Skip to content

Research at St Andrews

A hybrid procedure for detecting global treatment effects in multivariate clinical trials: theory and applications to fMRI studies

Research output: Contribution to journalArticle

DOI

Standard

A hybrid procedure for detecting global treatment effects in multivariate clinical trials : theory and applications to fMRI studies. / Minas, Giorgos; Rigat, Fabio; Nichols, Thomas E; Aston, John A D; Stallard, Nigel.

In: Statistics in Medicine, Vol. 31, No. 3, 10.02.2012, p. 253-68.

Research output: Contribution to journalArticle

Harvard

Minas, G, Rigat, F, Nichols, TE, Aston, JAD & Stallard, N 2012, 'A hybrid procedure for detecting global treatment effects in multivariate clinical trials: theory and applications to fMRI studies', Statistics in Medicine, vol. 31, no. 3, pp. 253-68. https://doi.org/10.1002/sim.4395

APA

Minas, G., Rigat, F., Nichols, T. E., Aston, J. A. D., & Stallard, N. (2012). A hybrid procedure for detecting global treatment effects in multivariate clinical trials: theory and applications to fMRI studies. Statistics in Medicine, 31(3), 253-68. https://doi.org/10.1002/sim.4395

Vancouver

Minas G, Rigat F, Nichols TE, Aston JAD, Stallard N. A hybrid procedure for detecting global treatment effects in multivariate clinical trials: theory and applications to fMRI studies. Statistics in Medicine. 2012 Feb 10;31(3):253-68. https://doi.org/10.1002/sim.4395

Author

Minas, Giorgos ; Rigat, Fabio ; Nichols, Thomas E ; Aston, John A D ; Stallard, Nigel. / A hybrid procedure for detecting global treatment effects in multivariate clinical trials : theory and applications to fMRI studies. In: Statistics in Medicine. 2012 ; Vol. 31, No. 3. pp. 253-68.

Bibtex - Download

@article{005894f4c91345b2be16f9a6df9c013b,
title = "A hybrid procedure for detecting global treatment effects in multivariate clinical trials: theory and applications to fMRI studies",
abstract = "In multivariate clinical trials, a key research endpoint is ascertaining whether a candidate treatment is more efficacious than an established alternative. This global endpoint is clearly of high practical value for studies, such as those arising from neuroimaging, where the outcome dimensions are not only numerous but they are also highly correlated and the available sample sizes are typically small. In this paper, we develop a two-stage procedure testing the null hypothesis of global equivalence between treatments effects and demonstrate its application to analysing phase II neuroimaging trials. Prior information such as suitable statistics of historical data or suitably elicited expert clinical opinions are combined with data collected from the first stage of the trial to learn a set of optimal weights. We apply these weights to the outcome dimensions of the second-stage responses to form the linear combination z and t tests statistics while controlling the test's false positive rate. We show that the proposed tests hold desirable asymptotic properties and characterise their power functions under wide conditions. In particular, by comparing the power of the proposed tests with that of Hotelling's T(2), we demonstrate their advantages when sample sizes are close to the dimension of the multivariate outcome. We apply our methods to fMRI studies, where we find that, for sufficiently precise first stage estimates of the treatment effect, standard single-stage testing procedures are outperformed.",
keywords = "Brain, Clinical Trials as Topic/statistics & numerical data, Humans, Magnetic Resonance Imaging/methods, Multivariate Analysis, Neuroimaging/statistics & numerical data, Research Design/statistics & numerical data, Sample Size",
author = "Giorgos Minas and Fabio Rigat and Nichols, {Thomas E} and Aston, {John A D} and Nigel Stallard",
note = "Copyright {\circledC} 2011 John Wiley & Sons, Ltd.",
year = "2012",
month = "2",
day = "10",
doi = "10.1002/sim.4395",
language = "English",
volume = "31",
pages = "253--68",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley & Sons, Ltd.",
number = "3",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - A hybrid procedure for detecting global treatment effects in multivariate clinical trials

T2 - theory and applications to fMRI studies

AU - Minas, Giorgos

AU - Rigat, Fabio

AU - Nichols, Thomas E

AU - Aston, John A D

AU - Stallard, Nigel

N1 - Copyright © 2011 John Wiley & Sons, Ltd.

PY - 2012/2/10

Y1 - 2012/2/10

N2 - In multivariate clinical trials, a key research endpoint is ascertaining whether a candidate treatment is more efficacious than an established alternative. This global endpoint is clearly of high practical value for studies, such as those arising from neuroimaging, where the outcome dimensions are not only numerous but they are also highly correlated and the available sample sizes are typically small. In this paper, we develop a two-stage procedure testing the null hypothesis of global equivalence between treatments effects and demonstrate its application to analysing phase II neuroimaging trials. Prior information such as suitable statistics of historical data or suitably elicited expert clinical opinions are combined with data collected from the first stage of the trial to learn a set of optimal weights. We apply these weights to the outcome dimensions of the second-stage responses to form the linear combination z and t tests statistics while controlling the test's false positive rate. We show that the proposed tests hold desirable asymptotic properties and characterise their power functions under wide conditions. In particular, by comparing the power of the proposed tests with that of Hotelling's T(2), we demonstrate their advantages when sample sizes are close to the dimension of the multivariate outcome. We apply our methods to fMRI studies, where we find that, for sufficiently precise first stage estimates of the treatment effect, standard single-stage testing procedures are outperformed.

