Multiple Comparisons by the Student–Newman–Keuls Test

  The Student–Newman–Keuls (SNK) test is a post-hoc procedure similar to Tukey’s test, based on the same studentized range distribution. However, it is more conservative in detecting statistically significant differences (i.e., it rejects the null hypothesis less frequently).

1 Equation:

\[ dm = q_{\alpha, k, gl} \sqrt{\frac{qmr}{r}} \]

Where

dm = critical difference

gl = degrees of freedom of the sample (n − k);

k = number of groups;

r = number of observations per group;

qmr = mean square of residuals;

q = studentized range statistic (critical q value).

  The SNK procedure differs from Tukey’s test by applying an ordered ranking of the group means (ascending order in the present program) and performing specific pairwise comparisons according to that ranking. As with Tukey’s test (and other post-hoc procedures), SNK is performed after an ANOVA.

2 Files:

  1. SNK1matrix program, critical q table, and 1ANAVA1matrix
  2. Program source code
  3. Critical q values table

3 Usage and example

# Input:
1. Enter the data matrix (column vectors);
2. Run the program "1ANAVA1matrix" from the main page ("hp50");
3. Run the program "SNK1matrix".

# Output:
1. "qcrit5%" – critical value of the q distribution;
2. "dm" – minimum significant difference;
3. Matrix containing comparison values for each pair of groups.


  Pairs are considered significantly different when:

\[ \Delta AB > dm \]

(a) Insertion of data matrix.
(b) ANOVA results.
(c) SNK test results.
(d) Pairwise comparison matrix. The group identifiers A and B appear on the left (not visible in the image).
Figure 1: SNK1matrix program running on the Android version of the HP50G calculator (Go49gp), showing data input, ANOVA output, SNK results, and the pairwise comparison worksheet. The matrix contains columns for A, B, values of \(\Delta AB\), and corresponding comparison thresholds.


  The results match those reported in the reference source, considering the ranking of treatments (Vieira, 2016).

4 References:

  1. Vieira, Sônia. 2016. Blospot. Accessed Feb 12, 2026.
Back to top