Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[nominal two samples] improve comments #142

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[nominal two samples] improve comments #142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 14 additions & 9 deletions nominal/paired_two_sample_test_of_nominal_scale.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
class PairedTwoSampleTestOfNominalScale:
def test(self, data):
"""
There is a question which we can answer yes (1) or no (0).
data = {"Before": [1,1,1,1,1,...,0], "After": [1,1,1,1,1,...,0]}

Yes No Total
Expand All @@ -26,10 +27,10 @@ def test(self, data):
number of Yes => No: b
number of No => Yes: c
"""
# check data length is 2
if len(data.keys()) != 2 and len(data[data.keys()[0]]) != len(data[data.keys()[1]]):
print "Please check the components of your data."
print "length of data should be four"
# check if the number of samples are appropriate
if len(data.keys()) != 2 or len(data[data.keys()[0]]) != len(data[data.keys()[1]]):
print ("Please check the components of your data.")
print ("the number of each data should be equal")
sys.exit()
else:
b = 0
Expand All @@ -39,13 +40,17 @@ def test(self, data):
b += 1
elif data[(data.keys())[0]][i] == 0 and data[(data.keys())[1]][i] == 1:
c += 1
# z = abs(b-c)-1 / root(b+c)
# chi2 = pow((abs(b-c)-1), 2.0) / (b+c)
# calculating chi-square value with Yate's continuity correction (イェーツの連続修正)
chi2 = pow((abs(b-c)-1), 2.0) / (b+c)

'''
If there is no consideration on Yate's continuity correction:
chi2 = pow(abs(b-c) - 1.0, 2.0) / (b+c)
'''
p = stats.chi2.pdf(chi2, df=1)
# pdf: probability density function
# cdf: Cumulative distribution function
# https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.chi2.html
print "chi2 value: {}".format(chi2)
print "p value: {}".format(p)
return p

if __name__ == '__main__':
pass
18 changes: 8 additions & 10 deletions nominal/unpaired_two_sample_test_of_nominal_scale.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,27 +6,25 @@

class UnpairedTwoSampleTestOfNominalScale:
def test(self, data):
# check data length
if len(data.keys()) != 2:
print "len(data.keys()) should be two"
sys.exit()
elif len(data[(data.keys())[0]]) != len(data[(data.keys())[1]]):
print "len(data[(data.keys())[0]]) and len(data[(data.keys())[1]]) should be same"
# check if the number of samples are appropriate
if len(data.keys()) != 2 or len(data[data.keys()[0]]) != len(data[data.keys()[1]]):
print ("Please check the components of your data.")
print ("the number of each data should be equal")
sys.exit()
else:
"""
Is there any difference between the number of people who satisfies Condition1 and Yes (a) and that of people who satisfies Condition2 and Yes (c)?
Is there any difference between the number of people who satisfies Condition1 as Yes (a) and that of people who satisfies Condition2 as Yes (c)?
data = {"Condition1": [a, b], "Condition2": [c, d]}
OrderedDict([('Illness', [52, 8]), ('Healty', [48, 42])])
ex. OrderedDict([('Illness', [52, 8]), ('Healty', [48, 42])])

Yes No Total <= sum_row
Yes No Total <= sum_row: [a+b, c+d]
--------------------------------------
Condition1 a b a+b
Condition2 c d c+d
--------------------------------------
Total a+c b+d n (= a+b+c+d)
^
|_ sum_column
|_ sum_column: [a+c, b+d]

"""
# calculate n
Expand Down