Skip to main content

Table 2 Degrees of freedom associated with common statistical tests.

From: The problem of pseudoreplication in neuroscientific studies: is it affecting your analysis?

Test Degrees of Freedom
T-test  
   Independent n1 + n2 - 2
   Paired n - 1
One-way ANOVA G - 1 and n - G
Two-way Anova  
   Main effect of A G A -1
   Main effect of B G B -1
   A × B interaction (GA -1)(GB -1)
   Error n - G A G B
One-way RM-Anova  
   Between subjects G - 1
   Error (n -1)(G -1)
Two-way Mixed ANOVA  
   Between subjects n(G - 1)
Groups    G-1
Error    G(n-1)
   Within subjects N - nG
Obs    Obs - 1
Group × Obs Interaction    (G - 1)(Obs - 1)
Error    N - nG - G (Obs - 1)
Linear Regression 1 and n - 2
Chi-square (R - 1)(C -1)
  1. n1 = sample size of group one; n2 = sample size of group two; n = total sample size; N = total number of observations (equal to n × Obs); G = number of groups; G A = number of groups for Factor A; G B = number of groups for Factor B; Obs = number of repeated observations on the same subject; R = number of rows; C = number or columns. † "Mixed" refers to the presence of both between and within subjects effects, and should not be confused with mixed effects models described in the text.