25.07.2013 Views

July 2006 Volume 9 Number 3 - CiteSeerX

July 2006 Volume 9 Number 3 - CiteSeerX

July 2006 Volume 9 Number 3 - CiteSeerX

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

assessment proceeded until round 3 (the conceptual, logistical, physical database design and the implementation)<br />

was completed.<br />

Figure 5. The student interface in defining fuzzy constraints<br />

Pearson’s correlation analysis is adopted to compare the correlations between peer and instructor marks. Student<br />

assessments are significantly and positively correlated with the instructors’ assessments for each evaluation<br />

concept utilized in the 3 rounds of assessment (Table 2).<br />

Table 2. Correlation analysis between instructor and student marks<br />

Round 1 Round 2 Round 3<br />

Evaluation Concepts Correlation Correlation Correlation<br />

Completeness 0.457* 0.619* 0.752**<br />

Correctness 0.534* 0.745** 0.623*<br />

Originality 0.413* 0.712** 0.676*<br />

*: p < 0.05, **: p < 0.01<br />

Paired t-test analysis for performance during the three rounds indicates that the improvement in learning for the<br />

13 teams was significant (Table 3). Students improved their performance from round 1 to round 2, and especially<br />

from round 1 to round 3.<br />

Table 3. Performance analysis over the 3 rounds<br />

Round 1 and 2 Round 2 and 3 Round 1 and 3<br />

Evaluation Concepts t-value p-value t-value p-value t-value p-value<br />

Completeness 5.84 2.89E-05 0.60 0.278 5.04 1.13E-04<br />

Correctness 5.66 3.88E-05 1.25 0.116 5.25 7.82E-05<br />

Originality 4.32 4.18E-04 0.39 0.348 4.66 2.22E-04<br />

Level of significanceα =0.05<br />

Furthermore, as the difference cannot be perceived in round 1, the instructor’s assessment is utilized in round 2<br />

and round 3 to evaluate the performance of the two groups. By t-test analysis, the difference between the two<br />

groups was significant (Table 4).<br />

Table 4. Performance analysis for the two groups<br />

Round 2 Round 3<br />

Evaluation Concepts t-value p-value t-value p-value<br />

Completeness 2.02 0.029 2.24 0.019<br />

Correctness 2.47 0.012 2.38 0.014<br />

Originality 1.46 0.082 3.09 0.003<br />

Level of significanceα =0.05<br />

23

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!