Home/ Questions/Q 538587
In Process

The Archive Base Latest Questions

Editorial Team
  • 0
Asked: 2026-05-13T10:02:51+00:00

Say I had some data, for which I want to fit a parametrized model

  • 0

Say I had some data, for which I want to fit a parametrized model over it. My goal is to find the best value for this model parameter.

I’m doing model selection using a AIC/BIC/MDL type of criterion which rewards models with low error but also penalizes models with high complexity (we’re seeking the simplest yet most convincing explanation for this data so to speak, a la Occam’s razor).

Following the above, this is an example of the sort of things I get for three different criteria (two are to be minimized, and one to be maximized):

aic-bic
fit

Visually you can easily see the elbow shape and you would pick a value for the parameter somewhere in that region.
The problem is that I’m doing do this for large number of experiments and I need a way to find this value without intervention.

My first intuition was to try to draw a line at 45 degrees angle from the corner and keep moving it until it intersect the curve, but that’s easier said than done 🙂 Also it can miss the region of interest if the curve is somewhat skewed.

Any thoughts on how to implement this, or better ideas?

Here’s the samples needed to reproduce one of the plots above:

curve = [8.4663 8.3457 5.4507 5.3275 4.8305 4.7895 4.6889 4.6833 4.6819 4.6542 4.6501 4.6287 4.6162 4.585 4.5535 4.5134 4.474 4.4089 4.3797 4.3494 4.3268 4.3218 4.3206 4.3206 4.3203 4.2975 4.2864 4.2821 4.2544 4.2288 4.2281 4.2265 4.2226 4.2206 4.2146 4.2144 4.2114 4.1923 4.19 4.1894 4.1785 4.178 4.1694 4.1694 4.1694 4.1556 4.1498 4.1498 4.1357 4.1222 4.1222 4.1217 4.1192 4.1178 4.1139 4.1135 4.1125 4.1035 4.1025 4.1023 4.0971 4.0969 4.0915 4.0915 4.0914 4.0836 4.0804 4.0803 4.0722 4.065 4.065 4.0649 4.0644 4.0637 4.0616 4.0616 4.061 4.0572 4.0563 4.056 4.0545 4.0545 4.0522 4.0519 4.0514 4.0484 4.0467 4.0463 4.0422 4.0392 4.0388 4.0385 4.0385 4.0383 4.038 4.0379 4.0375 4.0364 4.0353 4.0344];
plot(1:100, curve)

EDIT

I accepted the solution given by Jonas. Basically, for each point p on the curve, we find the one with the maximum distance d given by:

point-line-distance

Share

Leave an answer

You must login to add an answer.

Need An Account,

1 Answer

  1. Editorial Team

    A quick way of finding the elbow is to draw a line from the first to the last point of the curve and then find the data point that is farthest away from that line.

    This is of course somewhat dependent on the number of points you have in the flat part of the line, but if you test the same number of parameters each time, it should come out reasonably ok.

    curve = [8.4663 8.3457 5.4507 5.3275 4.8305 4.7895 4.6889 4.6833 4.6819 4.6542 4.6501 4.6287 4.6162 4.585 4.5535 4.5134 4.474 4.4089 4.3797 4.3494 4.3268 4.3218 4.3206 4.3206 4.3203 4.2975 4.2864 4.2821 4.2544 4.2288 4.2281 4.2265 4.2226 4.2206 4.2146 4.2144 4.2114 4.1923 4.19 4.1894 4.1785 4.178 4.1694 4.1694 4.1694 4.1556 4.1498 4.1498 4.1357 4.1222 4.1222 4.1217 4.1192 4.1178 4.1139 4.1135 4.1125 4.1035 4.1025 4.1023 4.0971 4.0969 4.0915 4.0915 4.0914 4.0836 4.0804 4.0803 4.0722 4.065 4.065 4.0649 4.0644 4.0637 4.0616 4.0616 4.061 4.0572 4.0563 4.056 4.0545 4.0545 4.0522 4.0519 4.0514 4.0484 4.0467 4.0463 4.0422 4.0392 4.0388 4.0385 4.0385 4.0383 4.038 4.0379 4.0375 4.0364 4.0353 4.0344];

%# get coordinates of all the points
nPoints = length(curve);
allCoord = [1:nPoints;curve]';              %'# SO formatting

%# pull out first point
firstPoint = allCoord(1,:);

%# get vector between first and last point - this is the line
lineVec = allCoord(end,:) - firstPoint;

%# normalize the line vector
lineVecN = lineVec / sqrt(sum(lineVec.^2));

%# find the distance from each point to the line:
%# vector between all points and first point
vecFromFirst = bsxfun(@minus, allCoord, firstPoint);

%# To calculate the distance to the line, we split vecFromFirst into two 
%# components, one that is parallel to the line and one that is perpendicular 
%# Then, we take the norm of the part that is perpendicular to the line and 
%# get the distance.
%# We find the vector parallel to the line by projecting vecFromFirst onto 
%# the line. The perpendicular vector is vecFromFirst - vecFromFirstParallel
%# We project vecFromFirst by taking the scalar product of the vector with 
%# the unit vector that points in the direction of the line (this gives us 
%# the length of the projection of vecFromFirst onto the line). If we 
%# multiply the scalar product by the unit vector, we have vecFromFirstParallel
scalarProduct = dot(vecFromFirst, repmat(lineVecN,nPoints,1), 2);
vecFromFirstParallel = scalarProduct * lineVecN;
vecToLine = vecFromFirst - vecFromFirstParallel;

%# distance to line is the norm of vecToLine
distToLine = sqrt(sum(vecToLine.^2,2));

%# plot the distance to the line
figure('Name','distance from curve to line'), plot(distToLine)

%# now all you need is to find the maximum
[maxDist,idxOfBestPoint] = max(distToLine);

%# plot
figure, plot(curve)
hold on
plot(allCoord(idxOfBestPoint,1), allCoord(idxOfBestPoint,2), 'or')
    • 0