Wilcoxon Signed Ranks

Test
An Alternative to the Paired Samples t

The Wilcoxon Signed Ranks

Test
The Wilcoxon test can be viewed as an
alternative to the paired samples t test
The test uses data from one sample where
each individual has been observed in two
different treatment conditions (or a matched
sample where each sample is observed
under one treatment) to test for a
significant difference between the two
treatments.

Wilcox Test, contd

P However, the Wilcoxon test does not require
that the distribution of the difference scores
be normal
< Therefore, the Wilcoxon can be significantly more
powerful than the paired t when the distribution of
difference scores is nonnormal

P The null hypothesis for the Wilcoxon test

simply states that there is no systematic or
consistent difference between the two
treatments being compared.

Ranking Difference Scores

Calculating the Wilcoxon

Test Statistic
P The calculation of the Wilcoxon T statistic
requires:
< 1. Observe the difference between treatment 1
and treatment 2 for each subject.
< 2. Rank order the absolute size of the differences
without regard to sign (increases are positive and
decreases are negative).
< 3. Find the sum of the ranks for the positive
differences and the sum of the ranks for the
negative differences.
< 4. The Wilcoxon T is the smaller of the two sums

Interpreting the Test Statistic

P If there is a consistent difference between
the two treatments, the difference scores
should be consistently positive (or
consistently negative).
< At the extreme, all the differences will be in the
same direction and one of the two sums will be
zero
If there are no negative differences then G Ranks = 0 for
the negative differences.)

P Thus, a small value for T indicates a

difference between treatments.

Evaluating the Wilcoxon Test

Statistic
P To determine whether the obtained T value
is sufficiently small to be significant, you
must consult the Wilcoxon table.
P For large samples, the obtained T statistic
can be converted to a z-score and the
critical region can be determined using the
unit normal table.

Wilcoxon Signed Ranks Example

P Dr. Brown wants to determine if reaction
times increase (when solving simple math
problems) under sleep deprivation
P Step 1:
< Ho: nsd $ sd ; H1: nsd < sd
< = .05

P Step 2:
< From Appendix B.10, a value of T less than 3 is
statistically significant at = .05

Example Data

Wilcoxon Signed Ranks Example

P +ranks = 1, -ranks = 27
P Therefore, T = 1
P Therefore, since T obtained (1) is less than T
critical (3) there is a significant decrease in
reaction times under no sleep deprivation,
relative to under sleep deprivation
P When n is large, we can use a normal
approximation of the statistic
< This z-statistic is reported by most software
packages