A statistics instructor measured student attitudes toward a statistics course pr
ID: 3361453 • Letter: A
Question
A statistics instructor measured student attitudes toward a statistics course prior to lectures, at the midterm, and after the final test. Attitudes were measured on a 16-point scale, with higher scores indicating more positive attitudes toward the statistics course.
Student Prior to Lectures At the Midterm After the Final
A 6 5 10
B 4 10 16
C 8 7 14
D 12 13 16
E 5 6 11
Based on the results shown in the table, test whether or not attitudes differed using the Friedman test at a 0.05 level of significance. (Round your answer to two decimal places.)
X^2R =_____________
Explanation / Answer
Results:
Friedman rank sum test for multiple correlated samples in a two-way balanced complete block design
Friedman chi-squared statistic: 7.6
degrees of freedom df : 2
This is the number of correlated samples (or groups), minus 1
p-value: 0.022371
This p-value is for rejection of the omnibus null hypothesis, that all samples (groups) are from the same distribution, i.e. there is no effect of groups. The alternate hypothesis that one or more of the correlated samples (groups) is different, i.e. there is a group effect.
The omnibus p-value is at or below the respectable critical threshold of 0.05, so post-hoc pairwise multiple comparison tests are conducted to discern which of the pairs have significantly differences. Three of many possible post-hoc tests are conducted: the methods of (1) Conover and (2) Nemenyi. For the (1) Conover method, the p-value is adjusted in two ways, first according to the family-wide error rate (FWER) procedure of Holm, and next by the false discovery rate (FDR) procedure of Benjaminyi-Hochberg.
PTL ATM ATF A 6 5 10 B 4 10 16 C 8 7 14 D 12 13 16 E 5 6 11Related Questions
drjack9650@gmail.com
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.