Jackknife-based Inference

Abstract class for delete-1 jackknife estimate correction and jackknife-Wald inference layered on top of bootstrap-capable inference classes.

Super classes

Inference -> InferenceRand -> InferenceRandCI -> InferenceNonParamBootstrap -> InferenceRandBootstrap -> InferenceRandBootstrapCI -> InferenceBayesianBootstrap -> InferenceJackknife

Methods

Public methods

• InferenceJackknife$approximate_jackknife_distribution_beta_hat_T()

• InferenceJackknife$compute_jackknife_estimate()

• InferenceJackknife$compute_jackknife_bias_estimate()

• InferenceJackknife$compute_jackknife_std_error()

• InferenceJackknife$compute_jackknife_wald_two_sided_pval()

• InferenceJackknife$compute_jackknife_wald_confidence_interval()

• InferenceJackknife$clone()

+ inherited public methods from InferenceBayesianBootstrap

• InferenceBayesianBootstrap$approximate_bayesian_bootstrap_distribution_beta_hat_T()
• InferenceBayesianBootstrap$compute_bayesian_bootstrap_confidence_interval()
• InferenceBayesianBootstrap$compute_bayesian_bootstrap_two_sided_pval()
• InferenceBayesianBootstrap$compute_estimate_with_bootstrap_weights()
• InferenceBayesianBootstrap$get_supported_bayesian_bootstrap_ci_types()
• InferenceBayesianBootstrap$get_supported_bayesian_bootstrap_pval_types()

+ inherited public methods from InferenceRandBootstrapCI

• InferenceRandBootstrapCI$compute_rand_bootstrap_confidence_interval()
• InferenceRandBootstrapCI$get_supported_rand_bootstrap_ci_types()

+ inherited public methods from InferenceRandBootstrap

• InferenceRandBootstrap$approximate_rand_bootstrap_distribution_beta_hat_T()
• InferenceRandBootstrap$compute_rand_bootstrap_two_sided_pval()
• InferenceRandBootstrap$get_supported_rand_bootstrap_pval_types()

+ inherited public methods from InferenceNonParamBootstrap

• InferenceNonParamBootstrap$approximate_bootstrap_distribution_beta_hat_T()
• InferenceNonParamBootstrap$approximate_m_out_of_n_bootstrap_distribution_beta_hat_T()
• InferenceNonParamBootstrap$approximate_subsampling_distribution_beta_hat_T()
• InferenceNonParamBootstrap$compute_bootstrap_confidence_interval()
• InferenceNonParamBootstrap$compute_bootstrap_two_sided_pval()
• InferenceNonParamBootstrap$compute_m_out_of_n_bootstrap_confidence_interval()
• InferenceNonParamBootstrap$compute_m_out_of_n_bootstrap_two_sided_pval()
• InferenceNonParamBootstrap$compute_subsampling_confidence_interval()
• InferenceNonParamBootstrap$compute_subsampling_sensitivity()
• InferenceNonParamBootstrap$compute_subsampling_two_sided_pval()
• InferenceNonParamBootstrap$get_supported_bootstrap_ci_types()
• InferenceNonParamBootstrap$get_supported_bootstrap_pval_types()
• InferenceNonParamBootstrap$select_optimal_b_subsampling()
• InferenceNonParamBootstrap$select_optimal_m_out_of_n_bootstrap()

+ inherited public methods from InferenceRandCI

• InferenceRandCI$compute_rand_confidence_interval()
• InferenceRandCI$compute_rand_two_sided_pval()

+ inherited public methods from InferenceRand

• InferenceRand$approximate_randomization_distribution_beta_hat_T()
• InferenceRand$set_custom_randomization_statistic_cpp()
• InferenceRand$set_custom_randomization_statistic_function()
• InferenceRand$supports_rand_pval_for_incidence()

+ 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()

---

InferenceJackknife$approximate_jackknife_distribution_beta_hat_T()

Returns the leave-one-out jackknife estimate distribution.

Usage

InferenceJackknife$approximate_jackknife_distribution_beta_hat_T(unit = "auto")

Arguments

unit

Deletion unit. Default `\"auto\"`, which chooses a design-aware unit automatically.

Returns

A numeric vector of jackknife replicate estimates.

---

InferenceJackknife$compute_jackknife_estimate()

Computes the delete-1 jackknife bias-corrected treatment estimate.

For blocking designs, this uses leave-one-block-out deletion units. For matching designs, it uses leave-match-out deletion units. For KK designs, it uses leave-match-out for matched pairs and leave-one-out for reservoir subjects.

Usage

InferenceJackknife$compute_jackknife_estimate(unit = "auto")

Arguments

unit

Deletion unit. Default `\"auto\"`, which chooses a design-aware unit automatically.

Returns

A numeric jackknife bias-corrected treatment estimate.

---

InferenceJackknife$compute_jackknife_bias_estimate()

Computes the jackknife bias estimate.

Usage

InferenceJackknife$compute_jackknife_bias_estimate(unit = "auto")

Arguments

unit

Deletion unit. Default `\"auto\"`.

Returns

A numeric jackknife bias estimate.

---

InferenceJackknife$compute_jackknife_std_error()

Computes the delete-1 jackknife standard error.

For blocking designs, this uses leave-one-block-out deletion units. For matching designs, it uses leave-match-out deletion units. For KK designs, it uses leave-match-out for matched pairs and leave-one-out for reservoir subjects.

Usage

InferenceJackknife$compute_jackknife_std_error(unit = "auto")

Arguments

unit

Deletion unit. Default `\"auto\"`, which chooses a design-aware unit automatically.

Returns

A numeric jackknife standard error.

---

InferenceJackknife$compute_jackknife_wald_two_sided_pval()

Computes a two-sided Wald p-value using the jackknife estimate and jackknife standard error.

For blocking designs, this uses leave-one-block-out deletion units. For matching designs, it uses leave-match-out deletion units. For KK designs, it uses leave-match-out for matched pairs and leave-one-out for reservoir subjects.

Usage

InferenceJackknife$compute_jackknife_wald_two_sided_pval(
  delta = 0,
  unit = "auto"
)

Arguments

delta

Null treatment-effect value. Default 0.

unit

Deletion unit. Default `\"auto\"`, which chooses a design-aware unit automatically.

Returns

A two-sided jackknife-Wald p-value.

---

InferenceJackknife$compute_jackknife_wald_confidence_interval()

Computes a normal-approximation confidence interval using the jackknife estimate and jackknife standard error.

For blocking designs, this uses leave-one-block-out deletion units. For matching designs, it uses leave-match-out deletion units. For KK designs, it uses leave-match-out for matched pairs and leave-one-out for reservoir subjects.

Usage

InferenceJackknife$compute_jackknife_wald_confidence_interval(
  alpha = 0.05,
  unit = "auto"
)

Arguments

alpha

Significance level. Default 0.05.

unit

Deletion unit. Default `\"auto\"`, which chooses a design-aware unit automatically.

Returns

A jackknife-Wald confidence interval.

---

InferenceJackknife$clone()

The objects of this class are cloneable with this method.

Usage

InferenceJackknife$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.