functions in fitlsq.i - f

    yp= fitlsq(y, x, xp)  
    ...  
    yfit= interp(yp, xp, xfit)  


performs a least squares fit to the data points (X, Y).  The input  
XP are the abcissas of the piecewise linear function passing through  
(XP, YP) which is the best fit to the data (X,Y) in a least squares  
sense.  The XP must be strictly monotone, either increasing or  
decreasing.  As for interp, the piecewise linear fit is taken to be  
constant outside the limits of the XP.  
The result YP is linearly interpolated through any consecutive  
intervals of XP which contain no data points X, and linearly  
extrapolated beyond the extreme values of X (if any of the intervals  
of XP lie outside these extremes).  
A WEIGHT keyword of the same length as X and Y may be supplied in  
order to weight the various data points differently; a typical  
WEIGHT function is 1/sigma^2 where sigma are the standard deviations  
associated with the Y values.  
Interpreted function, defined at i/fitlsq.i   line 10