get_pvalue_plot

Context: plotting

Synopsis

Access a histogram plot of likelihood ratio test results.

Syntax

get_pvalue_plot([null_model=None, alt_model=None, conv_model=None,
id=1, otherids=(), num=500, bins=25, numcores=None, recalc=False])

Access the data arrays and preferences defining the histogram plot produced by the plot_pvalue() function, a histogram of the likelihood ratios comparing fits of the null model to fits of the alternative model using faked data with Poisson noise. Data returned includes the likelihood ratio computed using the observed data, and the p-value, used to reject or accept the null model.

Arguments:

null_model - model representing the null hypothesis
alt_model - alternative model to compare to null
conv_model - convolution model (PSF or RSP) to include for fitting. default = None
id - Sherpa data id default = default data id
otherids - List of other Sherpa data ids default = ()
num - Number of iterations to run default = 500
bins - Number of bins for the histogram default = 25
numcores - Number of cpus to use during simulation default = number of detected cpus
recalc - Recalculate the likelihood ratio test simulation default = False

The get_pvalue_plot() function returns the following attributes:

ratios - likelihood ratios from 'num' iterations
lr - likelihood ratio on real, observed data
y - normalized frequencies of likelihood ratios
xlo - lower bin edges
xhi - upper bin edges

Example 1

sherpa> plot_pvalue(powlaw1d.p1, bpowlaw1d.bp1)
sherpa> print get_pvalue_plot()

ratios = [ 0.303   2.3149  0.5895 ..., -9.5852 -2.3156 -4.92  ]
lr = 12566.880545
xlo    = [-88.6406 -85.0598 -81.4791 ...,  -6.2833  -2.7026   0.8782]
xhi    = [-85.0598 -81.4791 -77.8983 ...,  -2.7026   0.8782   4.4589]
y      = [ 0.002  0.     0.    ...,  0.114  0.672  0.01 ]
xlabel = Likelihood Ratio
ylabel = Frequency
title  = Likelihood Ratio Distribution
histo_prefs = {'linethickness': None, 'symbolcolor': None, 'symbolfill': None, 'xlog': False, 'ylog': False, 'symbolangle': None, 'errthickness': None, 'fillcolor': None, 'linecolor': None, 'errstyle': None, 'linestyle': 1, 'symbolstyle': 0, 'errcolor': None, 'fillstyle': None, 'fillopacity': None, 'yerrorbars': False, 'symbolsize': None}

Call the get_pvalue_plot() command with no arguments to print to the screen the data arrays and preferences defining a histogram of likelihood ratios calculated using the plot_pvalue() command. View the arrays of ratios comparing fits to simulated data done with a simple (null) power-law model versus the more-complex (alternative) broken power-law model.

Example 2

sherpa> plot_pvalue(p1, p1+g1)
sherpa> my_lrt_plot = get_pvalue_plot()
sherpa> my_lrt_plot.ratios

array([ 0.303 ,  2.3149,  0.5895, ..., -9.5852, -2.3156, -4.92  ])

Store the data arrays and plot preferences returned by get_pvalue_plot() to variable "my_lrt_plot", in order to access and manipulate individual attributes within a script.

Bugs

See the bugs pages on the Sherpa website for an up-to-date listing of known bugs.