In patient-based studies, biomarker data are often subject to left censoring due to the detection limits, or to incomplete sample or data collection. In the context of longitudinal regression analysis, inappropriate handling of these issues could lead to biased parameter estimates. We developed a specific multiple imputation (MI) strategy based on weighted censored quantile regression (CQR) that not only accounts for censoring, but also missing data at early visits when longitudinal biomarker data are modeled as a covariate.
We assessed through simulation studies the performances of developed imputation approach by considering various scenarios of covariance structures of longitudinal data and levels of censoring. We also illustrated the application of the proposed method to the Prospective Study of Outcomes in Ankylosing spondylitis (AS) (PSOAS) data to address the issues of censored or missing C-reactive protein (CRP) level at early visits for a group of patients.
Our findings from simulation studies indicated that the proposed method performs better than other MI methods by having a higher relative efficiency. We also found that our approach is not sensitive to the choice of covariance structure as compared to other methods that assume normality of biomarker data. The analysis results of PSOAS data from the imputed CRP levels based on our method suggested that higher CRP is significantly associated with radiographic damage, while those from other methods did not result in a significant association.
The MI based on weighted CQR offers a more valid statistical approach to evaluate a biomarker of disease in the presence of both issues with censoring and missing data in early visits.
Braun J, Baraliakos X, Hermann KA, Xu S, Hsu B. Serum C-reactive Protein Levels Demonstrate Predictive Value for Radiographic and Magnetic Resonance Imaging Outcomes in Patients with Active Ankylosing Spondylitis Treated with Golimumab. J Rheumatol. 2016. doi: https://doi.org/10.3899/jrheum.160003.
Calin A, Farrett S, Whitelock H, Kennedy LG, OHea J, Mallorie P, Jenkinson T. A new approach to defining functional ability in ankylosing spondylitis: the development of the Bath Ankylosing Spondyitis Functional Index. J Rheumatol. 1994; 21:2281–5. PubMed
Creemers MC, Franssen MJ, vant Hof MA, Gribnau FW, van de Putte LB, van Riel PL. Assessment of outcome in ankylosing spondylitis: an extended radiographic scoring system. Ann Rheum Dis. 2005; 64:1279. CrossRef
Fitzenberger B. A guide to censored quantile regressions In: Maddala GS, Rao CR, editors. Handbook of Statistics, Volume 15 (Robust Inference). Amsterdam: Elsevier Science; 1997. p. 405–37.
Gao S, Thiebaut R. Mixed-effect Models for Truncated Longitudinal Outcomes with Nonignorable Missing Data. J Data Sci. 2009; 7(1):13–25.
Garrett S, Jenkinson T, Kennedy LG, Whitelock H, Gaisford P, Calin A. A new approach to defining disease status in ankylosing spondylitis: the Bath Ankylosing Spondylitis Disease Activity Index. J Rheumatol. 1994; 21:2286–91. PubMed
Lee M, Kong L. Median Regression for Longitudinal Left-censored Biomarker Data subject to Detection Limit. J Stat Biopharm Res. 2011; 3(2):363–71. CrossRef
Lee M, Kong L. Quantile Regression For Longitudinal Biomarker Data Subject to Left Censoring and Dropouts. Commun Stat Theory Methods. 2014; 43(21):4628–41. CrossRef
Li KH. Imputation Using Markov Chains. J Stat Comput Simul. 1988; 30:5779. CrossRef
Lipsitz SR, Fitzmaurice GM, Molenberghs G, Zhao LP. Quantile regression methods for longitudinal data with drop-outs: Application to CD4 cell counts of patients infected with the human immunodeficiency virus. J R Stat Soc: Ser C: Appl Stat. 1997; 46(4):463–476. CrossRef
Little RJA, Rubin DB. Statistical analysis with missing data, 2nd edition. New York: Wiley; 2002. CrossRef
Liu M, Wei L, Zhang J. Review of guidelines and literature for handling missing data in longitudinal clinical trials with a case study. Pharm Stat. 2006; 5:718. CrossRef
Lyles RH, Lyles CM, Taylor DJ. Random regression models for human immunodeficiency virus ribonucleic acid data subject to left censoring and informative drop-outs. J R Stat Soc: Ser C. 2000; 49(4):485–97. CrossRef
Meng X. Multiple-imputation inferences with uncongenial sources of input. Stat Sci. 1994; 9(4):538–73. CrossRef
Powell JL. Least Absolute Deviations Estimation for the Censored Regression Model. J Econ. 1984; 25(3):303–25. CrossRef
Powell JL. Censored regression quantiles. J Econ. 1986; 32(1):143–55. CrossRef
Rubin DB. Multiple Imputation for Nonresponse in Surveys. New York: Wiley; 1987. CrossRef
Rubin DB. Multiple imputation after 18 + years. J Am Stat Assoc. 1996; 91(434):473–89. CrossRef
Thiebaut R, Jacqmin-Gadda H, Babiker A, Commenges D. Joint modelling of bivariate longitudinal data with informative dropout and left-censoring, with application to the evolution of CD4+ cell count and HIV RNA viral load in response to treatment of HIV infection. Stat Med. 2005; 24(1):65–82. CrossRefPubMed
van Buuren S, Groothuis-Oudshoorn K. mice: Multivariate Imputation by Chained Equations in R. J Stat Softw. 2011; 45(3):1–67.
Wang JH, Fygenson M. Inference for Censored Quantile Regression Models in Longitudinal studies. Ann Stat. 2009; 37(2):756–81. CrossRef
Wang JH, Feng X. Multiple Imputation for M-regression with Censored Covariates. J Am Stat Assoc. 2012; 107(497):194–204. CrossRef
- A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits
Mohammad H. Rahbar
John D. Reveille
- BioMed Central
Neu im Fachgebiet AINS
Meistgelesene Bücher aus dem Fachgebiet AINS
Mail Icon II