Comparing curves fitted to two quadratic regressions


New Member

I have constructed two calibration curves, i.e. plotting known concentrations against response. Both of these sets of data seem to fit a quadratic model best. The curves fitted to these data have the following equations: y = -2.7484E-07x2 + 1.5453E-03x + 7.1982E-02 and y = -3.7290E-07x2 + 1.6799E-03x + 5.8039E-03

Is there anyway I can compare these two curves and see if they are significantly different to one another?

The two curves use different concentrations 0, 10, 200, 400, 600, 800 and 1000 for the one curve and 363, 373, 563, 763, 963, 1163 for the other. I have four replicates at each concentration (although one replicate is missing for one of the matrix matched concentrations).

Any ideas would be much appreciated. I am happy to use r, SPSS or excel.



Point Mass at Zero
never mind the fitted models,

if you want to compare if two curves (distributions) are similar to each other, then you can use the non-parametric version of two sample t-test. Look up for two-sample Kolmogorov-Smirnoff test or Mann Whitney test.

If normal, two sample t-test should be OK.
I have a similar question on this topic. I have two quadratic equations and I want to compare the slopes. Basically, my question is "Does one group decrease significantly faster than the other?"

I am not looking at mean or median. I am only looking at the rate of change between the two groups.