int_unc¶
-
sherpa.ui.
int_unc
(par, id=None, otherids=None, replot=False, min=None, max=None, nloop=20, delv=None, fac=1, log=False, numcores=None, overplot=False)¶ Calculate and plot the fit statistic versus fit parameter value.
Create a confidence plot of the fit statistic as a function of parameter value. Dashed lines are added to indicate the current statistic value and the parameter value at this point. The parameter value is varied over a grid of points and the statistic evaluated while holding the other parameters fixed. It is expected that this is run after a successful fit, so that the parameter values are at the best-fit location.
Parameters: - par – The parameter to plot.
- id (str or int, optional) –
- otherids (list of str or int, optional) – The id and otherids arguments determine which data set or data sets are used. If not given, all data sets which have a defined source model are used.
- replot (bool, optional) – Set to
True
to use the values calculated by the last call to int_proj. The default isFalse
. - min (number, optional) – The minimum parameter value for the calcutation. The
default value of
None
means that the limit is calculated from the covariance, using the fac value. - max (number, optional) – The maximum parameter value for the calcutation. The
default value of
None
means that the limit is calculated from the covariance, using the fac value. - nloop (int, optional) – The number of steps to use. This is used when delv is set
to
None
. - delv (number, optional) – The step size for the parameter. Setting this over-rides
the nloop parameter. The default is
None
. - fac (number, optional) – When min or max is not given, multiply the covariance of the parameter by this value to calculate the limit (which is then added or subtracted to the parameter value, as required).
- log (bool, optional) – Should the step size be logarithmically spaced? The
default (
False
) is to use a linear grid. - numcores (optional) – The number of CPU cores to use. The default is to use all the cores on the machine.
- overplot (bool, optional) – If
True
then add the data to an exsiting plot, otherwise create a new plot. The default isFalse
.
See also
conf()
- Estimate the confidence intervals using the confidence method.
covar()
- Estimate the confidence intervals using the covariance method.
get_int_unc()
- Return the interval-uncertainty object.
int_proj()
- Calculate and plot the fit statistic versus fit parameter value.
reg_unc()
- Plot the statistic value as two parameters are varied.
Notes
The difference to int_proj is that at each step only the single parameter value is varied while all other parameters remain at their starting value. This makes the result a less-accurate rendering of the projected shape of the hypersurface formed by the statistic, but the run-time is likely shorter than, the results of int_proj, which fits the model to the remaining thawed parameters at each step. If there are no free parameters in the source expression, other than the parameter being plotted, then the results will be the same.
Examples
Vary the
gamma
parameter of thep1
model component for all data sets with a source expression.>>> int_unc(p1.gamma)
Use only the data in data set 1:
>>> int_unc(p1.gamma, id=1)
Use two data sets (‘obs1’ and ‘obs2’):
>>> int_unc(clus.kt, id='obs1', otherids=['obs2'])
Vary the
bgnd.c0
parameter between 1e-4 and 2e-4, using 41 points:>>> int_unc(bgnd.c0, min=1e-4, max=2e-4, step=41)
This time define the step size, rather than the number of steps to use:
>>> int_unc(bgnd.c0, min=1e-4, max=2e-4, delv=2e-6)
Overplot the int_unc results for the parameter on top of the int_proj values:
>>> int_proj(mdl.xpos) >>> int_unc(mdl.xpos, overplot=True)