how to plot predicted values on lm line for a null model using ggplot in r

Question

Trying to reproduce below base code using ggplot which is yielding incorrect result

base code

model1 <- lm(wgt ~ 1, data = bdims)
model1_null <- augment(model1)
plot(bdims$hgt, bdims$wgt)
abline(model1, lwd = 2, col = "blue")
pre_null <- predict(model1)
segments(bdims$hgt, bdims$wgt, bdims$hgt, pre_null, col = "red")

ggplot code

bdims %>% 
  ggplot(aes(hgt, wgt)) +
  geom_point() +
  geom_smooth(method = "lm", formula = bdims$hgt ~ 1) +
  segments(bdims$hgt, bdims$wgt, bdims$hgt, pre_null, col = "red")

Gregor Thomas · Accepted Answer · 2018-04-05 03:56:58Z

1

Here's an example using the built-in mtcars data:

ggplot(mtcars, aes(wt, mpg)) +
    geom_point() +
    geom_smooth(method = "lm", formula = y ~ 1) + 
    geom_segment(aes(xend = wt, yend = mean(mpg)), col = "firebrick2")

The formula references the aesthetic dimensions, not the variable names. And you need to use geom_segment not the base graphics segments. In a more complicated case you would pre-compute the model's predicted values for the segments, but for a null model it's easy enough to just use mean inline.

answered Apr 5, 2018 at 3:56

Gregor Thomas

147k22 gold badges185 silver badges320 bronze badges

Sign up to request clarification or add additional context in comments.

4 Comments

avrp Over a year ago

> based on your answer tried by calculating model's predicted value with single variable hgt. here is the sample code 'pre_hgt <- predict(model2) bdims %>% ggplot(aes(hgt, wgt)) + geom_point() + geom_smooth(method = "lm", se = 0) + geom_segment(aes(xend = hgt, yend = pre_hgt), col = "firebrick2")'

Gregor Thomas Over a year ago

I'm not sure what the point of your comment is. I can't run your sample code since you haven't shared any sample data. Are you trying to say "Thanks, this worked great!" or "I can't get this to work on my data."? Either way, I would recommend only using length-1 constants or columns of your data frame inside aes. Using a vector with length > 1 that is not in your data frame like pre_hgt is asking for trouble. Reduce it to a single value or add it to your data frame.

avrp Over a year ago

Im new to this place tried commenting more than 3 times and it got locked. I meant to say thanks and included the code which did not include data source which worked after your input 'model2 <- lm(wgt ~ hgt, data = bdims) pre_hgt <- predict(model2) bdims %>% ggplot(aes(hgt, wgt)) + geom_point() + geom_smooth(method = "lm", se = 0) + geom_segment(aes(xend = hgt, yend = pre_hgt), col = "firebrick2")' and point noted in terms of length of constants or columns

Gregor Thomas Over a year ago

Great! If you're not hoping for additional answers, you should "accept" my answer to mark your question as solved. You can do this by clicking the check mark in the left margin next to the answer.

Collectives™ on Stack Overflow

how to plot predicted values on lm line for a null model using ggplot in r

1 Answer 1

4 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

4 Comments

Your Answer

Sign up or log in

Post as a guest

Related