This article was downloaded by: [University of Nebraska, Lincoln] On: 06 April 2015, At: 11:03 Publisher: Taylor & Francis Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, UK

Journal of Biopharmaceutical Statistics Publication details, including instructions for authors and subscription information: http://www.tandfonline.com/loi/lbps20

A Simple and Powerful Method for the Estimation of Intervention Effects on Serological Endpoints Using Paired Interval-Censored Data ab

c

de

fg

Ying Xu , K. F. Lam , Eng Eong Ooi , Annelies Wilder-Smith , fg

fg

abh

Nicholas I. Paton , Lawrence S. Lee & Yin Bun Cheung a

Centre for Quantitative Medicine, Office of Clinical Sciences, Duke-NUS Graduate Medical School, Singapore, Singapore b

Click for updates

Scientific Development Division, Singapore Clinical Research Institute, Singapore, Singapore c

Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong, Hong Kong d

Emerging Infectious Diseases Program, Duke-NUS Graduate Medical School, Singapore, Singapore e

DSO National Laboratories, Defense Medical and Environmental Research Institute, Singapore, Singapore f

Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore g

National University Health System, Singapore, Singapore

h

Department of International Health, University of Tampere, Tampere, Finland Accepted author version posted online: 16 May 2014.Published online: 20 Jan 2015.

To cite this article: Ying Xu, K. F. Lam, Eng Eong Ooi, Annelies Wilder-Smith, Nicholas I. Paton, Lawrence S. Lee & Yin Bun Cheung (2015) A Simple and Powerful Method for the Estimation of Intervention Effects on Serological Endpoints Using Paired Interval-Censored Data, Journal of Biopharmaceutical Statistics, 25:1, 124-136, DOI: 10.1080/10543406.2014.919936 To link to this article: http://dx.doi.org/10.1080/10543406.2014.919936

PLEASE SCROLL DOWN FOR ARTICLE Taylor & Francis makes every effort to ensure the accuracy of all the information (the “Content”) contained in the publications on our platform. However, Taylor & Francis, our agents, and our licensors make no representations or warranties whatsoever as to

the accuracy, completeness, or suitability for any purpose of the Content. Any opinions and views expressed in this publication are the opinions and views of the authors, and are not the views of or endorsed by Taylor & Francis. The accuracy of the Content should not be relied upon and should be independently verified with primary sources of information. Taylor and Francis shall not be liable for any losses, actions, claims, proceedings, demands, costs, expenses, damages, and other liabilities whatsoever or howsoever caused arising directly or indirectly in connection with, in relation to or arising out of the use of the Content.

Downloaded by [University of Nebraska, Lincoln] at 11:03 06 April 2015

This article may be used for research, teaching, and private study purposes. Any substantial or systematic reproduction, redistribution, reselling, loan, sub-licensing, systematic supply, or distribution in any form to anyone is expressly forbidden. Terms & Conditions of access and use can be found at http://www.tandfonline.com/page/termsand-conditions

Journal of Biopharmaceutical Statistics, 25: 124–136, 2015 Copyright © Taylor & Francis Group, LLC ISSN: 1054-3406 print/1520-5711 online DOI: 10.1080/10543406.2014.919936

Downloaded by [University of Nebraska, Lincoln] at 11:03 06 April 2015

A SIMPLE AND POWERFUL METHOD FOR THE ESTIMATION OF INTERVENTION EFFECTS ON SEROLOGICAL ENDPOINTS USING PAIRED INTERVAL-CENSORED DATA Ying Xu1,2 , K. F. Lam3 , Eng Eong Ooi4,5 , Annelies Wilder-Smith6,7 , Nicholas I. Paton6,7 , Lawrence S. Lee6,7 , and Yin Bun Cheung1,2,8 1 Centre for Quantitative Medicine, Office of Clinical Sciences, Duke-NUS Graduate Medical School, Singapore, Singapore 2 Scientific Development Division, Singapore Clinical Research Institute, Singapore, Singapore 3 Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong, Hong Kong 4 Emerging Infectious Diseases Program, Duke-NUS Graduate Medical School, Singapore, Singapore 5 DSO National Laboratories, Defense Medical and Environmental Research Institute, Singapore, Singapore 6 Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore 7 National University Health System, Singapore, Singapore 8 Department of International Health, University of Tampere, Tampere, Finland

Clinical trials often use a binary “fold increase” endpoint defined according to the ratio of interval-censored measurement at end-of-study to that at baseline. We propose a simple yet principled analytic approach based on the linear mixed-effects model for interval-censored data for the analysis of such paired measurements. Having estimated the model parameters, the risk ratio can be estimated by explicit composite estimand and the variance is estimated using the delta method. The estimation can be implemented using the existing procedures in popular statistical software. We use antibody data from the Chloroquine for Influenza Prevention Trial for illustration. Key Words: Fold increase; Interval censored; Linear mixed-effects model; Risk ratio.

1. INTRODUCTION Many epidemiological investigations involve laboratory assay data that are interval censored. The assays measure the presence of an analyte in a series of (usually) two-fold dilutions of each sample. The level of response is then taken as the reciprocal of the highest dilution that still shows a positive reading. An example is the hemagglutination inhibition (HI) assay, which measures influenza antibody concentration (Nauta, 2010). The serial Received February 14, 2013; Accepted July 30, 2013 Address correspondence to Ying Xu, Centre for Quantitative Medicine, Office of Clinical Sciences, DukeNUS Graduate Medical School, Singapore 169857, Singapore; E-mail: [email protected] 124

Downloaded by [University of Nebraska, Lincoln] at 11:03 06 April 2015

ESTIMATION OF INTERVENTION EFFECTS USING PAIRED INTERVAL-CENSORED DATA 125

dilutions may include 1:10, 1:20, 1:40, 1:80, and so on. The final dilution may be 1:640 (or sometimes higher). The assay read-out, called standard titer by Nauta and de Bruijn (2006), appears as

A simple and powerful method for the estimation of intervention effects on serological endpoints using paired interval-censored data.

Clinical trials often use a binary "fold increase" endpoint defined according to the ratio of interval-censored measurement at end-of-study to that at...
217KB Sizes 0 Downloads 3 Views