A comparison of least squares and conditional maximum likelihood estimators under volume endpoint censoring in tumor growth experiments.
Stat Med
; 31(29): 4061-73, 2012 Dec 20.
Article
em En
| MEDLINE
| ID: mdl-22826185
ABSTRACT
Measurements in tumor growth experiments are stopped once the tumor volume exceeds a preset threshold a mechanism we term volume endpoint censoring. We argue that this type of censoring is informative. Further, least squares (LS) parameter estimates are shown to suffer a bias in a general parametric model for tumor growth with an independent and identically distributed measurement error, both theoretically and in simulation experiments. In a linear growth model, the magnitude of bias in the LS growth rate estimate increases with the growth rate and the standard deviation of measurement error. We propose a conditional maximum likelihood estimation procedure, which is shown both theoretically and in simulation experiments to yield approximately unbiased parameter estimates in linear and quadratic growth models. Both LS and maximum likelihood estimators have similar variance characteristics. In simulation studies, these properties appear to extend to the case of moderately dependent measurement error. The methodology is illustrated by application to a tumor growth study for an ovarian cancer cell line.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Neoplasias Ovarianas
/
Análise dos Mínimos Quadrados
/
Funções Verossimilhança
Tipo de estudo:
Prognostic_studies
Limite:
Animals
Idioma:
En
Revista:
Stat Med
Ano de publicação:
2012
Tipo de documento:
Article
País de afiliação:
Irlanda