It iterates in a way similar to the well known bisection method in root finding, with the only exception is that our [a_n,b_n] intervals contain the inflection point now and the rule for choosing them follows definitions and Lemmas of [1], [2].
1  bede(x, y, index)

x 
The numeric vector of xabscissas, must be of length at least 4. 
y 
The numeric vector of the noisy or not yordinates, must be of length at least 4. 
index 
If data is convex/concave then index=0 
It is the fastest solution for very large data sets, over one million rows.
It returns a list of two elements:
iplast 
the last EDE estimation that was found 
iters 
a matrix with 4 columns ("n", "a", "b", "EDE") that give the number of xy pairs used at each iteration, the [a,b] range where we searched and the EDE estimated inflection point. 
New function in version 1.2
Demetris T. Christopoulos
[1]Demetris T. Christopoulos, Developing methods for identifying the inflection point of a convex/ concave curve, arXiv:1206.5478v2 [math.NA], 2012.
[2]Demetris T. Christopoulos, On the efficient identification of an inflection point,International Journal of Mathematics and Scientific Computing,(ISSN: 22315330), vol. 6(1), 2016.
See also the simple version ede
.
1 2 3 4 5 6 7 8 
Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
All documentation is copyright its authors; we didn't write any of that.