Internet Learning Volume 6, Number 2, Fall 2017/Winter 2018 | Page 35
Internet Learning Journal
Table 4: Mann–Whitney U-test
Ranks
Score
Term N Mean rank Sum of ranks
0 679 406.84 276,245.00
1 121 364.92 44,155.00
Total 800
Test Statistics a
Score
Mann–Whitney U 36,774.000
Wilcoxon W 44,155.000
Z
−1.844
Asymp. Sig.
(two-tailed) .065
Again, the sig. value (0.065) is
greater than the α value (0.05), which
indicates that neither term length results
in significantly higher final exam
scores than the other. This aligns with
the descriptive statistics, such that the
mean final exam score in the 8-week
class is slightly higher (78.87) than the
mean final exam score in the 16-week
class (75.81).
The purpose of this study was to
determine if a significant difference in
final exam scores exists between students
in two different lengths of terms.
Findings from the Mann–Whitney
U-test indicate that there is not a statistically
significant difference, which
begs the question of why? What factors
would lead to this finding? Furthermore,
what are the implications for students
and universities?
Perhaps, a key indicator is the fact
that students self-select into the course,
meaning that they choose whether to
take a 16-week or 8-week class. An important
consideration is why students
choose one term over the other. Perhaps,
it is due to their schedule, where
one course fits in better (Diaz & Cartnal,
2006). Maybe it is because they perceive
one term length to be a better fit
for their current level of mathematical
knowledge (Rodrigue, Fanguy, Soule,
& Kleen, 2016). Particularly for those
34