Odds and Risk Ratios

This node calculates the Maximum Likelihood Estimate (MLE) Odds Ratio (OR) and the Maximum Likelihood Estimate (MLE) Risk Ratio (RR), i.e., "Wald" OR and RR, from two selected categorical columns. For each column a value is selected to be considered the value under observation. All other values in non-binary categorical columns are considered as the "not" case.

X¬ XYab¬ Ycd

Odds Ratio:
OR = (a/b) / (c/d) = (a * d) / (b * c)

Risk Ratio:
RR = (a / (a+b)) / (c / (c+d))

Fisher's Exact Test is calculated with
p = (a + b)!(c + d)!(a + c)!(b + d)! / (a!b!c!d!n!), where
n = a + b + c + d
over the sum of the marginal tables.

The two-tailed, left-tailed, and right-tailed p-values are calculated. The value for the Laplace correction is not considered for this calculation.

The Chi-Squared Test ( Χ ² ) is calculated with
Χ ² = ∑ _i ∑ _j (O _ij - E _ij ) ² / E _ij ²
where
E _ij = T _i * T _j /n
and
T _i and T _j are the sums of the row and columns respectively.

Yates' Corrected Χ ² is
Χ ² _Yates = ∑ _i ∑ _j (|O _ij - E _ij |-0.5) ² / E _ij ²

Pearson's Coefficient of Contingency
Pearson's C = √Χ ² / (Χ ² + n)

Cramér's Coefficient of Contingency
Cramér's V = √Χ ² /n

Input ports

1. Type: Table
   Data
   The data table with the two features to compare.

Output ports

1. Type: Table
   Results
   The output table with the results and significance measurements.
2. Type: Table
   Contingency Table
   A table with the values from the table shown above.