LWA-style Marginal Cox IVWC Compound Inference for KK Designs

Fits a compound (IVWC) estimator for KK matching-on-the-fly designs with survival responses: matched pairs are analyzed with a marginal Cox model \(\lambda(t \mid w) = \lambda_0(t)\exp(\beta_T w)\) whose robust variance uses the Lee-Wei-Amato (1992) cluster-robust sandwich (treating each matched pair as an independent cluster of correlated failure times), while reservoir subjects are analyzed with a standard (independent-subjects) Cox partial likelihood; the two log-hazard-ratio estimates are then combined by inverse-variance weighting. likelihood_tier = "partial" (Cox partial likelihood), but likelihood-ratio/score/gradient tests are not exposed on this IVWC compound (only on the OneLik sibling, which fits one combined partial likelihood across both sources instead of pooling two separate fits).

Details

Legacy class. Not fully tested in comprehensive_tests.R.

References

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 -> InferenceSurvivalKKLWACoxPHIVWC

Methods

Public methods

• InferenceSurvivalKKLWACoxPHIVWC$set_custom_randomization_statistic_function()

• InferenceSurvivalKKLWACoxPHIVWC$set_custom_randomization_statistic_cpp()

• InferenceSurvivalKKLWACoxPHIVWC$approximate_randomization_distribution_beta_hat_T()

• InferenceSurvivalKKLWACoxPHIVWC$supports_rand_pval_for_incidence()

• InferenceSurvivalKKLWACoxPHIVWC$compute_rand_two_sided_pval()

• InferenceSurvivalKKLWACoxPHIVWC$clone()

+ 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()

---

InferenceSurvivalKKLWACoxPHIVWC$set_custom_randomization_statistic_function()

Usage

InferenceSurvivalKKLWACoxPHIVWC$set_custom_randomization_statistic_function(
  custom_randomization_statistic_function
)

---

InferenceSurvivalKKLWACoxPHIVWC$set_custom_randomization_statistic_cpp()

Usage

InferenceSurvivalKKLWACoxPHIVWC$set_custom_randomization_statistic_cpp(fn)

---

InferenceSurvivalKKLWACoxPHIVWC$approximate_randomization_distribution_beta_hat_T()

Usage

InferenceSurvivalKKLWACoxPHIVWC$approximate_randomization_distribution_beta_hat_T(
  r = 501,
  delta = 0,
  transform_responses = "none",
  show_progress = TRUE,
  permutations = NULL,
  debug = FALSE,
  zero_one_logit_clamp = .Machine$double.eps
)

---

InferenceSurvivalKKLWACoxPHIVWC$supports_rand_pval_for_incidence()

Usage

InferenceSurvivalKKLWACoxPHIVWC$supports_rand_pval_for_incidence()

---

InferenceSurvivalKKLWACoxPHIVWC$compute_rand_two_sided_pval()

Usage

InferenceSurvivalKKLWACoxPHIVWC$compute_rand_two_sided_pval(
  r = 501,
  delta = 0,
  transform_responses = "none",
  na.rm = TRUE,
  show_progress = TRUE,
  permutations = NULL,
  zero_one_logit_clamp = .Machine$double.eps
)

---

InferenceSurvivalKKLWACoxPHIVWC$clone()

The objects of this class are cloneable with this method.

Usage

InferenceSurvivalKKLWACoxPHIVWC$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# \donttest{
seq_des = DesignSeqOneByOneKK14$new(n = 10, response_type = 'survival')
for (i in 1:10) {
  seq_des$add_one_subject_to_experiment_and_assign(data.frame(x1 = rnorm(1), x2 = rnorm(1)))
}
seq_des$add_all_subject_responses(runif(10))
inf = InferenceSurvivalKKLWACoxPHIVWC$new(seq_des)
inf$compute_estimate()
#> [1] 0.8178309
# }