generalBootstrap: Abstract class of bootstrap

In wilsoncai1992/TMLEbootstrap: Bootstrap Confidence Intervals for Targeted Maximum Likelihood Estimators

Description

Abstract class of bootstrap

Abstract class of bootstrap

Details

Output both the point estimate and the bootstrap confidence interval

Methods

Public methods

• generalBootstrap$new()

• generalBootstrap$bootstrap()

• generalBootstrap$exact_bootstrap()

• generalBootstrap$exact_bootstrap_paper()

• generalBootstrap$center_CI()

• generalBootstrap$scale_adjust_CI()

• generalBootstrap$penalized_CI()

• generalBootstrap$penalized_CI_half()

• generalBootstrap$shift2()

• generalBootstrap$sigma_mse()

• generalBootstrap$spread()

• generalBootstrap$all_boot_CI()

• generalBootstrap$clone()

---

Method new()

Usage

generalBootstrap$new()

---

Method bootstrap()

regular bootstrap

Usage

generalBootstrap$bootstrap(n_bootstrap, alpha = 0.05, ...)

Arguments

n_bootstrap

number of bootstrap samples

alpha

significance level for CI

...

other passed to "run_bootstrap"

Returns

NULL

---

Method exact_bootstrap()

exact bootstrap

Usage

generalBootstrap$exact_bootstrap(n_bootstrap, alpha = 0.05, ...)

Arguments

n_bootstrap

number of bootstrap samples

alpha

significance level for CI

...

other passed to "run_bootstrap"

Returns

NULL

---

Method exact_bootstrap_paper()

exact bootstrap on vdl paper

Usage

generalBootstrap$exact_bootstrap_paper(n_bootstrap, alpha = 0.05, ...)

Arguments

n_bootstrap

number of bootstrap samples

alpha

significance level for CI

...

other passed to "run_bootstrap"

Returns

NULL

---

Method center_CI()

center the bootstrap CI on the point estimate

Usage

generalBootstrap$center_CI(bootCI = NULL)

Arguments

bootCI

the vector of CI

Returns

NULL

---

Method scale_adjust_CI()

scale the bootstrap CI to be wider than Wald CI

Usage

generalBootstrap$scale_adjust_CI(bootCI = NULL)

Arguments

bootCI

the vector of CI

Returns

NULL

---

Method penalized_CI()

bias penalized bootstrap

add abs(bias) to both sides of the bootstrap CI (wider)

Usage

generalBootstrap$penalized_CI(bootCI = NULL)

Arguments

bootCI

the vector of CI

Returns

NULL

---

Method penalized_CI_half()

bias penalized bootstrap (half)

add 0.5*abs(bias) to both sides of the bootstrap CI (wider)

Usage

generalBootstrap$penalized_CI_half(bootCI = NULL)

Arguments

bootCI

the vector of CI

Returns

NULL

---

Method shift2()

two bias shifted bootstrap

shift the center of CI by two times the bias

Usage

generalBootstrap$shift2(bootCI = NULL)

Arguments

bootCI

the vector of CI

Returns

NULL

---

Method sigma_mse()

use the stddev of bootstrap samples, to put a Normal CI around point estimate

Usage

generalBootstrap$sigma_mse(bootCI = NULL)

Arguments

bootCI

the vector of CI

Returns

CI

---

Method spread()

use the z-quantiles of bootstrap samples, to put a Normal CI around point estimate

Usage

generalBootstrap$spread(bootCI = NULL)

Arguments

bootCI

the vector of CI

Returns

CI

---

Method all_boot_CI()

return all CI

Usage

generalBootstrap$all_boot_CI()

Returns

list of CI

---

Method clone()

The objects of this class are cloneable with this method.

Usage

generalBootstrap$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

wilsoncai1992/TMLEbootstrap documentation built on Feb. 27, 2021, 7:57 a.m.