Sage Journals: Discover world-class research

Abstract

When undertaking confirmatory analyses of data from clinical trials, statisticians frequently are confronted with having to assess and address potential biases introduced by missing data. New developments for handling missing data have proliferated in the literature. Sensitivity analysis, which allows the assessment of the impact of a wide range of nonignorable missingness mechanisms on the robustness of the statistical results, provides a reasonable alternative for analyzing trials with missing data. Two case studies utilizing sensitivity analyses in pharmaceutical industry clinical trials are presented. The first is based on an Alzheimer disease trial with a time-to-event endpoint, and the second is from an osteoporosis trial with a repeated binary outcome. The practical issues associated with the application of sensitivity analysis are discussed as well.

Keywords

Missing data Model-based multiple imputation Sensitivity Clinical trial

Get full access to this article

View all access options for this article.

References

Little

RJA

Rubin

. Statistical Analysis With Missing Data. New York: Wiley; 2002.

Mallinckrodt

. Recommendations for the primary analysis of continuous endpoints in longitudinal clinical trials. (2007). Manuscript submitted for publication.

Yang

. A view on missing data issue from a regulatory perspective. Paper presented at Drug Information Association 43 rd Annual Meeting, 2007.

Hogan

. Tutorial in biostatistics: Handling drop-out in longitudinal studies. Stat. Med. 2004; 23: 1455–1497.

Molenberghs

Verbeke

. Models for Discrete Longitudinal Data. New York: Springer; 2005.

Diggle

Kenward

. Informative drop-out in longitudinal data analysis (with discussion). Appl Stat. 1994; 43: 49–93.

Hogan

Laird

. Mixture models for the joint distribution of repeated measures and event times. Stat Med. 1997; 16: 239–257.

Little

RJA

. Pattern-mixture models for multivariate incomplete data. J Am Stat Assoc. 1993; 88: 125–134.

Little

RJA

. Modeling the missing mechanism in repeated-measures studies. J Am Stat Assoc. 1995; 90: 1112–1121.

10.

Committee for Proprietary Medicinal Products.

Points to consider on missing data. CPMP/EWP/1776/99. London: European Agency for the Evaluation of Medicinal Products; 2001.

11.

Feldman

Ferris

Winblad

. Effect of rivastigmine on delay to diagnosis of Alzheimer's disease from mild cognitive impairment: The InD-DEx study. Lancet Neurol. 2007; 6: 501–512.

12.

Black

. An assessment tool for predicting fracture risk in postmenopausal women. Osteoporos Int. 2001; 12: 519–528.

13.

Schafer

. Analysis of Incomplete Multivariate Data. London: CRC Press Chapman & Hall; 1997.

14.

Chesnut

. A randomized trial of nasal spray salmon calcitonin in postmenopausal women with established osteoporosis: The prevent recurrence of osteoporotic fractures study. Am J Med. 2000; 109: 267–276.

15.

Neuenschwander

Branson

. Modeling missingness for time-to-event data: A case study in osteoporosis. J Biopharm Stat. 2004; 14: 1005–1019.

16.

Kanis

. A new approach to the development of assessment guidelines for osteoporosis. Osteoporos Int. 2002; 13: 527–536.

17.

Miller

. An approach to identifying osteopenic women at increased short-term risk of fracture. Arch Intern Med. 2004; 164: 1113–1120.

18.

Hosmer

Lemeshow

. Applied Logistic Regression. New York: John Wiley; 1989.

19.

Thijs

. Strategies to fit pattern-mixture models. Biostatistics. 2002; 3: 245–265.

20.

Curran

. Sensitivity analysis for pattern mixture models. J Biopharm Stat. 2004; 14: 125–143.

21.

Daniels

Hogan

. Reparameterizing the pattern mixture model for sensitivity analyses under informative dropout. Biometrics. 2000; 56: 1241–1248.

Sensitivity Analysis of Missing Data: Case Studies Using Model-Based Multiple Imputation

Abstract

Keywords

Get full access to this article

References