Core procedure of floodgate

This function produces floodgate LCBs for given fitted mu.

fg.inference(
  S,
  mu_X,
  mu_Xk,
  Y,
  V_mean = NULL,
  useMC = TRUE,
  one.sided = TRUE,
  alevel = 0.05,
  test = "z",
  verbose = TRUE
)

Arguments

S	a list of selected variables.
mu_X	a list of kength |S|, whose element is the matrix of mu(X) with dimension n2-by-1.
mu_Xk	a list of kength |S|, whose element is the matrix of mu(Xk) with dimension n2-by-K or n2-by-1.
Y	a n2 by 1 matrix, containing the response variables of the inferene samples.
V_mean	A vector of length |S|, whose element is the expected conditional variance term Var(Xj |X-j).
useMC	whether to use Monte Carlo estimators of the conditional quantities (default: TRUE).=
one.sided	whether to obtain LCB or p-values via the one-sided way (default: TRUE).
alevel	confidence level (defaul: 0.05).
test	type of the hypothesis test (defaul: "z").
verbose	whether to show intermediate progress (default: FALSE).

Value

A list of three objects. inf.out: a matrix of |S|-by-4, containing the p-values, LCI, UCI and the floodgate LCB for variable in S; S: a list of selected variables.

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(), fit.mu(), floodgate.binary(), floodgate(), inference_general()