Independent Random Samples of Households in the Four U

Short Answer

Independent random samples of households in the four U.S.regions (Northeast,Midwest,South,and West)yielded data on last year's energy consumption.We are interested in assessing,at the 1% significance level,if the data provide sufficient evidence to conclude that last year's average energy consumption was different among the four U.S.regions.Assume that energy consumption in the four regions is Normally distributed.
SPSS was used to create the side-by-side boxplots shown below. What assumption needed for an ANOVA F test can be checked with this graph?