Contingency tables

Statsmodels supports a variety of approaches for analyzing contingency tables, including methods for assessing independence, symmetry, homogeneity, and methods for working with collections of tables from a stratified population.

The methods described here are mainly for two-way tables. Multi-way tables can be analyzed using log-linear models. Statsmodels does not currently have a dedicated API for loglinear modeling, but Poisson regression in statsmodels.genmod.GLM can be used for this purpose.

A contingency table is a multi-way table that describes a data set in which each observation belongs to one category for each of several variables. For example, if there are two variables, one with r levels and one with c levels, then we have a r \times c contingency table. The table can be described in terms of the number of observations that fall into a given cell of the table, e.g. T_{ij} is the number of observations that have level i for the first variable and level j for the second variable. Note that each variable must have a finite number of levels (or categories), which can be either ordered or unordered. In different contexts, the variables defining the axes of a contingency table may be called categorical variables or factor variables. They may be either nominal (if their levels are unordered) or ordinal (if their levels are ordered).

The underlying population for a contingency table is described by a distribution table P_{i, j}. The elements of P are probabilities, and the sum of all elements in P is 1. Methods for analyzing contingency tables use the data in T to learn about properties of P.

The statsmodels.stats.Table is the most basic class for working with contingency tables. We can create a Table object directly from any rectangular array-like object containing the contingency table cell counts:

In [1]: import numpy as np

In [2]: import pandas as pd

In [3]: import statsmodels.api as sm

In [4]: df = sm.datasets.get_rdataset("Arthritis", "vcd", cache=True).data
---------------------------------------------------------------------------
gaierror                                  Traceback (most recent call last)
/usr/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
   1317                 h.request(req.get_method(), req.selector, req.data, headers,
-> 1318                           encode_chunked=req.has_header('Transfer-encoding'))
   1319             except OSError as err: # timeout error

/usr/lib/python3.6/http/client.py in request(self, method, url, body, headers, encode_chunked)
   1238         """Send a complete request to the server."""
-> 1239         self._send_request(method, url, body, headers, encode_chunked)
   1240 

/usr/lib/python3.6/http/client.py in _send_request(self, method, url, body, headers, encode_chunked)
   1284             body = _encode(body, 'body')
-> 1285         self.endheaders(body, encode_chunked=encode_chunked)
   1286 

/usr/lib/python3.6/http/client.py in endheaders(self, message_body, encode_chunked)
   1233             raise CannotSendHeader()
-> 1234         self._send_output(message_body, encode_chunked=encode_chunked)
   1235 

/usr/lib/python3.6/http/client.py in _send_output(self, message_body, encode_chunked)
   1025         del self._buffer[:]
-> 1026         self.send(msg)
   1027 

/usr/lib/python3.6/http/client.py in send(self, data)
    963             if self.auto_open:
--> 964                 self.connect()
    965             else:

/usr/lib/python3.6/http/client.py in connect(self)
   1391 
-> 1392             super().connect()
   1393 

/usr/lib/python3.6/http/client.py in connect(self)
    935         self.sock = self._create_connection(
--> 936             (self.host,self.port), self.timeout, self.source_address)
    937         self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)

/usr/lib/python3.6/socket.py in create_connection(address, timeout, source_address)
    703     err = None
--> 704     for res in getaddrinfo(host, port, 0, SOCK_STREAM):
    705         af, socktype, proto, canonname, sa = res

/usr/lib/python3.6/socket.py in getaddrinfo(host, port, family, type, proto, flags)
    744     addrlist = []
--> 745     for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
    746         af, socktype, proto, canonname, sa = res

gaierror: [Errno -2] Name or service not known

During handling of the above exception, another exception occurred:

URLError                                  Traceback (most recent call last)
<ipython-input-4-30b371d59b8a> in <module>()
----> 1 df = sm.datasets.get_rdataset("Arthritis", "vcd", cache=True).data

/build/statsmodels-JytjB9/statsmodels-0.8.0/.pybuild/cpython3_3.6_statsmodels/build/statsmodels/datasets/utils.py in get_rdataset(dataname, package, cache)
    288                      "master/doc/"+package+"/rst/")
    289     cache = _get_cache(cache)
--> 290     data, from_cache = _get_data(data_base_url, dataname, cache)
    291     data = read_csv(data, index_col=0)
    292     data = _maybe_reset_index(data)

/build/statsmodels-JytjB9/statsmodels-0.8.0/.pybuild/cpython3_3.6_statsmodels/build/statsmodels/datasets/utils.py in _get_data(base_url, dataname, cache, extension)
    219     url = base_url + (dataname + ".%s") % extension
    220     try:
--> 221         data, from_cache = _urlopen_cached(url, cache)
    222     except HTTPError as err:
    223         if '404' in str(err):

