Modeling age-of-onset: Cox model with latent major gene effects
- Univ. of Washington, Seattle, WA (United States)
Analysis of age-of-onset is a key factor in the segregation and linkage analysis of complex genetic traits, but is complicated by the censoring of unaffected individuals. Most previous work has used parametric distributional assumptions, but it is hard to characterize the distribution of age-of-onset by a single distribution. Other approaches discretize age-of-onset and use logistic regression to model incidence; this approach does not use the information fully. Frailty models have been used for age-of-oset in the biostatistics literature, but these models do not lend themselves to modeling the correlations due to genetic effects which segregate within a family. Here, we propose use of the Cox model with latent major gene effects; conditional on the major genotypes, Cox`s proportional hazards model is used for age-of-onset for each individual. This is a semiparametric model; we do not specify the baseline hazard function. Likelihood analysis of such models is restricted by the difficulty in evaluating of maximizing the likelihood, especially when data are available for some of the members of an extended pedigree. Markov chain Monte Carlo permits genotypic configurations to be realized from the posterior distributions given a current model and the observed data. Hence methods for likelihood analysis can be developed: Monte Carlo EM is used for estimation of the parameters and their variance-covariance matrix. Markers and observed covariates are easily incorporated into this analysis. We present the model, methods for likelihood analysis and the results of a simulation study. The results are comparable with those based on a Cox model with known genotypic dependence in a pedigree. An early-onset Alzheimer`s pedigree and some breast cancer pedigrees have been used as real data examples. Some possible extensions are also discussed.
- OSTI ID:
- 133911
- Report Number(s):
- CONF-941009-; ISSN 0002-9297; TRN: 95:005313-0645
- Journal Information:
- American Journal of Human Genetics, Vol. 55, Issue Suppl.3; Conference: 44. annual meeting of the American Society of Human Genetics, Montreal (Canada), 18-22 Oct 1994; Other Information: PBD: Sep 1994
- Country of Publication:
- United States
- Language:
- English
Similar Records
Covariate analysis of survival data: a small-sample study of Cox's model
Incidence of monotone likelihood in the Cox model
Related Subjects
BASIC STUDIES
99 MATHEMATICS
COMPUTERS
INFORMATION SCIENCE
MANAGEMENT
LAW
MISCELLANEOUS
AGE GROUPS
STATISTICAL MODELS
CORRELATIONS
PHENOTYPE
SEGREGATION
GENETIC EFFECTS
HEREDITARY DISEASES
AGE DEPENDENCE
HUMAN POPULATIONS
GENETICS
GENOTYPE
GENES
BIOLOGICAL MARKERS
MONTE CARLO METHOD