ROOT Version: 6.18/04 Platform: Linux Hi all! I have plotted efficiency curves, and now I want to fit sigmoid functions to them. I tried to fit a sigmoid function to the first efficiency curve (the red one), which is called eff[0]. [c1] I tried: TF1 *sigm = new TF1("sigm", "(1/(1+ TMath::Exp(-…

Try (before fitting): sigm->SetParameters(0.5, 50.); In ROOT, before you try to fit your graph or histogram, you MUST set “reasonable” initial values for ALL parameters of your function (except for some “built-in” formulas, like “gaus”, for which the standard fit procedure can automatically “guess”…

I tried adding that line, and my fit looks better, but it still says STATUS: FAILED, which means that it couldn’t find a proper fit I guess? And the fit still changes quite a lot depending on which initial values I choose… It’s almost as if, it just draws the sigmoid function using the chosen parame…

@moneta can you help with this one?

Already @Wile_E_Coyote answers. It is essential to set parameters as close as possible to the solution. In addition you might need to set parameter limits to avoid regions where the function is ill defined or does not make sense for your data, for example wrong slopes for your sigmoids. However I s…

The fit works if I add “W” or “EX0” to the Fit function!

Hi, I think you need to add EX0. It looks to me your plot comes from an histogram. There is then no reason to have an error in ‘X’. Lorenzo

Hi, yes, my plot comes from a histogram. I tried both “W” and “EX0”, and “W” seems to give a nicer fit in general, I am just not sure whether it is justified to just ignore all my errors…

But what is the type of eff[0]. If your data are efficiencies, for a correct error display and fitting you should use the TEfficiency class and TEfficiency::Fit Lorenzo

Home | News | Documentation | Download

ROOT Forum

Sigmoid fit to efficiency plot

Newbie

Wile_E_Coyote March 23, 2020, 12:02pm 10

Fit function uses initial parameter values Newbie

ROOT Version: 6.18/04 Platform: Linux I defined a sigmoid function with 2 parameters (and set the initial parameter values). I am now trying to fit this function to a plot (called fun[1]), however my ‘fit’ always just takes my initial parameter values, even though that is definitely not the best fit. Most of the time I also get the message saying that STATUS = FAILED, a few times, however, I got STATUS = CONVERGED, but that result clearly wasn’t the best fit. I tried: TF1 *sigm = new TF1("si…

show post in topic

Home
Categories
Guidelines
Terms of Service
Privacy Policy

Powered by Discourse, best viewed with JavaScript enabled