Plots the fit statistic as a function of parameter value, using the
PROJECTION algorithm.
The commands INT-PROJ and INTPROJ
are abbreviated equivalents.
sherpa> INTERVAL-PROJECTION [<dataset range> | ALLSETS] <arg>
where <dataset range> = #, or more generally #:#,#:#,..., such that #
specifies a dataset number, and #:# represents an inclusive range of
datasets; one may specify multiple inclusive ranges by separating them
with commas. The default is to create plots using data from all
appropriate datasets.
The command-line argument may be:
INTERVAL-PROJECTION Command Argument
| <sherpa_modelname>.{<paramname> | <#>} |
A specified model component parameter (e.g., GAUSS.pos). |
| <modelname>.{<paramname> | <#>} |
A specified model component parameter (e.g., g.pos). |
The user may configure INTERVAL-PROJECTION via
the Sherpa state object structure intproj.
The current values of the fields of this structure may be
displayed using the command print(sherpa.intproj),
or using the more verbose Sherpa/S-Lang module
function list_intproj().
The structure fields are:
intproj Structure Fields
| fast |
If 1, use a fast optimization algorithm
(LEVENBERG-MARQUARDT
or
SIMPLEX)
regardless of the current
METHOD.
If 0, use the current
METHOD. |
| expfac |
A multiplicative factor that expands the grid limits estimated by the
COVARIANCE
algorithm, if
the grid limits are determined automatically (see arange,
and below).
|
| arange |
If 1, the grid limits are to be determined automatically. If 0, the
grid limits are specified (see min and max).
|
| min |
Specifies the grid minimum.
This is always a linear quantity, regardless of the setting of
log (see below).
The setting is ignored if arange = 1.
|
| max |
Specifies the grid maximum.
This is always a linear quantity, regardless of the setting of
log (see below).
The setting is ignored if arange = 1.
|
| log |
Specifies whether to use a linear (0) or
logarithmic (1) spacing of grid points.
|
| nloop |
Specifies the number of grid points.
|
| sigma |
Specifies the number of sigma
(i.e., the change in statistic) for the plot.
|
Field values may be set using directly, e.g.,
sherpa> sherpa.intproj.arange = 0
NOTE: strict checking of value inputs is not done,
i.e., the user can errantly change arrays to scalars,
etc. To restore the default settings of the structure
at any time, use the Sherpa/S-Lang module function
restore_intproj().
The plot is created by varying each selected parameter's value on the
determined (arange = 1) or specified
(arange = 0) grid, and computing the
best-fit statistic at each grid point. INTERVAL-PROJECTION
differs from INTERVAL-UNCERTAINTY in
that all other thawed parameters are allowed to float to new best-fit
values, instead of being fixed to their best-fit values. This makes a
plot created by INTERVAL-PROJECTION a more accurate
rendering of the projected shape of statistical hypersurface, but
but causes the computation to proceed more slowly. For a fuller theoretical
description of error estimation, see PROJECTION, UNCERTAINTY, and COVARIANCE.
If arange = 1, then the grid limits
for the plot are determined automatically using the
PROJECTION algorithm. The selected
parameter's value is varied until the fit statistic is increased by
delta_S, which is a function of
INTERVAL-PROJECTION.sigma (e.g., delta_S = 1 if the statistic is chi-square and sigma = 1).
The grid-point values and best-fit statistics at each grid point may
be retrieved using the Sherpa/S-Lang module function
get_intproj. See the examples below.
List the current and default values of the intproj structure,
and restore the default values:
sherpa> sherpa.intproj.arange = 0
sherpa> sherpa.intproj.log = 1
sherpa> sherpa.intproj.sigma = 5
sherpa> list_intproj()
Parameter Current Default Description
----------------------------------------------------------------------
fast 1 1 Switch to LM/simplex: 0(n)/1(y)
expfac 3 3 Expansion factor for grid
arange 0 1 Auto-range: 0(n)/1(y)
min 0 0 Minimum value
max 0 0 Maximum value
log 1 0 Log-spacing: 0(n)/1(y)
nloop 20 20 Number of grid points
sigma 5 1 Number of sigma
sherpa> restore_intproj()
sherpa> list_intproj()
Parameter Current Default Description
----------------------------------------------------------------------
fast 1 1 Switch to LM/simplex: 0(n)/1(y)
expfac 3 3 Expansion factor for grid
arange 1 1 Auto-range: 0(n)/1(y)
min 0 0 Minimum value
max 0 0 Maximum value
log 0 0 Log-spacing: 0(n)/1(y)
nloop 20 20 Number of grid points
sigma 1 1 Number of sigma
Plot chi-square within the
3-sigma confidence interval for a fit:
sherpa> READ DATA example1.dat
sherpa> PARAMPROMPT OFF
sherpa> SOURCE = POLYNOM1D[my]
sherpa> THAW my.c1 my.c2
sherpa> my.c0.min = -10
sherpa> FIT
...
sherpa> sherpa.intproj.sigma = 3
sherpa> INTERVAL-PROJECTION my.c0
Interval-Projection: computing grid size with covariance...done.
outer grid loop 20% done...
outer grid loop 40% done...
outer grid loop 60% done...
outer grid loop 80% done...
Plot chi-square for the same fit within
manually set grid limits:
sherpa> sherpa.intproj.arange = 0
sherpa> sherpa.intproj.min = -25
sherpa> sherpa.intproj.max = 25
sherpa> INTERVAL-PROJECTION my.c0
Interval-Projection: grid size set by user.
outer grid loop 20% done...
outer grid loop 40% done...
outer grid loop 60% done...
outer grid loop 80% done...
Save the results of INTERVAL-PROJECTION to an ASCII file:
[...run INTERVAL-PROJECTION...]
sherpa> my_var = get_intproj()
sherpa> writeascii("my_output.dat",my_var.x0,my_var.y)
sherpa> quit
Goodbye.
unix> more my_output.dat
-25 34.2524
-22.3684 27.5464
-19.7368 21.5764
...
Prior to CIAO 3.2 the INTERVAL-PROJECTION command could not be used until the dataset had been fit. This was done to ensure that the parameter values were at their best-fit location, but caused problems when fitting multiple datasets or loading previously-saved analysis sessions. This restriction has now been removed. Please note that the results of INTERVAL-PROJECTION may not be valid unless the parameters are at their best-fit values.
- sherpa
-
berrors,
bsyserrors,
compute_errors,
compute_statistic,
covariance,
errors,
ftest,
get_paramest,
get_paramestint,
get_paramestlim,
get_paramestreg,
goodness,
interval-uncertainty,
list_paramest,
mlr,
projection,
region-projection,
region-uncertainty,
restore_paramest,
run_paramest,
run_paramestint,
run_paramestlim,
run_paramestreg,
set_errors,
set_syserrors,
staterrors,
syserrors,
uncertainty
|
![[CIAO Logo]](../imgs/ciao_logo_navbar.gif){kind=logo}