Best linear fit to data with errors in both x and y

I have data with errors in both x and y, just like :x,xerr,y,yerr;How can I fit them with the error. As the fit function only consider x and y.Is there any other function can do it?

Answer 1

[the cyclist]

There is one technique I know of called "Total Least Squares", that accounts for error in both the independent and dependent variables. I don't know of any built-in MATLAB functions that do this technique. I found this FEX submission, which is highly rated. You could try it.