What is the way to find a linear regression model in R which minimizes the mean square error of residuals expressed in percents rather than the absolute difference?
Solved – Finding a linear regression model that minimized percentage error in R
rregression
Related Solutions
The shortest half is the shortest interval containing half the distribution or data (when dealing with populations or samples respectively). [Some authors call this interval of the shortest half the shorth, though the term seems to have been coined by Andrews et al (1972) who used it to refer to the mean of the observations in the shortest half, so it would more properly refer to that. Probably best to just explicitly say shortest half and mean of the shortest half to avoid that potential confusion]
The midpoint of the shortest half should minimize the median of the absolute deviations; you sometimes see it called "the midpoint of the shortest half", but it has another name (see below).
This is a one-dimensional version of a minimum volume estimator.
Because quantiles are equivariant to monotonic-increasing transformation, in one dimension we can see that minimizing the median of the absolute deviations is equivalent to minimizing the median of the squared deviations [or any other monotonic increasing function of them -- at least if we keep our definition of medians as interval-valued when they don't fall exactly at observations, otherwise they'll differ slightly but always lie between the same observations].
So the literature on least median of squares (LMS) estimation will probably be of some use to you here. e.g. see Rousseeuw & Leroy, 1987 [1], for example
There's often explicit code for LMS estimators (especially for regression, but if you only fit an intercept ... you should get the original thing you asked about) and sometimes code for producing estimators based on the shortest half (e.g. Nick Cox seems to have written one for Stata, for example)
So the alternative name I referred to earlier would be the "least median of squares estimate of location".
Sorry both terms seem to be such a mouthful; off the top of my head I don't know any reasonably unambiguous names that are shorter.
[1] Rousseeuw, P.J. and Leroy, A.M. (1987),
Robust Regression and Outlier Detection,
Wiley, New York.
Best Answer
Easy. There are actually several choices, first is to take the logarithm of the y-axis values, that converts multiplication into addition thus it converts relative error into absolute error.
Second choice, that you didn't ask for, would be to do the regression minimizing a different norm. That is, usually one minimizes $||model-y_{data}||$, where $||.||$ is the norm, A.K.A. the L2 norm, A.K.A. the absolute value of a vector difference, A.K.A. the square root of the sum of squares of the difference. To do this for proportional modeling one minimizes $||\frac{model}{y_{data}}-1||$.