The difference in mean topography test scores between the digital-map experimental group and the paper-map control group was not statistically significant¶

Claim · All claims
Evidence · 1 study · causal r1 · q2
Currency · newest study 2015 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? The experimental group's higher mean score (8.62 vs 7.31) was not statistically significant; the two-sample t-test (t = 1.901, df = 24, Sig. 2-tailed = 0.069) did not exceed the tabled critical value, so the difference could not be attributed to the new method. → Dániel Balla 2015

Evidence¶

Dániel Balla 2015¶

Dániel Balla, Marianna Zichar, Judit Boda, Tibor József Novák. (2015). Control Grouped Pedagogical Experiment to Test the Performance of Second-generation Web Maps and the Traditional Maps at the University of Debrecen. IAFOR Journal of Education, Volume III - Issue I. http://webgis.web44.net/program.php?tipus=oktato

q2 · i? · causal · r1

Statistical analysis of the controlled experiment: after a variance check (Levene's F = 1.889, Sig. 0.182), a two-sample t-test compared the 13-student groups' scores; the article reports the quoted result and mean difference of 1.308.

"Table 2. demonstrates the result of the two-sample t-test t”=1.901 (the degree of freedom is 24). The probability belonging to this value is 0.69, which means a level of 93.1%. Since the calculated t-value is less than the appropriate value from the table (ttable=2,064) we have to claim that the difference of the arithmetic means calculated from the results of the two examined samples was random and cannot be explained only by introducing the new methodology."

Discussion¶

Related Claims¶

• The experimental and control groups did not differ significantly in writing scores at pre-test, supporting attribution of post-test differences to the instructional methods — related
• The two groups did not differ significantly in writing quality before the treatment — related