ci.test: Independence and Conditional Independence Tests

Description

Perform either an independence test or a conditional independence test.

Usage

## S3 method for class 'character':
ci.test(x, y = NULL, z = NULL, data, test = NULL,
  B = NULL, debug = FALSE, ...)
## S3 method for class 'data.frame':
ci.test(x, test = NULL, B = NULL, debug = FALSE, ...)
## S3 method for class 'numeric':
ci.test(x, y = NULL, z = NULL, test = NULL,
  B = NULL, debug = FALSE, ...)
## S3 method for class 'factor':
ci.test(x, y = NULL, z = NULL, test = NULL,
  B = NULL, debug = FALSE, ...)
## S3 method for class 'default':
ci.test(x, ...)

Arguments

a character string (the name of a variable), a data frame, a numeric vector or a factor object.

a character string (the name of another variable), a numeric vector or a factor object.

a vector of character strings (the names of the conditioning variables), a numeric vector, a factor object or a data frame. If NULL an independence test will be executed.

data

a data frame containing the variables to be tested.

test

a character string, the label of the conditional independence test to be used in the algorithm. If none is specified, the default test statistic is the mutual information for discrete data sets and the linear correlation

a positive integer, the number of permutations considered for each permutation test. It will be ignored with a warning if the conditional independence test specified by the test argument is not a permutation test.

debug

a boolean value. If TRUE a lot of debugging output is printed; otherwise the function is completely silent.

...

extra arguments from the generic method (currently ignored).

Value

An object of class htest containing the following components:
statisticthe value the test statistic.
parameterthe degrees of freedom of the approximate chi-squared or t distribution of the test statistic; the number of permutationscomputed by Monte Carlo tests. Semiparametric tests have both.
p.valuethe p-value for the test.
methoda character string indicating the type of test performed, and whether Monte Carlo simulation or continuity correction was used.
data.namea character string giving the name(s) of the data.
null.valuethe value of the test statistic under the null hypothesis, always 0.
alternativea character string describing the alternative hypothesis

References

Edwards DI (2000). Introduction to Graphical Modelling. Springer, 2nd edition.

Hausser J, Strimmer K (2009). "Entropy inference and the James-Stein estimator, with application to nonlinear gene association networks". Statistical Applications in Genetics and Molecular Biology, 10, 1469-1484.

Ledoit O, Wolf M (2003). "Improved Estimation of the Covariance Matrix of Stock Returns with an Application to Portfolio Selection". Journal of Empirical Finance, 10, 603-621.

Legendre P (2000). "Comparison of Permutation Methods for the Partial Correlation and Partial Mantel Tests". Journal of Statistical Computation and Simulation, 67, 37-73.

Tsamardinos I, Borboudakis G (2010). "Permutation Testing Improves Bayesian Network Learning". In "Machine Learning and Knowledge Discovery in Databases", pp. 322-337. Springer.

Examples

Run this code

data(gaussian.test)
data(learning.test)

# using a data frame and column labels.
ci.test(x = "F" , y = "B", z = c("C", "D"), data = gaussian.test)
#
#	 Pearson's Linear Correlation
#
# data:  F ~ B | C + D
# cor = -0.1275, df = 4996, p-value < 2.2e-16
# alternative hypothesis: true value is not equal to 0

# using a data frame.
ci.test(gaussian.test)
#
#	 Pearson's Linear Correlation
#
# data:  A ~ B | C + D + E + F + G
# cor = -0.5654, df = 4993, p-value < 2.2e-16
# alternative hypothesis: true value is not equal to 0

# using factor objects.
attach(learning.test)
ci.test(x = F , y = B, z = data.frame(C, D))
#
# 	Mutual Information (discrete)
#
# data:  F ~ B | data.frame(C, D)
# mi = 25.2664, df = 18, p-value = 0.1178
# alternative hypothesis: true value is greater than 0