[R] How to find a split point in a curve?

Rui Barradas ru|pb@rr@d@@ @end|ng |rom @@po@pt
Thu May 14 17:21:18 CEST 2020


Hello,

Are you looking for a segmented regression?

fit <- lm(Y ~ X)
seg <- segmented::segmented(fit, seg.Z = ~X)
seg$psi[, 'Est.']
#[1] 29.21595

plot(X, Y)
plot(seg, add = TRUE)


Hope this helps,

Rui Barradas


Às 16:12 de 14/05/20, Luigi Marongiu escreveu:
> Dear all,
> I am trying to find a turning point in some data. In the initial phase, the
> data increases more or less exponentially (thus it is linear in a nat log
> transform), then reaches a plateau. I would like to find the point that
> marks the end of the exponential phase.
> I understand that the function spline can build a curve; is it possible
> with it to find the turning points? I have no idea of how to use spline
> though.
> Here is a working example.
> Thank you
> 
> ```
> Y = c(259, 716, 1404, 2173, 3944, 5403, 7140, 9121,
>        11220, 13809, 16634, 19869, 23753, 27447,
>        30590, 33975, 36627, 39600, 42067, 44082,
>        58190, 63280, 65921, 67929, 69977, 71865,
>        73614, 74005, 74894, 75717, 76365, 76579,
>        77087, 77493, 77926, 78253, 78680, 79253,
>        79455, 79580, 79699, 79838, 79981, 80080,
>        80124, 80164, 80183, 80207, 80222, 80230,
>        80241, 80261, 80261, 80277, 80290, 80303,
>        80337, 80376, 80422, 80461, 80539, 80586,
>        80653, 80708, 80762, 80807, 80807, 80886,
>        80922, 80957, 80988, 81007, 81037, 81076,
>        81108, 81108, 81171, 81213, 81259, 81358,
>        81466, 81555, 81601, 81647, 81673, 81998,
>        82025, 82041, 82053, 82064, 82094, 82104,
>        82110, 82122, 82133, 82136, 82142, 82164,
>        82168, 82180, 82181, 82184, 82187, 82188,
>        82190, 82192, 82193, 82194)
> Y = log(Y)
> X = 1:length(Y)
> plot(Y ~ X, ylab = "Ln(Y)", xlim=c(0,10, main="zoomed in"))
> abline(lm(Y[1:3] ~ X[1:3]))
> abline(lm(Y[1:5] ~ X[1:5]), lty=2)
> text(7, 6, "After third or fifth point, there is deviance", pos=3)
> text(2.5, 10, "Solid line: linear model points 1:3", pos =3)
> text(2.5, 9, "Dashed line: linear model points 1:5", pos =3)
> plot(Y ~ X, ylab = "Ln(Y)", xlim=c(0,10, main="overall"))
> abline(lm(Y[1:3] ~ X[1:3]))
> ```
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>



More information about the R-help mailing list