I'm using curve_fit from numpy to try an fit some data I have. The function I used was the logistic function defined http://en.wikipedia.org/wiki/Logistic_function
and the parameters I picked were
(0.026, 0.745, 19.0, 0.0005), for L, k, x0, and an extra parameter a.
I tested the goodness of fit using chi-squared test. The test said it was a bad fit, and it is visibly a bad fit from the picture shown below.
I'm not sure if what other function would be better to fit this data, and if this is a good function what parameters should I change?