There are many examples where the ‘p’ value is the key factor in determining whether the results are significant. An example of this is when looking at a relationship between smoking and lung cancer. If there is a significant difference when you look at people who smoke heavily compared to those who don’t, this would be considered evidence that smoking can cause cancer.

However, with this method, the ‘p’ value does not tell you how big the difference is. You need to calculate a ‘f value’. This is what is called a ‘fishy’ test. In fish studies, scientists put fish in a tank with ‘tasty’ food. The fish will eat the ‘tasty’ food, which results in a fishy smell.

If you have an anova, you can then run your calculation using the difference in the number of hits from your control group, who don’t smoke, and the number of hits from the ‘tasty’ group. You will calculate the difference between these two figures. ANOVA tells you how much your sample’s difference in number of hits with the other group (the control group) is statistically significant. Once you know how much significance there is in the difference between your groups, you can calculate the ‘f’ value.

In anova, the difference in number of hits (f value) is important because it tells you the number of times the difference in the difference between groups is significant. The p value tells you whether this difference is statistically significant or not, but doesn’t tell you the size of this difference. Because anova only works by calculating the difference in the number of hits between your control group and the other group, the size of the difference in the difference is not significant. The f value tells you how much the difference is significant, but doesn’t tell you how big it is.

If you run your analysis using anova, you also need to know how many times the difference in the number of hits (f value) between the control group and the other group was significant. You cannot calculate the difference between the number of hits with the other group and the control group, since there is no difference between these two groups when using anova.

So, if you want to use anova to determine whether or not the difference between the number of hits with the other group and the control group is statistically significant, you need to run your analysis using the difference between the number of hits with the control group and the other group divided by the number of hits without the control group. This gives you the number of hits divided by the number of hits without the control group.

Because there is no difference between these two groups, anova is useless in determining if the difference between the number of hits is statistically significant. You cannot use anova to tell you how many times the difference in the number of hits with the other group and the control group were significant because there is no difference between these two groups when using anova. But using the difference in the number of hits between the control group and the other group and dividing this number by the number of hits without the control group gives you a statistic which is very similar to the p value of the difference.