Recent content by Predictor

It's not clear to me whether you are more interested in RA or log(RA), but I don't see why a simple mean absolute error or mean absolute percentage error couldn't be used to characterize your model's error, though it should be calculated on observations not used to fit the model function...

I assume that you are referring specifically to linear regressions. The difference between least squares and least absolute deviation is what is being optimized when the line is fit to the data. Yes, the mechanics of the LS and LAD (also called "L-1") fitting procedures are quite different...

I imagine that you are referring to the bias-variance trade-off? The total of these components would appear in error resampling, so that as model complexity increased, total error would decrease (as we reduce one component faster than the other increases) until the optimal fit, after which...

There are two basic approaches to answering this question: 1. The traditional statistics approach is to make various assumptions about the distributions of the data, errors, etc., and calculate some diagnostic summary of the model. 2. The error resampling method involves holding out data...

Yes, you could use one of the longer integer data types and bit-level operators. Try: help uint64 help bitset help bitget -Will Dwinnell http://matlabdatamining.blogspot.com/"

The problem is that imread is expecting a single string parameter. You need to concatenate the components of the file name, by wrapping them in square brackets: cur=imread(['salam(' int2str(counter) ').jpg']); -Will Dwinnell http://matlabdatamining.blogspot.com/"

Right, and you can place whatever value or values in 'a' that you like. For instance, if 'a' is a vector containing 7 different values, and the formula is written correctly, then 'y' will contain 7 values, each that function of the corresponding element in 'a': >> a = [-1 0 1 2 3 4 5] a =...