Blog Home

R for Data Science Statistical Transformations

Nov 9, 2023

From R for Data Science

Statistical Transformations

1-What is the default geom associated with stat_summary()? How could you rewrite the previous plot to use that geom function instead of the stat function?

ggplot(diamonds) + 
  stat_summary(
    aes(x = cut, y = depth),
    fun.min = min,
    fun.max = max,
    fun = median
  )
  
ggplot(diamonds) +
  geom_pointrange(
    aes(x = cut, y = depth),
    stat = "summary",
    fun.min = min,
    fun.max = max,
    fun = median
  )

2-What does geom_col() do? How is it different from geom_bar()?

geom_col uses the bar heights to represent the data. geom_bar uses bar heights to show the proportion of the data to the number of cases in each group. geom_bar() uses stat_count() by default and counts the number of cases at each x position; geom_col() uses stat_identity() and leaves the data as is.

3-Most geoms and stats come in pairs that are almost always used in concert. Make a list of all the pairs. What do they have in common? (Hint: Read through the documentation.)

Here is the reference guide

  • geom_bar() -> stat_count()
  • geom_bin_2d() -> stat_bin_2d()
  • geom_boxplot() -> stat_boxplot()
  • geom_contour() -> stat_contour(); geom_contour_filled() -> stat_contour_filled()
  • geom_count() -> stat_sum()
  • geom_density() -> stat_density()
  • geom_density_2d() -> stat_density_2d(); geom_density_2d_filled() -> stat_density_2d_filled()
  • geom_function() -> stat_function()
  • geom_hex() -> stat_bin_hex()
  • geom_freqpoly(), geom_histogram() -> stat_bin()
  • geom_crossbar() geom_errorbar() geom_linerange() geom_pointrange()
  • geom_qq_line() -> stat_qq_line(); geom_qq() -> stat_qq()
  • geom_quantile() -> stat_quantile()
  • geom_area() -> stat_align()
  • geom_smooth() -> stat_smooth()
  • geom_violin() -> stat_ydensity()
  • geom_sf(), geom_sf_label(), geom_sf_text() stat_sf()
  • geom_function() -> stat_function()

4-What variables does stat_smooth() compute? What arguments control its behavior?

stat_smooth() calculates geom_smooth(). The method and formula arguments determine its behavior.

5-In our proportion bar chart, we need to set group = 1. Why? In other words, what is the problem with these two graphs?

ggplot(diamonds, aes(x = cut, y = after_stat(prop))) + 
  geom_bar()
ggplot(diamonds,  aes(x = cut, y = after_stat(prop), fill=color)) + 
  geom_bar()

These two graphs show the proportion of each cut to itself, so that all are 100%. The group = 1 combines all cut values so that each bar is a proportion of all cuts as a whole group.

These graphs could be fixed with:

ggplot(diamonds, aes(x = cut, y = after_stat(prop), group = 1)) + 
  geom_bar()
ggplot(diamonds,  aes(x = cut, y = after_stat(prop), group=1, fill = after_stat(prop))) + 
  geom_bar()