dataFrame.columns.stat — anova()

Description

The anova() method of the stat object performs a one-way analysis of variance (ANOVA) on the selected columns.

Signature

dataFrame.columns(...columnNames).stat.anova({ mode: 'welch' })
Scope
columns
Family
stat
Returns
object

Arguments

...columnNames ( string[] )
The name of the columns from which to compute ANOVA.
options (object)
ANOVA options.

Option

mode (string)
The ANOVA method to use.
  • fisher
  • welch (default)

Returns

stat ( object[] )
A statistic object containing the ANOVA test results.
F_stat (number)
The F statistic.
p_value (number)
The p-value associated with the test.
eta_squared (number)
The proportion of variance explained by group membership.
omega_squared (number)
The estimated proportion of variance explained by group membership in the population.
df_between (number)
The between-groups degrees of freedom.
df_within (number)
The within-groups degrees of freedom.

Notes

  • The fisher mode performs the classical one-way ANOVA assuming equal variances across groups.
  • The welch mode performs Welch's ANOVA and does not assume equal variances across groups.
  • The null hypothesis states that all group means are equal.
  • etaSquared (η²) is an effect size measure representing the proportion of variance explained by the grouping variable.
  • omegaSquared (ω²) is a less biased effect size measure that estimates the proportion of variance explained in the population.
  • Larger values of etaSquared and omegaSquared indicate a stronger effect of group membership on the observed values.

Example

// test the values of 3 columns of the dataFrame
var stat = dataFrame.columns('groupA', 'groupB', 'groupC').stat.anova();

// log the stat details
notebook.log(stat);