A randomized complete block design was used to test if three different soccer kits (jerseys) being displayed in the window impacted sales at the team store. Each match (9 total) was used as a blocking variable and the three different versions of the team jersey for sale at the team store, one in the window of each of three team store locations, were the levels of the design variable. How does the assumption of additivity impact the results?

Tests of Fixed Effects Term DF Num DF Den F-Value P-Value Jersey 2.00 16.00 10.47 0.001 Variance Components Source Var % of Total SE Var Z-Value P-Value Match 9.323908+04 55.71% 5.961898+04 1.563917 0.059 Error 7.41345E+04 44.29% 2.62105E+04 2.828427 0.002 Total 1.67373E+05 -2 Log likelihood = 358.529186 Coefficients Term Coef SE Coef DF T-Value P-Value Constant 1149.344472 114.479741 8.00 10.039719 0.000 Jersey Alternate 338.708829 74.104273 16.00 4.570706 0.000 Away -156.499275 74.104273 16.00 -2.111879 0.051