/build/statsmodels-JytjB9/statsmodels-0.8.0/.pybuild/cpython3_3.6_statsmodels/build/statsmodels/datasets/utils.py in _urlopen_cached(url, cache)
    210     # not using the cache or didn't find it in cache
    211     if not from_cache:
--> 212         data = urlopen(url).read()
    213         if cache is not None:  # then put it in the cache
    214             _cache_it(data, cache_path)

/usr/lib/python3.6/urllib/request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
    221     else:
    222         opener = _opener
--> 223     return opener.open(url, data, timeout)
    224 
    225 def install_opener(opener):

/usr/lib/python3.6/urllib/request.py in open(self, fullurl, data, timeout)
    524             req = meth(req)
    525 
--> 526         response = self._open(req, data)
    527 
    528         # post-process response

/usr/lib/python3.6/urllib/request.py in _open(self, req, data)
    542         protocol = req.type
    543         result = self._call_chain(self.handle_open, protocol, protocol +
--> 544                                   '_open', req)
    545         if result:
    546             return result

/usr/lib/python3.6/urllib/request.py in _call_chain(self, chain, kind, meth_name, *args)
    502         for handler in handlers:
    503             func = getattr(handler, meth_name)
--> 504             result = func(*args)
    505             if result is not None:
    506                 return result

/usr/lib/python3.6/urllib/request.py in https_open(self, req)
   1359         def https_open(self, req):
   1360             return self.do_open(http.client.HTTPSConnection, req,
-> 1361                 context=self._context, check_hostname=self._check_hostname)
   1362 
   1363         https_request = AbstractHTTPHandler.do_request_

/usr/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
   1318                           encode_chunked=req.has_header('Transfer-encoding'))
   1319             except OSError as err: # timeout error
-> 1320                 raise URLError(err)
   1321             r = h.getresponse()
   1322         except:

URLError: <urlopen error [Errno -2] Name or service not known>

In [5]: tab = pd.crosstab(df['Treatment'], df['Improved'])
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-5-15ac28c3b344> in <module>()
----> 1 tab = pd.crosstab(df['Treatment'], df['Improved'])

NameError: name 'df' is not defined

In [6]: tab = tab.loc[:, ["None", "Some", "Marked"]]
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-6-35c7697d04d2> in <module>()
----> 1 tab = tab.loc[:, ["None", "Some", "Marked"]]

NameError: name 'tab' is not defined

In [7]: table = sm.stats.Table(tab)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-7-c4347556c2e2> in <module>()
----> 1 table = sm.stats.Table(tab)

NameError: name 'tab' is not defined

Alternatively, we can pass the raw data and let the Table class construct the array of cell counts for us:

In [8]: table = sm.stats.Table.from_data(df[["Treatment", "Improved"]])
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-8-7482675bef59> in <module>()
----> 1 table = sm.stats.Table.from_data(df[["Treatment", "Improved"]])

NameError: name 'df' is not defined

Independence

Independence is the property that the row and column factors occur independently. Association is the lack of independence. If the joint distribution is independent, it can be written as the outer product of the row and column marginal distributions:

P_{ij} = sum_k P_{ij} cdot sum_k P_{kj} forall i, j

We can obtain the best-fitting independent distribution for our observed data, and then view residuals which identify particular cells that most strongly violate independence:

In [9]: print(table.table_orig)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-9-bdebfcd351e6> in <module>()
----> 1 print(table.table_orig)

NameError: name 'table' is not defined

In [10]: print(table.fittedvalues)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-10-93e2447e60fa> in <module>()
----> 1 print(table.fittedvalues)

NameError: name 'table' is not defined

In [11]: print(table.resid_pearson)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-11-3c1bd716f10e> in <module>()
----> 1 print(table.resid_pearson)

NameError: name 'table' is not defined

In this example, compared to a sample from a population in which the rows and columns are independent, we have too many observations in the placebo/no improvement and treatment/marked improvement cells, and too few observations in the placebo/marked improvement and treated/no improvement cells. This reflects the apparent benefits of the treatment.

If the rows and columns of a table are unordered (i.e. are nominal factors), then the most common approach for formally assessing independence is using Pearson’s \chi^2 statistic. It’s often useful to look at the cell-wise contributions to the \chi^2 statistic to see where the evidence for dependence is coming from.

