normal_sample

sherpa.astro.ui.normal_sample(num=1, sigma=1, correlate=True, id=None, otherids=(), numcores=None)

Sample the fit statistic by taking the parameter values from a normal distribution.

For each iteration (sample), change the thawed parameters by drawing values from a uni- or multi-variate normal (Gaussian) distribution, and calculate the fit statistic.

Parameters:
  • num (int, optional) – The number of samples to use (default is 1).
  • sigma (number, optional) – The width of the normal distribution (the default is 1).
  • correlate (bool, optional) – Should a multi-variate normal be used, with parameters set by the covariance matrix (True) or should a uni-variate normal be used (False)?
  • id (int or str, optional) – The data set containing the model expression. If not given then the default identifier is used, as returned by get_default_id.
  • otherids (sequence of int or str, optional) – For when multiple source expressions are being used.
  • numcores (optional) – The number of CPU cores to use. The default is to use all the cores on the machine.
Returns:

A NumPy array table with the first column representing the statistic and later columns the parameters used.

Return type:

samples

See also

fit()
Fit a model to one or more data sets.
set_model()
Set the source model expression for a data set.
set_stat()
Set the statistical method.
t_sample()
Sample from the Student’s t-distribution.
uniform_sample()
Sample from a uniform distribution.

Notes

All thawed model parameters are sampled from the Gaussian distribution, where the mean is set as the best-fit parameter value and the variance is determined by the diagonal elements of the covariance matrix. The multi-variate Gaussian is assumed by default for correlated parameters, using the off-diagonal elements of the covariance matrix.

Examples

The model fit to the default data set has three free parameters. The median value of the statistic calculated by normal_sample is returned:

>>> ans = normal_sample(num=10000)
>>> ans.shape
(1000, 4)
>>> np.median(ans[:,0])
119.82959326927781