pcMI {micd}

Estimate the Equivalence Class of a DAG Using the PC-MI Algorithm for Multiple Imputed Data Sets

Description

This function is a modification of pcalg::pc() to be used for multiple imputation.

Usage

pcMI(
  data,
  alpha,
  labels,
  p,
  fixedGaps = NULL,
  fixedEdges = NULL,
  NAdelete = TRUE,
  m.max = Inf,
  u2pd = c("relaxed", "rand", "retry"),
  skel.method = c("stable", "original"),
  conservative = FALSE,
  maj.rule = FALSE,
  solve.confl = FALSE,
  verbose = FALSE
)

Arguments

data

An object of type mids, which stands for 'multiply imputed data set', typically created by a call to function mice()

alpha

Significance level (number in (0,1) for the conditional independence tests

labels

(Optional) character vector of variable (or "node") names. Typically preferred to specifying p.

p

(Optional) number of variables (or nodes). May be specified if labels are not, in which case labels is set to 1:p.

fixedGaps

A logical matrix of dimension p*p. If entry [i,j] or [j,i] (or both) are TRUE, the edge i-j is removed before starting the algorithm. Therefore, this edge is guaranteed to be absent in the resulting graph.

fixedEdges

A logical matrix of dimension p*p. If entry [i,j] or [j,i] (or both) are TRUE, the edge i-j is never considered for removal. Therefore, this edge is guaranteed to be present in the resulting graph

NAdelete

If indepTest returns NA and this option is TRUE, the corresponding edge is deleted. If this option is FALSE, the edge is not deleted.

m.max

Maximal size of the conditioning sets that are considered in the conditional independence tests.

u2pd

String specifying the method for dealing with conflicting information when trying to orient edges (see details below).

skel.method

Character string specifying method; the default, "stable" provides an order-independent skeleton, see pcalg::skeleton() for details.

conservative

Logical indicating if the conservative PC is used. See pcalg::pc() for details.

maj.rule

Logical indicating that the triples shall be checked for ambiguity using a majority rule idea, which is less strict than the conservative PC algorithm. For more information, see pcalg::pc().

solve.confl

See pcalg::pc() for more details.

verbose

If TRUE, detailed output is provided.

Details

An object of class "pcAlgo" (see pcAlgo) containing an estimate of the equivalence class of the underlying DAG.

Value

See pcalg::pc() for more details.

Note

This is a modified function of pcalg::pc() from the package 'pcalg' (Kalisch et al., 2012; http://www.jstatsoft.org/v47/i11/).

Author(s)

Original code by Markus Kalisch, Martin Maechler, and Diego Colombo. Modifications by Ronja Foraita.

Examples

daten <- mice::ampute(windspeed)$amp

## Impute missing values
imp <- mice(daten)
pcMI(data = imp, label = colnames(imp$data), alpha = 0.01)