def stat(self, baseline=0.0):
"""
Return the decision statistic associated with the test of the
null hypothesis: (H0) 'contrast equals baseline'
"""
self._baseline = baseline
# Case: one-dimensional contrast ==> t or t**2
if self.dim == 1:
# avoids division by zero
t = (self.effect-baseline) / np.sqrt(np.maximum(self.variance, self._tiny))
if self.type == 'F':
t = t**2
# Case: F contrast
elif self.type == 'F':
# F = |t|^2/q , |t|^2 = e^t v-1 e
t = mahalanobis(self.effect-baseline, np.maximum(self.variance, self._tiny))/self.dim
# Case: tmin (conjunctions)
elif self.type == 'tmin':
vdiag = self.variance.reshape([self.dim**2]+list(self.variance.shape[2:]))[::self.dim+1]
t = (self.effect-baseline) / np.sqrt(np.maximum(vdiag, self._tiny))
t = t.min(0)
# Unknwon stat
else:
raise ValueError, 'Unknown statistic type'
self._stat = t
return t
def test_mahalanobis2(self):
x = rand(100,3,4)
Aa = zeros([100,100,3,4])
for i in range(3):
for j in range(4):
A = rand(100,100)
A = dot(A.transpose(), A)
Aa[:,:,i,j] = A
i = randint(3)
j = randint(4)
mah = dot(x[:,i,j], dot(inv(Aa[:,:,i,j]), x[:,i,j]))
f_mah = (fu.mahalanobis(x, Aa))[i,j]
assert_almost_equal(mah, f_mah, decimal=3)
def test_mahalanobis(self):
x = rand(100)
A = rand(100, 100)
A = dot(A.transpose(), A)
mah = dot(x, dot(inv(A), x))
assert_almost_equal(mah, fu.mahalanobis(x, A), decimal=1)