Re: [R] Segmented model

2015-07-27 Thread Bert Gunter
Segmented linear regression with breakpoint locations as parameters is NON-linear regression. R^2 for nonlinear regression -- and certainly R^2 for individual segments in segmented regression-- makes no (or at best very little) sense. For why this is so, post on a statistics list like stats.stacke

Re: [R] Segmented model

2015-07-27 Thread emiP
I apologize! I mean R2 (R squared) for each of the two segments-regressions arising from the model. -- View this message in context: http://r.789695.n4.nabble.com/Segmented-model-tp4710384p4710459.html Sent from the R help mailing list archive at Nabble.com. __

Re: [R] Segmented model

2015-07-27 Thread Bert Gunter
... Presumably the length of the segment ?? I leave it to the OP or others to look up the answer in their high school math texts. -- Bert Bert Gunter "Data is not information. Information is not knowledge. And knowledge is certainly not wisdom." -- Clifford Stoll On Mon, Jul 27, 2015 at 3:5

Re: [R] Segmented model

2015-07-27 Thread Rolf Turner
On 27/07/15 20:21, emiP wrote: Hi to all, I used segmented package for my analysis. All is OK, I can find the slope and the intercept of each segment but I can't find the R2 (square root) of each segment. Any idea? What *on earth* do you mean??? What is the square root of a segment??? cheers,

[R] Segmented model

2015-07-27 Thread emiP
Hi to all, I used segmented package for my analysis. All is OK, I can find the slope and the intercept of each segment but I can't find the R2 (square root) of each segment. Any idea? Thank you in advance, Emilia -- View this message in context: http://r.789695.n4.nabble.com/Segmented-model-tp4