Find Significant Rules
Provides the generic functions and the S4 method is.significant
to find significant associations and an implementation for rules.
is.significant(x, transactions, method = "fisher", alpha = 0.01, adjust = "bonferroni")
x |
a set of rules. |
transactions |
set of transactions used to mine the rules. |
method |
test to use. Options are
|
alpha |
required significance level. |
adjust |
method to adjust for multiple comparisons. Options are
|
The implementation for association rules uses Fisher's exact test with correction for multiple comparisons to test the null hypothesis that the LHS and the RHS of the rule are independent. Significant rules have a p-value less then the specified significance level alpha (the null hypothesis of independence is rejected.).
returns a logical vector indicating which rules are significant.
Michael Hahsler
Hahsler, Michael and Kurt Hornik (2007). New probabilistic interest measures for association rules. Intelligent Data Analysis, 11(5):437–455.
data("Income") rules <- apriori(Income, parameter = list(support = 0.5)) is.significant(rules, Income) inspect(rules[is.significant(rules, Income)])
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.