What makes the original scatter plot overcrowded or difficult to interpret?
It is harder to interpret the individual trends of each subgroup in the original scatterplot.
How does facet_wrap() help address the problem?
The code facet_wrap() helps address an overcrowded scatterplot by providing clearer subgroup comparison.
What additional information does facet_grid() provide?
The additional information .facet_grid() provides is that class is not the only influence on the trend observed, the scatterplot also represents drv.
Which of the three visualizations would you recommend for communicating the relationship between engine displacement and highway MPG? Justify your answer.
The visualization I would recommend for communicating the relationship between engine displacement and highway MPG is the facet_grid() plot. This is due to the individually represented subgroups additional to the clear distinction of the data’s trend not only being influenced by class but also drive type to which once can clearly see the proportion of data represented by class.
Are there any disadvantages to using too many facets?
The disadvantages to using too many facets may be clutter making the data harder to read and easily misinterpreted.