def test_significant():
# Some test data and test code taken from example at:
# http://www.jarrodmillman.com/rcsds/lectures/glm_intro.html
psychopathy = [11.416, 4.514, 12.204, 14.835,
8.416, 6.563, 17.343, 13.02,
15.19 , 11.902, 22.721, 22.324]
clammy = [0.389, 0.2 , 0.241, 0.463,
4.585, 1.097, 1.642, 4.972,
7.957, 5.585, 5.527, 6.964]
def t_stat(y, X, c):
""" betas, t statistic and significance test given data, design matrix, contrast
This is OLS estimation; we assume the errors to have independent
and identical normal distributions around zero for each $i$ in
$\e_i$ (i.i.d).
"""
# Make sure y, X, c are all arrays
y = np.asarray(y)
X = np.asarray(X)
c = np.atleast_2d(c).T # As column vector
# Calculate the parameters - b hat
beta = npl.pinv(X).dot(y)
# The fitted values - y hat
fitted = X.dot(beta)
# Residual error
errors = y - fitted
# Residual sum of squares
RSS = (errors**2).sum(axis=0)
# Degrees of freedom is the number of observations n minus the number
# of independent regressors we have used. If all the regressor
# columns in X are independent then the (matrix rank of X) == p
# (where p the number of columns in X). If there is one column that
# can be expressed as a linear sum of the other columns then
# (matrix rank of X) will be p - 1 - and so on.
df = X.shape[0] - npl.matrix_rank(X)
# Mean residual sum of squares
MRSS = RSS / df
# calculate bottom half of t statistic
SE = np.sqrt(MRSS * c.T.dot(npl.pinv(X.T.dot(X)).dot(c)))
t = c.T.dot(beta) / SE
# Get p value for t value using cumulative density dunction
# (CDF) of t distribution
ltp = t_dist.cdf(t, df) # lower tail p
p = 1 - ltp # upper tail p
return beta, t, df, p
X = np.column_stack((np.ones(12), clammy))
Y = np.asarray(psychopathy)
B1, t1, df1, p1 = t_stat(Y, X, [1, 0])
B2, t2, df2, p2 = t_stat(Y, X, [0, 1])
#---------------------------------------------------------#
# my function
myt1, myt2 = significant(X, Y, B1)
# assert
assert_almost_equal(t1.ravel(), myt1)
assert_almost_equal(t2.ravel(), myt2)
boldname='ds005/sub0'+str(i).zfill(2)+'/model/model001/task001_run00'+`j`+'.feat/filtered_func_data_mni.nii.gz'
img=nib.load(boldname)
data=img.get_data()
data=smooth_spatial(data)
run = j
behav_cond = 'ds005/sub0'+str(i).zfill(2)+'/behav/task001_run00'+`j`+'/behavdata.txt'
task_cond1 = 'ds005/sub0'+str(i).zfill(2)+'/model/model001/onsets/task001_run00'+`j`+'/cond001.txt'
task_cond2 = 'ds005/sub0'+str(i).zfill(2)+'/model/model001/onsets/task001_run00'+`j`+'/cond002.txt'
task_cond3 = 'ds005/sub0'+str(i).zfill(2)+'/model/model001/onsets/task001_run00'+`j`+'/cond003.txt'
task_cond4 = 'ds005/sub0'+str(i).zfill(2)+'/model/model001/onsets/task001_run00'+`j`+'/cond004.txt'
parameters = merge_cond(behav_cond, task_cond1, task_cond2, task_cond3, task_cond4)
neural_prediction = events2neural_extend(parameters,TR, n_vols)
gain, loss, linear_dr, quad_dr = getRegressor(TR, n_vols, hrf_at_trs, neural_prediction, standard = True)
data, gain, loss, linear_dr, quad_dr = deleteOutliers(data, gain, loss, i, run, dvars_out, fd_out)
data_full = np.concatenate((data_full,data),axis=3)
gain_full = np.concatenate((gain_full,gain),axis=0)
loss_full = np.concatenate((loss_full,loss),axis=0)
# mea=calcMRSS(data_full, gain_full, loss_full, None, None, threshold)
X, Y, beta=calcBeta(data_full, gain_full, loss_full, None, None, threshold)
# calculate t values
t_val=np.zeros((2,902629))
for k in range(Y.shape[1]):
t_val[:,k] = significant(X,Y[:,k], beta[:,k])
# file names for beta and t
beta_file='../results/texts/sub0'+str(i).zfill(2)+'_standard_beta.txt'
t_file='../results/texts/sub0'+str(i).zfill(2)+'_standard_tvals.txt'
# save beta and t values to file
np.savetxt(beta_file, beta)
np.savetxt(t_file, t_val)
