DataLab is a compact statistics package aiming at exploratory data analysis. Please visit the DataLab Web site for more information....


Contingency Analysis

Command: Math -> Bivariate Statistics -> Contingency Analysis...


The contingency analysis calculates the contingency table of two categorical variables and several parameters derived from it:
Pearson's Chi2 (c2) is a statistical test applied to categorical variables to evaluate how likely it is that any observed difference between the variables arose by chance.
Cramer's V (sometimes referred to as Cramer's phi and denoted as fc) is a measure of association between two nominal variables, giving a value between 0 and +1.
The contingency coefficient is a coefficient of association that tells whether two variables are independent of each other.
The lambda coefficient is a measure of the strength of association of the cross tabulations when the variables are measured at the nominal level.
The Rand index (named after William M. Rand) is a measure of the similarity between two data clusterings.
The adjusted Rand index is the corrected-for-chance version of the Rand index.
The following statistical characteristics are calculated only for 2x2 contingency tables:
P.'s Chi2 (Yates corr.) displays Pearson's chi-squared test including the Yates correction
Phi is a simple measure of association whose valid range is between 0 (no association) and +1 (high association).
p(Contingency Table) denotes the probability that the current contingency table occurs under the condition that the margin sums are constant.
Fisher's Exact Test provides the probability that the current contingency table or a more extreme table occurs (again under the condition that the margin sums are constant).

How To:
  1. Load the both (ordinal or nominal) variables which are to be analysed
  2. Depending on the size of the contingency table all or part of the above-mentioned parameters are displayed