How to find slopes of multiple regression?

Question

I'm making a plot of several linear regressions and I would like to find the slope of each of them. The problem is that I don't find how to do it in my case. Like you can see on my plot, I'm testing the weight as a function of the temperature, a quality (my two colors) and quantity (my facet wrap).

My code for this plot is that :

g = ggplot(donnees_tot, aes(x=temperature, y=weight, col = quality))+
     geom_point(aes(col=quality), size = 3)+
     geom_smooth(method="lm", span = 0.8,aes(col=quality, fill=quality))+
     scale_color_manual(values=c("S" = "aquamarine3",
                              "Y" = "darkgoldenrod3"))+
     scale_fill_manual(values=c("S" = "aquamarine3",
                             "Y" = "darkgoldenrod3"))+
     scale_x_continuous(breaks=c(20,25,28), limits=c(20,28))+
     annotate("text", x= Inf, y = - Inf, label =eqn, parse = T, hjust=1.1, vjust=-.5)+
     facet_wrap(~quantity)
   g

Also, if you have a tips to write them on my plot, I would be really grateful ! Thank you

Does this help? https://stackoverflow.com/q/7549694/17144974 — cgvoller, Dec 07 '22 at 10:29
you should look at the [ggpmisc](https://cran.r-project.org/web/packages/ggpmisc/vignettes/model-based-annotations.html) package — Elia, Dec 07 '22 at 11:20
Thank you, I've watched the topic of this link and with the ggpmisc package, I solved my problem — Nathan FRIZOT, Dec 08 '22 at 12:54
You can calculate the slope yourself: e.g., `df <- data.frame( x = 1:10, y = c(0, 2, rnorm(6), 7, 9) ) lm(df$y ~ df$x)$coeff[2] df$x 0.6469238 ` — Chris Ruehlemann, Dec 08 '22 at 13:29

score 0 · Answer 1 · answered Dec 08 '22 at 12:57

0

By using the ggpmisc package, I've had these lines to my code and it works !

stat_poly_line() +
  stat_poly_eq(aes(label = paste(after_stat(eq.label),
                                 after_stat(rr.label), sep = "*\", \"*"))) +

answered Dec 08 '22 at 12:57

Nathan FRIZOT

121
6

How to find slopes of multiple regression?

1 Answers1