Stratified Cox / Standard Cox Compound Inference for KK Designs
Source:R/inference_survival_KK_strat_cox.R
InferenceSurvivalKKStratCoxPHIVWC.RdThis class implements a compound estimator for KK matching-on-the-fly designs with survival responses. For matched pairs, it uses stratified Cox proportional hazards regression (each pair is a stratum). For reservoir subjects, it uses standard Cox regression. The two estimates (both log-hazard ratios) are combined via a variance-weighted linear combination.
Details
Under harden = TRUE, multivariate fits preserve the treatment column and
progressively retry reduced covariate sets after QR-based rank reduction and
correlation-based pruning. Extreme finite coefficients / standard errors are
rejected and treated as non-estimable.
The matched-pair sub-estimate treats each pair as its own stratum (a pair-specific baseline hazard, exactly canceling shared-frailty effects within the pair via Cox's partial likelihood) and is a special case of the Lee-Wei-Amato (1992) large-numbers-of-small-groups stratified Cox approach; the reservoir sub-estimate is a standard unstratified Cox partial-likelihood fit (Cox 1972). The two log-hazard-ratio estimates are combined by inverse-variance weighting, the same rule used throughout the KK IVWC family.
Legacy class. Not fully tested in comprehensive_tests.R.
References
Cox, D. R. (1972). "Regression Models and Life-Tables." Journal of the Royal Statistical Society, Series B, 34(2), 187-220.
Lee, E. W., Wei, L. J., and Amato, D. A. (1992). "Cox-Type Regression Analysis for Large Numbers of Small Groups of Correlated Failure Time Observations." In Survival Analysis: State of the Art, 237-247. Springer. doi:10.1007/978-94-015-7983-4_14
Super class
Inference -> InferenceSurvivalKKStratCoxPHIVWC
Methods
Public methods
InferenceSurvivalKKStratCoxPHIVWC$set_custom_randomization_statistic_function()InferenceSurvivalKKStratCoxPHIVWC$set_custom_randomization_statistic_cpp()InferenceSurvivalKKStratCoxPHIVWC$approximate_randomization_distribution_beta_hat_T()InferenceSurvivalKKStratCoxPHIVWC$supports_rand_pval_for_incidence()InferenceSurvivalKKStratCoxPHIVWC$compute_rand_two_sided_pval()
+ inherited public methods from Inference
Inference$capabilities()Inference$compute_asymp_confidence_interval()Inference$compute_asymp_two_sided_pval()Inference$compute_estimate()Inference$compute_exact_confidence_interval()Inference$compute_exact_two_sided_pval_for_treatment_effect()Inference$duplicate()Inference$get_analysis_data()Inference$get_covariates()Inference$get_design_object()Inference$get_model_formula()Inference$get_nonestimable_reason()Inference$get_nonestimable_stage()Inference$get_optimization_alg()Inference$get_response()Inference$get_response_type()Inference$get_treatment()Inference$initialize()Inference$is_nonestimable()Inference$set_optimization_alg()Inference$set_seed()Inference$supports()