Semiparametric Estimation of Marginal Hazard Function from Case–Control Family Studies

Hsu, Li; Lü, Chen; Gorfine, Malka; Malone, Kathleen E.

doi:10.1111/j.0006-341x.2004.00249.x

Cited by 25 publications

(33 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One may further improve the efficiency of the dependence parameter estimate obtained by maximizing the profile likelihood function L with plug-in estimates and 0 (t). From our simulation study [22], this additional step appears to have little impact on the efficiency of and 0 (t), but it improves the efficiency of substantially. We will use this iterative approach in the simulation study.…”

Section: An Estimation Procedures For Retrospective Correlated Failurementioning

confidence: 83%

“…For retrospectively collected correlated failure time data such as those arising from case-control family studies, both retrospective sampling and the dependency of the failure times need to be accounted for when estimating the regression coefficients, the marginal hazard function and the dependence parameters. We recently proposed a two-stage estimation technique under the gamma frailty model [22] by estimating in the first stage, then assuming known, estimating and 0 (t) in the second stage. The idea is that if the frailty were known for each family, the marginal hazard function could be estimated through the standard software routine for the Cox proportional hazards model with an offset term of log( ).…”

Section: An Estimation Procedures For Retrospective Correlated Failurementioning

confidence: 99%

“…The researchers were interested in studying how risk factors are correlated within a family and how they affect the age at onset distribution for women. For such data, estimation procedures developed for cohort correlated failure times would need to be modified to adjust for the non-cohort design of cases and controls [21,22]. It is unclear whether Glidden and Vittinghoff's observation on the regression coefficients still holds in this situation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On robustness of marginal regression coefficient estimates and hazard functions in multivariate survival analysis of family data when the frailty distribution is mis‐specified

Hsu

Gorfine

Malone

2007

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

The shared frailty model is an extension of the Cox model to correlated failure times and, essentially, a random effects model for failure time outcomes. In this model, the latent frailty shared by individual members in a cluster acts multiplicatively as a factor on the hazard function and is typically modelled parametrically. One commonly used distribution is gamma, where both shape and scale parameters are set to be the same to allow for unique identification of baseline hazard function. It is popular because it is a conjugate prior, and the posterior distribution possesses the same form as gamma. In addition, the parameter can be interpreted as a time-independent cross-ratio function, a natural extension of odds ratio to failure time outcomes. In this paper, we study the effect of frailty distribution mis-specification on the marginal regression estimates and hazard functions under assumed gamma distribution with an application to family studies. The simulation results show that the biases are generally 10% and lower, even when the true frailty distribution deviates substantially from the assumed gamma distribution. This suggests that the gamma frailty model can be a practical choice in real data analyses if the regression parameters and marginal hazard function are of primary interest and individual cluster members are exchangeable with respect to their dependencies.

show abstract

Section: An Estimation Procedures For Retrospective Correlated Failurementioning

confidence: 83%

Section: An Estimation Procedures For Retrospective Correlated Failurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On robustness of marginal regression coefficient estimates and hazard functions in multivariate survival analysis of family data when the frailty distribution is mis‐specified

Hsu

Gorfine

Malone

2007

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…Shih and Chatterjee (2001) developed a similar estimation procedure but leave the baseline hazard function unspecified. Hsu et al (2004) proposed a two-stage estimation procedure. At the first stage, we estimate the dependence parameter in the distribution for the risk heterogeneity without obtaining the marginal distribution first or simultaneously.…”

Section: Familiar Aggregation Based On Case-control Family Designmentioning

confidence: 99%

Survival Analysis Methods in Genetic Epidemiology

Li¹

2007

Current Topics in Human Genetics

View full text Add to dashboard Cite

Mapping genes for complex human diseases is a challenging problem due to the fact that many such diseases are due to both genetic and enviromental risk factors and many also exhibit phenotypic heterogeneity, such as variable age of onset. Information on variable age of disease onset is often a good indicator for disease heterogeneity and incorporation of such information together with enviromental risk factors into genetic analysis should lead to more powerful tests for genetic analysis. Due to the problem of censoring, survival analysis methods have proved to be very useful for genetic analysis. In this paper, I review some recent methodological developments on integrating modern survival analysis methods and human genetics in order to rigorously incorporate both age of onset and enviromental covariates data into aggregation analysis, segregation analysis, linkage analysis, association analysis and gene risk characterization. I also briefly discuss the issue of ascertainment correction and survival analysis methods for high-dimensional genomic data. Finally, I outline several areas that need further methodological developments. Survival Analysis Methods in Genetic Epidemiology AbstractMapping genes for complex human diseases is a challenging problem due to the fact that many such diseases are due to both genetic and environmental risk factors and many also exhibit phenotypic heterogeneity, such as variable age of onset. Information on variable age of disease onset is often a good indicator for disease heterogeneity and incorporation of such information together with environmental risk factors into genetic analysis should lead to more powerful tests for genetic analysis. Due to the problem of censoring, survival analysis methods have proved to be very useful for genetic analysis. In this paper, I review some recent methodological developments on integrating modern survival analysis methods and human genetics in order to rigorously incorporate both age of onset and environmental covariates data into aggregation analysis, segregation analysis, linkage analysis, association analysis and gene risk characterization. I also briefly discuss the issue of ascertainment correction and survival analysis methods for high-dimensional genomic data. Finally, I outline several areas that need further methodological developments.

show abstract

“…The frequency of breast cancer was elevated albeit only marginally significant (five observed, 1.94 expected, SIR ¼ 2.58; 95% CI: 0.84-6.0; two-sided P ¼ 0.09). Although these estimates of risk are in part naïve, as we have made no adjustment for familial relationships, 7 and hence confidence limits given may be too narrow, they serve to emphasize the over-representation of lymphoproliferative diseases and breast cancer in the family. The other nonhaematological cancers were not significantly different to those expected.…”

Section: Com)mentioning

confidence: 99%