Confidence intervals

[kdund]

function to compute confidence intervals. Code to test:

from alea.examples.gaussian_model import GaussianModel

model = GaussianModel()

data = model.generate_data(mu=0,sigma=1)
data[0]["hat_mu"] = 0.
model.data = data

model.parameters.sigma.fittable = False
model.parameters.sigma.nominal_value = 1.
model.parameters.mu.nominal_value = 1.
model.parameters.mu.fittable = True
ci_upper =  model.confidence_interval(parameter="mu", parameter_interval_bounds=[-10,10], confidence_interval_kind="upper") #should return nan, sps.norm().isf(0.1) = 1.28
ci_lower = model.confidence_interval(parameter="mu", parameter_interval_bounds=[-10,10], confidence_interval_kind="lower") #should return -sps.norm().isf(0.1) = 1.28 , nan
ci_central = model.confidence_interval(parameter="mu", parameter_interval_bounds=[-10,10], confidence_interval_kind="central") #should return [-1,1]* sps.norm().isf(0.05) = 1.64

[hammannr]

Hi @kdund and thanks a lot for this addition. Looks great and works as intedned! 😊
I have a few suggestions and I quickly fixed the Parameters class init.

[hammannr]

Looks great! 😊