who can help me solve the error appearing in matlab cftool

e+a.*((c-1)./c).^((1-c)./c) .* ((x-d)./b+((c-1)./c).^(1./c).^(c-1)) .* exp(-(x-d)./b+((c-1)./c).^(1./c).^c+(c-1)./c)

I use this function to make curve fittiing,but in matlab cftool appears this error:Ignoring NaNs in data. Complex value computed by model function, fitting cannot continue. Try using or tightening upper and lower bounds on coefficients.

I get this function from the sigmaplot curve fitting report:

Data Source: Data 1 in Notebook1 Equation: Peak, Weibull, 5 Parameter

f = if(x<=x0-b*((c-1)/c)^(1/c),
       y0, 
       y0+a*((c-1)/c)^((1-c)/c) * (abs((x-x0)/b+((c-1)/c)^(1/c))^(c-1)) * ...
          exp(-abs((x-x0)/b+((c-1)/c)^(1/c))^c+(c-1)/c))

 this is the function that I used ,I just remove abs

R         Rsqr         Adj Rsqr         Standard Error of Estimate

0.9425        0.8882        0.8868                3.0055        

        Coefficient        Std. Error        t        P        

a        29.1202        0.6399        45.5066        <0.0001        
b        1.1594        0.0280        41.4211        <0.0001        
c        1.5093        0.0413        36.5247        <0.0001        
x0        6.1068        0.0252        241.9026        <0.0001        
y0        2.2064        0.2053        10.7457        <0.0001

I also attach the original data

Answer 1

[dpb]

f = if(x<=x0-b*((c-1)/c)^(1/c),
     y0, 
     y0+a*((c-1)/c)^((1-c)/c) * (abs((x-x0)/b+((c-1)/c)^(1/c))^(c-1)) * ...
        exp(-abs((x-x0)/b+((c-1)/c)^(1/c))^c+(c-1)/c))

...this is the function that I used ,I just remove abs

Well, you did quite a lot else besides -- you removed the x<=x0... conditional section, as well as the abs()

I don't know SigmaPlot syntax, but just guessing I'd translate the above as

   if x <= x0-b*((c-1)/c)^(1/c)
     f=y0;
   else 
     f=y0+a*((c-1)/c)^((1-c)/c) * ...
         (abs((x-x0)/b+((c-1)/c)^(1/c))^(c-1)) * ...
          exp(-abs((x-x0)/b+((c-1)/c)^(1/c))^c+(c-1)/c));
   end

in Matlab.

Don't believe cftool has the flexibility for such a model with the conditional in it; you'll have to use one of the more sophisticated nonlinear fitting tools in Matlab.