Search Results
Title: Bivariate Survival Analysis with Association
Resulting in 1 citation.
| 1. |
Huang, Jinlin |
|
Bivariate Survival Analysis with Association Presented: Ft. Lauderdale, FL, American Statistical Association Winter Conference, Families and Children: Research Findings, Data Needs, and Survey Issues, 1993 Cohort(s): NLSY79 Publisher: American Statistical Association Keyword(s): Data Analysis; Marriage; Modeling, Mixed Effects; Monte Carlo; Pairs (also see Siblings); Statistical Analysis; Variables, Independent - Covariate Linear model approach is used on a bivariate survival model with censoring in either or both components. Various parametric, semi-parametric and non-parametric methods are applied to estimate an association parameter, as well as the covariates. When the postulated model has fewer covariates than the true model has, the estimation bias is smaller with bivariate model than with univariate model. A new bivariate model with time-dependent covariates and competing risks is established. Special goodness-to-fit technique for censored data and Monte Carlo simulation are used. The final section is an application to the ages at the first marriage for pairs of sisters where "failure" means the first marriage. The data is from the National Longitudinal Study of Youth from 1978 to 1988. |
|
|
Bibliography Citation
Huang, Jinlin. "Bivariate Survival Analysis with Association." Presented: Ft. Lauderdale, FL, American Statistical Association Winter Conference, Families and Children: Research Findings, Data Needs, and Survey Issues, 1993. |