In [12]: rslt = table.test_nominal_association()
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-12-2ec3a2583cea> in <module>()
----> 1 rslt = table.test_nominal_association()

NameError: name 'table' is not defined

In [13]: print(rslt.pvalue)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-13-f241230dd807> in <module>()
----> 1 print(rslt.pvalue)

NameError: name 'rslt' is not defined

In [14]: print(table.chi2_contribs)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-14-f130716672e5> in <module>()
----> 1 print(table.chi2_contribs)

NameError: name 'table' is not defined

For tables with ordered row and column factors, we can us the linear by linear association test to obtain more power against alternative hypotheses that respect the ordering. The test statistic for the linear by linear association test is

sum_k r_i c_j T_{ij}

where r_i and c_j are row and column scores. Often these scores are set to the sequences 0, 1, …. This gives the ‘Cochran-Armitage trend test’.

In [15]: rslt = table.test_ordinal_association()
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-15-26fa82556e55> in <module>()
----> 1 rslt = table.test_ordinal_association()

NameError: name 'table' is not defined

In [16]: print(rslt.pvalue)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-16-f241230dd807> in <module>()
----> 1 print(rslt.pvalue)

NameError: name 'rslt' is not defined

We can assess the association in a r\times x table by constructing a series of 2\times 2 tables and calculating their odds ratios. There are two ways to do this. The local odds ratios construct 2\times 2 tables from adjacent row and column categories.

In [17]: print(table.local_oddsratios)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-17-2deb641370f6> in <module>()
----> 1 print(table.local_oddsratios)

NameError: name 'table' is not defined

In [18]: taloc = sm.stats.Table2x2(np.asarray([[7, 29], [21, 13]]))

In [19]: print(taloc.oddsratio)
0.14942528735632185

In [20]: taloc = sm.stats.Table2x2(np.asarray([[29, 7], [13, 7]]))

In [21]: print(taloc.oddsratio)
2.230769230769231

The cumulative odds ratios construct 2\times 2 tables by dichotomizing the row and column factors at each possible point.

In [22]: print(table.cumulative_oddsratios)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-22-c6bac8968cdc> in <module>()
----> 1 print(table.cumulative_oddsratios)

NameError: name 'table' is not defined

In [23]: tab1 = np.asarray([[7, 29 + 7], [21, 13 + 7]])

In [24]: tacum = sm.stats.Table2x2(tab1)

In [25]: print(tacum.oddsratio)
0.18518518518518517

In [26]: tab1 = np.asarray([[7 + 29, 7], [21 + 13, 7]])

In [27]: tacum = sm.stats.Table2x2(tab1)

In [28]: print(tacum.oddsratio)
1.0588235294117647

A mosaic plot is a graphical approach to informally assessing dependence in two-way tables.

from statsmodels.graphics.mosaicplot import mosaic
mosaic(data)

Symmetry and homogeneity

Symmetry is the property that P_{i, j} = P_{j, i} for every i and j. Homogeneity is the property that the marginal distribution of the row factor and the column factor are identical, meaning that

sum_j P_{ij} = sum_j P_{ji} forall i

Note that for these properties to be applicable the table P (and T) must be square, and the row and column categories must be identical and must occur in the same order.

To illustrate, we load a data set, create a contingency table, and calculate the row and column margins. The Table class contains methods for analyzing r \times c contingency tables. The data set loaded below contains assessments of visual acuity in people’s left and right eyes. We first load the data and create a contingency table.

In [29]: df = sm.datasets.get_rdataset("VisualAcuity", "vcd").data
---------------------------------------------------------------------------
gaierror                                  Traceback (most recent call last)
/usr/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
   1317                 h.request(req.get_method(), req.selector, req.data, headers,
-> 1318                           encode_chunked=req.has_header('Transfer-encoding'))
   1319             except OSError as err: # timeout error

/usr/lib/python3.6/http/client.py in request(self, method, url, body, headers, encode_chunked)
   1238         """Send a complete request to the server."""
-> 1239         self._send_request(method, url, body, headers, encode_chunked)
   1240 

/usr/lib/python3.6/http/client.py in _send_request(self, method, url, body, headers, encode_chunked)
   1284             body = _encode(body, 'body')
-> 1285         self.endheaders(body, encode_chunked=encode_chunked)
   1286 

/usr/lib/python3.6/http/client.py in endheaders(self, message_body, encode_chunked)
   1233             raise CannotSendHeader()
-> 1234         self._send_output(message_body, encode_chunked=encode_chunked)
   1235 

/usr/lib/python3.6/http/client.py in _send_output(self, message_body, encode_chunked)
   1025         del self._buffer[:]
-> 1026         self.send(msg)
   1027 

/usr/lib/python3.6/http/client.py in send(self, data)
    963             if self.auto_open:
--> 964                 self.connect()
    965             else:

