Skip to main content

Meeting in the middle; or fudging model II regression with nls

My colleague Karen needed an equation to predict trunk diameter given tree height, which she hoped to base on measurements of trees in semi-arid Australian woodlands. This is the dark art of allometry and a quick google found a large number of formulae that have been used in different studies of tree dimensions. No problem: I started to play with a few of them and eventually settled on this one:

dbh = exp( b0 + b1 / (b2 + h) )
where: dbh is trunk diameter at breast height; h is tree height.

Karen also needed to do reverse predictions, ie. predict a tree's height given its trunk diameter. Again no problem, the inverse equation is simply:

height = b1 / (log( dbh ) - b0) - b2

But then, the pièce de résistance: the forward predictions had to agree with the reverse predictions, ie. if plugging height h into the forward equation gave trunk diameter d, then plugging d into the reverse equation should get you back to h. Karen pointed out that this seemed to be a Model II regression problem because as well as needing symmetric predictions, both variables were subject to measurement error.

R has at least two packages with Model II regression functions: lmodel2 and smatr, but both seemed to be restricted to a single predictor (I'd be interested to hear if I'm wrong about that). Meanwhile, the trusty nls function seemed to do a good job of fitting the forward and reverse equations while dealing with the pattern of variance displayed by the tree data (mu^3).

A solution arrived in the form of this post in the r-help list archive explaining how the coefficients from the forward and reverse fits could be combined by taking their geometric mean to arrive at a form of Model II regression. We tried this and it appeared to work nicely.
The plot above shows the separate fits, plus the combined fit which does indeed give symmetric predictions, for one of the tree species.

Comments

Popular posts from this blog

Circle packing in R (again)

Back in 2010 I posted some R code for circle packing . Now, just five years later, I've ported the code to Rcpp and created a little package which you can find at GitHub . The main function is circleLayout which takes a set of overlapping circles and tries to find a non-overlapping arrangement for them. Here's an example: And here's the code: # Create some random circles, positioned within the central portion # of a bounding square, with smaller circles being more common than # larger ones. ncircles <- 200 limits <- c(-50, 50) inset <- diff(limits) / 3 rmax <- 20 xyr <- data.frame( x = runif(ncircles, min(limits) + inset, max(limits) - inset), y = runif(ncircles, min(limits) + inset, max(limits) - inset), r = rbeta(ncircles, 1, 10) * rmax) # Next, we use the `circleLayout` function to try to find a non-overlapping # arrangement, allowing the circles to occupy any part of the bounding square. # The returned value is a list with elements for

Fitting an ellipse to point data

Some time ago I wrote an R function to fit an ellipse to point data, using an algorithm developed by Radim Halíř and Jan Flusser 1 in Matlab, and posted it to the r-help list . The implementation was a bit hacky, returning odd results for some data. A couple of days ago, an email arrived from John Minter asking for a pointer to the original code. I replied with a link and mentioned that I'd be interested to know if John made any improvements to the code. About ten minutes later, John emailed again with a much improved version ! Not only is it more reliable, but also more efficient. So with many thanks to John, here is the improved code: fit.ellipse <- function (x, y = NULL) { # from: # http://r.789695.n4.nabble.com/Fitting-a-half-ellipse-curve-tp2719037p2720560.html # # Least squares fitting of an ellipse to point data # using the algorithm described in: # Radim Halir & Jan Flusser. 1998. # Numerically stable direct least squares fitting of ellipses

Graph-based circle packing

The previous two posts showed examples of a simple circle packing algorithm using the packcircles package (available from CRAN and GitHub ). The algorithm involved iterative pair-repulsion to jiggle the circles until (hopefully) a non-overlapping arrangement emerged. In this post we'll look an alternative approach. An algorithm to find an arrangement of circles satisfying a prior specification of circle sizes and tangencies was described by Collins and Stephenson in their 2003 paper in Computation Geometry Theory and Applications. A version of their algorithm was implemented in Python by David Eppstein as part of his PADS library (see CirclePack.py ). I've now ported David's version to R/Rcpp and included it in the packcircles package. In the figure below, the graph on the left represents the desired pattern of circle tangencies: e.g. circle 7 should touch all of, and only, circles 1, 2, 6 and 8. Circles 5, 7, 8 and 9 are internal , while the remaining circles are exter