micd (version 1.1.1)

disCItwd: G square Test for (Conditional) Independence between Discrete Variables with Missings

Description

A wrapper for pcalg::disCItest, to be used within pcalg::skeleton, pcalg::pc or pcalg::fci when the data contain missing values. Observations where at least one of the variables involved in the test is missing are deleted prior to performing the test (test-wise deletion).

Usage

disCItwd(x, y, S = NULL, suffStat)

Value

A p-value.

Arguments

x, y, S

(Integer) position of variable X, Y and set of variables S, respectively, in suffStat. It is tested whether X and Y are conditionally independent given the subset S of the remaining variables.

suffStat

A list with three elements, "dm", "nlev", "adaptDF"; each corresponding to the above arguments. Can be obtained from a data.frame of factor variables using the suffStat function (see example section)

Details

See disCItest for details on the G square test. Test-wise deletion is valid if missingness does not jointly depend on X and Y.

See Also

pcalg::disCItest for complete data, disMItest for multiply imputed data

Examples

## load data (200 observations)
data(gmD)
dat <- gmD$x[1:1000,]

## delete some observations of X2 and X3
set.seed(123)
dat[sample(1:1000, 50), 2] <- NA
dat[sample(1:1000, 50), 3] <- NA

## analyse incomplete data
# test-wise deletion ==========
sufftwd <- getSuff(dat, test = "disCItwd")
disCItwd(1, 3, NULL, suffStat = sufftwd)

# list-wise deletion ==========
dat2 <- dat[complete.cases(dat), ]
suffStat2 <- getSuff(dat2, test = "disCItest", adaptDF = FALSE)
disCItest(1, 3, NULL, suffStat = suffStat2)

## use disCItwd within pcalg::pc ==========
pc.fit <- pc(suffStat = sufftwd, indepTest = disCItwd, alpha = 0.1, p = 5)
pc.fit

if (requireNamespace("Rgraphviz", quietly = TRUE))
plot(pc.fit)