Use histogram to see the shape. Move_W_to_dBm has a double peak at low values, with an extremely long tail to the right (I deleted values larger than 8*10^-10 in order to see the doube peak better). There is no way this is a normal curve! Looks like it might be a combination of a couple of normals, perhaps (ignoring the rightwards bias, that is). However, you could use the histogram to define your own pdf, and use cumtrapz, perhaps, to define the cdf.