Plotting geom_smooth/geom_spline regression line through the origin

Question

Related to this question (Plotting a regression line through the origin), I want to force a geom_smooth(method="loess") call through the origin (0). For geom_smooth(method="lm"), this is possible by specifying the formula in the call, ie geom_smooth(method=lm, formula=y~x-1). What would be the equivalent for geom_smooth(method="loess")?

Answer 1

This is an odd thing to want to do. A loess regression is a locally adaptive fit, so you cannot constrain it to pass through the origin unless you include in your regression a heavily weighted point (or tight cluster of points) at the origin. This is a bit artificial at best.

If you were able to expand on what you are trying to achieve and what your data represents, there may be a better option, but in the meantime, you could achieve what you are asking like this.

First, let's set up a simple example:

library(ggplot2)

set.seed(1)

df <- data.frame(x = 0:10, y = rnorm(11, 0:10) + 5)

p <- ggplot(df, aes(x, y)) + 
       geom_point() + 
       coord_cartesian(xlim = c(0, 10), ylim = c(0, 20)) +
       theme_bw(base_size = )

Our standard geom_smooth call would look like this:

p + geom_smooth(formula = y ~ x, method = "loess")

And to force it through the origin we can do:

p + geom_smooth(data = rbind(df, data.frame(x = 0, y = 0)),
                formula = y ~ x,
                aes(weight = c(rep(1, nrow(df)), 100)),
                method = "loess")

^{Created on 2020-12-13 by the reprex package (v0.3.0)}