Obtain the floodgate LCB using the Delta method

This function produces floodgate LCB using the Delta method.

inference_general(
  R,
  V = NULL,
  V_mean = NULL,
  alevel = 0.05,
  test = "z",
  one.sided = TRUE
)

Arguments

R

a vector of length n2, corresonding the term in the paper.
V

a vector of length n2, corresonding the term in the paper (defaul: NULL).
V_mean

the expected conditional variance term Var(Xj |X-j) (defaul: NULL).
alevel

confidence level (defaul: 0.05).
test

type of the hypothesis test (defaul: "z").
one.sided

whether to obtain LCB or p-values via the one-sided way (default: TRUE).

Value

A vector of length 4: p-value, LCI, UCI and LCB.

References

Zhang L, Janson L (2020). “Floodgate: Inference for Model-Free Variable Importance.” arXiv preprint arXiv:2007.01283.

See also

Other methods: calculate.V_mean(), calulate.mu_Xk(), fg.inference.binary(), fg.inference(), fit.mu(), floodgate.binary(), floodgate()