Setting method as default method in geom_smooth gives different result
I am drawing some data and have the following code:
ggplot(aes(x = x, y = y), data = data) +
geom_point(alpha = 1/15, color = 'blue')+
scale_y_continuous('y')+
scale_x_continuous('x')+
geom_smooth(stat = 'smooth', color = 'Red')
The graph looks like this:
But if I specify "gam" in a function geom_smooth
like:
geom_smooth(stat = 'smooth', color = 'Red', method = 'gam')
I get a different result:
Why is this happening?
source to share
In the Documentation, you can see that:
an antialiasing method (function) to use eg. "lm", "glm", "gam", "leess", "RLM".
For method = "auto", the anti-aliasing method is selected based on the size of the largest group (across all panels). loess used fewer than 1000 observations; otherwise the gamma is used with the formula = y ~ s (x, bs = "CS"). Somewhat anecdotally, loess gives a better look and feel, but O (n ^ 2) in memory, so doesn't work for large datasets.
Note that when the 'auto' method uses gam, it also changes the formula. Default formula
formula = y ~ x
So, in the first scenario, he uses the gam method, with a modified function function y ~ s (x, bs = "cs"). The second time, you only indicate that the "gam" method should be used, but you don't overwrite the formula, so y ~ x is still used. You can do it:
geom_smooth(stat = 'smooth', color = 'Red', method = 'gam', formula = y ~ s(x, bs = "cs"))
To get the same result. Hope this helps!
source to share