Kafatos, George; Andrews, Nick; McConway, Kevin J. and Farrington, Paddy
Regression models for censored serological data.
Journal of Medical Microbiology (In Press).
(Click here to request a copy from the OU Author.
This paper aims to assess the impact of censored serological measurements on regression equations fitted to data from panels of sera tested by different laboratories, for the purpose of standardising serosurvey results to common units. Several methods that adjust for censoring were compared, such as deletion, simple substitution, multiple imputation and censored regression. Simulations were generated from different scenarios for varying proportions of data censored. The scenarios were based on serological panel comparisons tested by different national laboratories and assays as part of the European Sero-Epidemiology Network (ESEN2) project. The results showed that the simple substitution and deletion methods worked reasonably well for low proportions of data censored (<20%). However, in general, the censored regression method gave estimates closer to the truth than the other methods examined under different scenarios, such as types of equations used and violation of regression assumptions. Interval censored regression produced the least biased estimates for assay data resulting from dilution series. Censored regression produced the least biased estimates in comparison to the other methods examined. In addition, a case has been made for applying in the future interval censored regression for assay data resulting from dilution series.
Actions (login may be required)