AB - In multivariate clinical trials, a key research endpoint is ascertaining whether a candidate treatment is more efficacious than an established alternative. This global endpoint is clearly of high practical value for studies, such as those arising from neuroimaging, where the outcome dimensions are not only numerous but they are also highly correlated and the available sample sizes are typically small. In this paper, we develop a two-stage procedure testing the null hypothesis of global equivalence between treatments effects and demonstrate its application to analysing phase II neuroimaging trials. Prior information such as suitable statistics of historical data or suitably elicited expert clinical opinions are combined with data collected from the first stage of the trial to learn a set of optimal weights. We apply these weights to the outcome dimensions of the second-stage responses to form the linear combination z and t tests statistics while controlling the test's false positive rate. We show that the proposed tests hold desirable asymptotic properties and characterise their power functions under wide conditions. In particular, by comparing the power of the proposed tests with that of Hotelling's T(2), we demonstrate their advantages when sample sizes are close to the dimension of the multivariate outcome. We apply our methods to fMRI studies, where we find that, for sufficiently precise first stage estimates of the treatment effect, standard single-stage testing procedures are outperformed.

KW - Brain

KW - Clinical Trials as Topic/statistics & numerical data

KW - Humans

KW - Magnetic Resonance Imaging/methods

KW - Multivariate Analysis

KW - Neuroimaging/statistics & numerical data

KW - Research Design/statistics & numerical data

KW - Sample Size

U2 - 10.1002/sim.4395

DO - 10.1002/sim.4395

M3 - Article

VL - 31

SP - 253

EP - 268

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 3

ER -

Related by author

  1. Parameter sensitivity analysis for biochemical reaction networks

    Minas, G. & Rand, D. A., 6 May 2019, In : Mathematical Biosciences and Engineering. 16, 5, p. 3965-3987 23 p.

    Research output: Contribution to journalArticle

  2. Inferring transcriptional logic from multiple dynamic experiments

    Minas, G., Jenkins, D. J., Rand, D. A. & Finkenstädt, B., 1 Nov 2017, In : Bioinformatics. 33, 21, p. 3437-3444 8 p.

    Research output: Contribution to journalArticle

  3. Long-time analytic approximation of large stochastic oscillators: simulation, analysis and inference

    Minas, G. & Rand, D. A., 24 Jul 2017, In : PLoS Computational Biology. 13, 7, 23 p., e1005676.

    Research output: Contribution to journalArticle

  4. ReTrOS: a MATLAB toolbox for reconstructing transcriptional activity from gene and protein expression data

    Minas, G., Momiji, H., Jenkins, D. J., Costa, M. J., Rand, D. A. & Finkenstädt, B., 26 Jun 2017, In : BMC Bioinformatics. 18, 11 p., 316.

    Research output: Contribution to journalArticle

  5. Adaptive multivariate global testing

    Minas, G., Aston, J. A. D. & Stallard, N., Jun 2014, In : Journal of the American Statistical Association. 109, 506, p. 613-623 11 p.

    Research output: Contribution to journalArticle

Related by journal

  1. Identifying prognostic structural features in tissue sections of colon cancer patients using point pattern analysis

    Jones-Todd, C. M., Caie, P., Illian, J. B., Stevenson, B. C., Savage, A., Harrison, D. J. & Brown, J. L., 28 Nov 2018, In : Statistics in Medicine. Early View

    Research output: Contribution to journalArticle

  2. Incomplete contingency tables with censored cells with application to estimating the number of people who inject drugs in Scotland

    Overstall, A., King, R., Bird, S., Hutchinson, S. & Hay, G., 30 Apr 2014, In : Statistics in Medicine. 33, 9, p. 1564-1579

    Research output: Contribution to journalArticle

  3. Combining hidden Markov models for comparing the dynamics of multiple sleep electroencephalograms

    Langrock, R., Swihart, B., Caffo, B., Crainiceanu, C. & Punjabi, N., 2013, In : Statistics in Medicine. 32, 19, p. 3342-3356

    Research output: Contribution to journalArticle

  4. Author's Rejoinder to Commentaries on 'Designs for dose-escalation trials with quantitative responses'

    Bailey, R. A., 30 Dec 2009, In : Statistics in Medicine. 28, 30, p. 3759-3760 2 p.

    Research output: Contribution to journalComment/debate

ID: 255153852

Top