C * exp(2.2/X) + 51.0 + pi ** e - sinc(1.1) / [B + A]  # coefficients are A, B and C 

 Scale * exp(X) + offset  # Scale and offset are coefficents in this example 

 # the following three examples are equivalent 
 power(X+shift, C0)  # shift and C0 are coefficients in this example 
 [X+shift] ** C0     # shift and C0 are coefficients in this example 
 (X+shift) ** C0     # shift and C0 are coefficients in this example 

 MX + B  # This fails, it should be written as M*X + B 

• Convert commas to spaces (1,2,0,3 yields 1 2 0 3)
• Use comma as decimal separator (1,203 = 1.203)
• Remove commas from text (1,2,0,3 yields 1203)

• Standard Unweighted Fitting: no weights required
• Weighted Fitting: each data point requires a weight

• Lowest sum of squared absolute error
• Lowest sum of squared orthogonal distance
• Lowest sum of squared relative error
• Lowest sum of absolute value of absolute error
• Lowest sum of squared log[predicted/actual]
• Lowest sum of absolute value of relative error
• Lowest peak absolute value of absolute error
• Lowest peak absolute value of relative error
• Lowest Akaike Information Criterion
• Lowest Bayesian Information Criterion