def calc_twosample_ts(propGroup1, propGroup2):
n1 = len(propGroup1[0])
n2 = len(propGroup2[0])
numFeatures = len(propGroup1)
T_statistics = []
effectSizes = []
notes = []
for r in xrange(0, numFeatures):
meanG1 = float(sum(propGroup1[r])) / n1
varG1 = variance(propGroup1[r], meanG1)
stdErrG1 = varG1 / n1
meanG2 = float(sum(propGroup2[r])) / n2
varG2 = variance(propGroup2[r], meanG2)
stdErrG2 = varG2 / n2
dp = meanG1 - meanG2
effectSizes.append(dp * 100)
denom = math.sqrt(stdErrG1 + stdErrG2)
if denom == 0:
notes.append(
'degenerate case: zero variance for both groups; variance set to 1e-6.'
)
T_statistics.append(dp / 1e-6)
else:
notes.append('')
T_statistics.append(dp / denom)
return T_statistics, effectSizes, notes
def calc_twosample_ts(propGroup1, propGroup2):
n1 = len(propGroup1[0])
n2 = len(propGroup2[0])
numFeatures = len(propGroup1)
T_statistics = []
effectSizes = []
notes = []
for r in xrange(0, numFeatures):
meanG1 = float(sum(propGroup1[r])) / n1
varG1 = variance(propGroup1[r], meanG1)
stdErrG1 = varG1 / n1
meanG2 = float(sum(propGroup2[r])) / n2
varG2 = variance(propGroup2[r], meanG2)
stdErrG2 = varG2 / n2
dp = meanG1 - meanG2
effectSizes.append(dp*100)
denom = math.sqrt(stdErrG1 + stdErrG2)
if denom == 0:
notes.append('degenerate case: zero variance for both groups; variance set to 1e-6.')
T_statistics.append(dp/1e-6)
else:
notes.append('')
T_statistics.append(dp/denom)
return T_statistics, effectSizes, notes
def run(self, seqGroup1, seqGroup2, parentSeqGroup1, parentSeqGroup2, confIntervMethod, coverage): note = '' n1 = len(seqGroup1) n2 = len(seqGroup2) if n1 >= 2 and n2 >= 2: # calculate proportions propGroup1 = [] for i in xrange(0, n1): propGroup1.append(float(seqGroup1[i]) / parentSeqGroup1[i]) propGroup2 = [] for i in xrange(0, n2): propGroup2.append(float(seqGroup2[i]) / parentSeqGroup2[i]) # calculate p-value, effect size, and CI meanG1 = float(sum(propGroup1)) / n1 meanG2 = float(sum(propGroup2)) / n2 dp = meanG1 - meanG2 varG1 = variance(propGroup1, meanG1) varG2 = variance(propGroup2, meanG2) normVarG1 = varG1 / n1 normVarG2 = varG2 / n2 unpooledVar = normVarG1 + normVarG2 sqrtUnpooledVar = math.sqrt(unpooledVar) if unpooledVar != 0: # p-value T_statistic = (meanG1 - meanG2) / sqrtUnpooledVar dof = (unpooledVar*unpooledVar) / ( (normVarG1*normVarG1)/(n1-1) + (normVarG2*normVarG2)/(n2-1) ) pValue = t.cdf(T_statistic, dof) # CI tCritical = t.isf(0.5 * (1.0-coverage), dof) # 0.5 factor accounts from symmetric nature of distribution lowerCI = dp - tCritical*sqrtUnpooledVar upperCI = dp + tCritical*sqrtUnpooledVar else: if meanG1 != meanG2: pValue = 0.0 # the difference (at least according to these samples) must be true as there is no variance else: pValue = 0.5 lowerCI = dp upperCI = dp note = 'degenerate case: variance of both groups is zero' else: pValue = 0.5 lowerCI = 0.0 upperCI = 0.0 dp = 0.0 note = 'degenerate case: both groups must contain at least 2 samples' return 1.0 - pValue, 2*min(pValue, 1.0 - pValue), lowerCI*100, upperCI*100, dp*100, note
def run(self, seqGroup1, seqGroup2, parentSeqGroup1, parentSeqGroup2, confIntervMethod, coverage):
note = ''
n1 = len(seqGroup1)
n2 = len(seqGroup2)
try:
if n1 < 2 or n2 < 2:
raise Exception('degenerate case: both groups must contain at least 2 samples')
# calculate proportions
propGroup1 = []
for i in xrange(0, n1):
propGroup1.append(float(seqGroup1[i]) / parentSeqGroup1[i])
propGroup2 = []
for i in xrange(0, n2):
propGroup2.append(float(seqGroup2[i]) / parentSeqGroup2[i])
# calculate statistics
meanG1 = float(sum(propGroup1)) / n1
meanG2 = float(sum(propGroup2)) / n2
dp = meanG1 - meanG2
varG1 = variance(propGroup1, meanG1)
varG2 = variance(propGroup2, meanG2)
dof = n1 + n2 - 2
pooledVar = ((n1 - 1)*varG1 + (n2 - 1)*varG2) / (n1 + n2 - 2)
sqrtPooledVar = math.sqrt(pooledVar)
denom = sqrtPooledVar * math.sqrt(1.0/n1 + 1.0/n2)
# p-value
T_statistic = (meanG1 - meanG2) / denom
pValue = t.cdf(T_statistic, dof)
# CI
tCritical = t.isf(0.5 * (1.0-coverage), dof) # 0.5 factor accounts from symmetric nature of distribution
lowerCI = dp - tCritical*denom
upperCI = dp + tCritical*denom
except Exception as note:
pValue = 0.5
lowerCI = 0.0
upperCI = 0.0
dp = 0.0
except ZeroDivisionError:
