Every year, administrators of the San Francisco airport conduct a survey to analyze guest satisfaction. Suppose management wants to compare the restaurant quality scores of four terminals. Restaurant scoring ranges from1 to 5, with 1 = Unacceptable, 2 = Below Average, 3 = Average, 4 = Good, and 5 = Outstanding. Since it is an ordinal response variable, it is decided a Kruskal–Wallis test will be implemented. Kruskal–Wallis test on restaurant quality scores

a) Write the null and alternative hypothesis.
b) According to the table above, is the null rejected at 5% significance?
c) Assuming the distribution of scores per terminal have the same shape, does it appear that the difference between medians is large?

Transcribed Image Text:

Terminal 1 2 3 4 Overall H = 143.99 H = 162.36 N 540 277 438 514 1769 DF = 3 DF = 3 Median 3.00 4.00 4.00 3.00 P = 0.000 P = 0.000 Ave rank 727.8 1141.9 983.6 827.6 885.0 (adjusted for ties) Z -8.58 9.11 4.66 -3.02