annotate toolboxes/FullBNT-1.0.7/KPMstats/chisquared_prob.m @ 0:e9a9cd732c1e tip

first hg version after svn
author wolffd
date Tue, 10 Feb 2015 15:05:51 +0000
parents
children
rev   line source
wolffd@0 1 function P = chisquared_prob(X2,v)
wolffd@0 2 %CHISQUARED_PROB computes the chi-squared probability function.
wolffd@0 3 % P = CHISQUARED_PROB( X2, v ) returns P(X2|v), the probability
wolffd@0 4 % of observing a chi-squared value <= X2 with v degrees of freedom.
wolffd@0 5 % This is the probability that the sum of squares of v unit-variance
wolffd@0 6 % normally-distributed random variables is <= X2.
wolffd@0 7 % X2 and v may be matrices of the same size size, or either
wolffd@0 8 % may be a scalar.
wolffd@0 9 %
wolffd@0 10 % e.g., CHISQUARED_PROB(5.99,2) returns 0.9500, verifying the
wolffd@0 11 % 95% confidence bound for 2 degrees of freedom. This is also
wolffd@0 12 % cross-checked in, e.g., Abramowitz & Stegun Table 26.8
wolffd@0 13 %
wolffd@0 14 % See also CHISQUARED_TABLE
wolffd@0 15 %
wolffd@0 16 %Peter R. Shaw, WHOI
wolffd@0 17
wolffd@0 18 % References: Press et al., Numerical Recipes, Cambridge, 1986;
wolffd@0 19 % Abramowitz & Stegun, Handbook of Mathematical Functions, Dover, 1972.
wolffd@0 20
wolffd@0 21 % Peter R. Shaw, Woods Hole Oceanographic Institution
wolffd@0 22 % Woods Hole, MA 02543
wolffd@0 23 % (508) 457-2000 ext. 2473 pshaw@whoi.edu
wolffd@0 24 % March, 1990; fixed Oct 1992 for version 4
wolffd@0 25
wolffd@0 26 % Computed using the Incomplete Gamma function,
wolffd@0 27 % as given by Press et al. (Recipes) eq. (6.2.17)
wolffd@0 28
wolffd@0 29 % Following nonsense is necessary from Matlab version 3 -> version 4
wolffd@0 30 versn_str=version; eval(['versn=' versn_str(1) ';']);
wolffd@0 31 if versn<=3, %sigh
wolffd@0 32 P = gamma(v/2, X2/2);
wolffd@0 33 else
wolffd@0 34 P = gammainc(X2/2, v/2);
wolffd@0 35 end