if meanG1 != meanG2:
pValue = 0.0 # the difference (at least according to these samples) must be true as there is no variance
else:
pValue = 0.5
lowerCI = dp
upperCI = dp
note = 'degenerate case: variance of both groups is zero'
return 1.0 - pValue, 2*min(pValue, 1.0 - pValue), lowerCI*100, upperCI*100, dp*100, note
#=======================================================================
def run(self, seqGroup1, seqGroup2, parentSeqGroup1, parentSeqGroup2, confIntervMethod, coverage):
note = ''
n1 = len(seqGroup1)
n2 = len(seqGroup2)
try:
if n1 < 2 or n2 < 2:
raise Exception('degenerate case: both groups must contain at least 2 samples')
# calculate proportions
propGroup1 = []
for i in xrange(0, n1):
if parentSeqGroup1[i] > 0:
propGroup1.append(float(seqGroup1[i]) / parentSeqGroup1[i])
else:
propGroup1.append( 0.0 )
note = 'degenerate case: parent group had a count of zero'
propGroup2 = []
for i in xrange(0, n2):
if parentSeqGroup2[i] > 0:
propGroup2.append(float(seqGroup2[i]) / parentSeqGroup2[i])
else:
propGroup2.append( 0.0 )
note = 'degenerate case: parent group had a count of zero'
# calculate statistics
meanG1 = float(sum(propGroup1)) / n1
meanG2 = float(sum(propGroup2)) / n2
dp = meanG1 - meanG2
varG1 = variance(propGroup1, meanG1)
varG2 = variance(propGroup2, meanG2)
dof = n1 + n2 - 2
pooledVar = ((n1 - 1)*varG1 + (n2 - 1)*varG2) / (n1 + n2 - 2)
sqrtPooledVar = math.sqrt(pooledVar)
denom = sqrtPooledVar * math.sqrt(1.0/n1 + 1.0/n2)
# p-value
T_statistic = (meanG1 - meanG2) / denom
pValue = t.cdf(T_statistic, dof)
# CI
tCritical = t.isf(0.5 * (1.0-coverage), dof) # 0.5 factor accounts from symmetric nature of distribution
lowerCI = dp - tCritical*denom
upperCI = dp + tCritical*denom
except Exception as note:
pValue = 0.5
lowerCI = 0.0
upperCI = 0.0
dp = 0.0
except ZeroDivisionError:
if meanG1 != meanG2:
pValue = 0.0 # the difference (at least according to these samples) must be true as there is no variance
else:
pValue = 0.5
lowerCI = dp
upperCI = dp
note = 'degenerate case: variance of both groups is zero'
return 1.0 - pValue, 2*min(pValue, 1.0 - pValue), lowerCI*100, upperCI*100, dp*100, note
#=======================================================================
#=======================================================================
def run(self, seqGroup1, seqGroup2, parentSeqGroup1, parentSeqGroup2,
confIntervMethod, coverage):
note = ''
n1 = len(seqGroup1)
n2 = len(seqGroup2)
if n1 >= 2 and n2 >= 2:
# calculate proportions
propGroup1 = []
for i in xrange(0, n1):
if parentSeqGroup1[i] > 0:
propGroup1.append(float(seqGroup1[i]) / parentSeqGroup1[i])
else:
propGroup1.append(0.0)
note = 'degenerate case: parent group had a count of zero'
propGroup2 = []
for i in xrange(0, n2):
if parentSeqGroup2[i] > 0:
propGroup2.append(float(seqGroup2[i]) / parentSeqGroup2[i])
else:
propGroup2.append(0.0)
note = 'degenerate case: parent group had a count of zero'
# calculate p-value, effect size, and CI
meanG1 = float(sum(propGroup1)) / n1
meanG2 = float(sum(propGroup2)) / n2
dp = meanG1 - meanG2
varG1 = variance(propGroup1, meanG1)
varG2 = variance(propGroup2, meanG2)
normVarG1 = varG1 / n1
normVarG2 = varG2 / n2
unpooledVar = normVarG1 + normVarG2
sqrtUnpooledVar = math.sqrt(unpooledVar)
if unpooledVar != 0:
# p-value
T_statistic = (meanG1 - meanG2) / sqrtUnpooledVar
dof = (unpooledVar * unpooledVar) / ((normVarG1 * normVarG1) /
(n1 - 1) +
(normVarG2 * normVarG2) /
(n2 - 1))
pValue = t.cdf(T_statistic, dof)
# CI
tCritical = t.isf(
0.5 * (1.0 - coverage), dof
) # 0.5 factor accounts from symmetric nature of distribution
lowerCI = dp - tCritical * sqrtUnpooledVar
upperCI = dp + tCritical * sqrtUnpooledVar
else:
if meanG1 != meanG2:
pValue = 0.0 # the difference (at least according to these samples) must be true as there is no variance
else:
pValue = 0.5
lowerCI = dp
upperCI = dp
note = 'degenerate case: variance of both groups is zero'
else:
pValue = 0.5
lowerCI = 0.0
upperCI = 0.0
dp = 0.0
note = 'degenerate case: both groups must contain at least 2 samples'
return 1.0 - pValue, 2 * min(
pValue, 1.0 - pValue), lowerCI * 100, upperCI * 100, dp * 100, note
#=======================================================================