The first step for conducting an ANOVA in R is to create an ANOVA object. There are two ways of doing this, using the `lm()`

command, and using the `aov()`

command. For simplicity we will be using the `aov()`

command now, but we will get to the `lm()`

object later.

By using the `aov()`

command, we can create an object that tells `summary()`

, `plot()`

or any other commands that the object is specifically for an ANOVA and as such, will be treated as one.

The syntax for almost all analyses in R is the same. Within our analysis command (`aov()`

in this example) we write a line equation for our analysis:

**y ~ x**

This is simply your response variable (Y) and explanatory variable(s) (X) separated by a tilde **~**. The tilde acts as an = sign for the analysis.

For this analysis, we will be using the **weeds** dataset.

`weeds.aov <- aov(flowers ~ species, data=weeds) # flowers (Y variable) ~ species (X variable), then data = weeds to direct it to our dataframe. `

As per usual, name your newly created object something that will remind you of what it is. I tend to name it something to remind me of the dataset as well as the statistical technique. Generally **dataset.analysis**.

Now we have our `aov()`

object, it is good practice to test the assumptions before we look at the results of the analysis. Having this workflow in place will hopefully prevent you from conveniently “forgetting” assumptions after seeing a significant result.