Runs test table, cut point = mode
  • In this second test table, the cut point is the mode. Remember that the distribution of ratings is actually bimodal.
  • A footnote warns you that the mode being used is the larger of the two data values.
  • The number of cases above and below this cut point stands in contrast to the previous table. Ratings below 12 outnumber those at or above 12 by more than a 2 to 1 margin. This is not surprising, given that 12 is also the 75th percentile.
  • Because it is a function of the number of positive and negative cases, the expected number of runs always depends on the cut point. In this table, the expected number of runs is about 15, which is very close to the observed number.
  • The 2-tailed significance value does not allow you to reject the null hypothesis that the order of the ratings is random with respect to the higher modal value of 12.