, except when there is relatively large autocorrelation, there is little difference between the power of the parametric and semi-parametric bootstrap tests. We also experiment with two intervention designs: ABAB and AB, and show the ABAB design has more power. The results provide guidelines for designing N-of-1 studies, in the sense of how many observations and how many intervention changes are needed to achieve a certain level of power and which test should be performed.

The data on this page was last updated at 04:40 on November 22, 2017.