/usr/lib/python3.6/http/client.py in connect(self)
   1391 
-> 1392             super().connect()
   1393 

/usr/lib/python3.6/http/client.py in connect(self)
    935         self.sock = self._create_connection(
--> 936             (self.host,self.port), self.timeout, self.source_address)
    937         self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)

/usr/lib/python3.6/socket.py in create_connection(address, timeout, source_address)
    703     err = None
--> 704     for res in getaddrinfo(host, port, 0, SOCK_STREAM):
    705         af, socktype, proto, canonname, sa = res

/usr/lib/python3.6/socket.py in getaddrinfo(host, port, family, type, proto, flags)
    744     addrlist = []
--> 745     for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
    746         af, socktype, proto, canonname, sa = res

gaierror: [Errno -2] Name or service not known

During handling of the above exception, another exception occurred:

URLError                                  Traceback (most recent call last)
<ipython-input-29-bd62c2610a72> in <module>()
----> 1 df = sm.datasets.get_rdataset("VisualAcuity", "vcd").data

/build/statsmodels-JytjB9/statsmodels-0.8.0/.pybuild/cpython3_3.6_statsmodels/build/statsmodels/datasets/utils.py in get_rdataset(dataname, package, cache)
    288                      "master/doc/"+package+"/rst/")
    289     cache = _get_cache(cache)
--> 290     data, from_cache = _get_data(data_base_url, dataname, cache)
    291     data = read_csv(data, index_col=0)
    292     data = _maybe_reset_index(data)

/build/statsmodels-JytjB9/statsmodels-0.8.0/.pybuild/cpython3_3.6_statsmodels/build/statsmodels/datasets/utils.py in _get_data(base_url, dataname, cache, extension)
    219     url = base_url + (dataname + ".%s") % extension
    220     try:
--> 221         data, from_cache = _urlopen_cached(url, cache)
    222     except HTTPError as err:
    223         if '404' in str(err):

/build/statsmodels-JytjB9/statsmodels-0.8.0/.pybuild/cpython3_3.6_statsmodels/build/statsmodels/datasets/utils.py in _urlopen_cached(url, cache)
    210     # not using the cache or didn't find it in cache
    211     if not from_cache:
--> 212         data = urlopen(url).read()
    213         if cache is not None:  # then put it in the cache
    214             _cache_it(data, cache_path)

/usr/lib/python3.6/urllib/request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
    221     else:
    222         opener = _opener
--> 223     return opener.open(url, data, timeout)
    224 
    225 def install_opener(opener):

/usr/lib/python3.6/urllib/request.py in open(self, fullurl, data, timeout)
    524             req = meth(req)
    525 
--> 526         response = self._open(req, data)
    527 
    528         # post-process response

/usr/lib/python3.6/urllib/request.py in _open(self, req, data)
    542         protocol = req.type
    543         result = self._call_chain(self.handle_open, protocol, protocol +
--> 544                                   '_open', req)
    545         if result:
    546             return result

/usr/lib/python3.6/urllib/request.py in _call_chain(self, chain, kind, meth_name, *args)
    502         for handler in handlers:
    503             func = getattr(handler, meth_name)
--> 504             result = func(*args)
    505             if result is not None:
    506                 return result

/usr/lib/python3.6/urllib/request.py in https_open(self, req)
   1359         def https_open(self, req):
   1360             return self.do_open(http.client.HTTPSConnection, req,
-> 1361                 context=self._context, check_hostname=self._check_hostname)
   1362 
   1363         https_request = AbstractHTTPHandler.do_request_

/usr/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
   1318                           encode_chunked=req.has_header('Transfer-encoding'))
   1319             except OSError as err: # timeout error
-> 1320                 raise URLError(err)
   1321             r = h.getresponse()
   1322         except:

URLError: <urlopen error [Errno -2] Name or service not known>

In [30]: df = df.loc[df.gender == "female", :]
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-30-cefa155c8818> in <module>()
----> 1 df = df.loc[df.gender == "female", :]

NameError: name 'df' is not defined

In [31]: tab = df.set_index(['left', 'right'])
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-31-a9a89cea7be4> in <module>()
----> 1 tab = df.set_index(['left', 'right'])

NameError: name 'df' is not defined

In [32]: del tab["gender"]
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-32-21569d1674ca> in <module>()
----> 1 del tab["gender"]

NameError: name 'tab' is not defined

In [33]: tab = tab.unstack()
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-33-333904d786a5> in <module>()
----> 1 tab = tab.unstack()

NameError: name 'tab' is not defined

In [34]: tab.columns = tab.columns.get_level_values(1)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-34-63fa72c45fa5> in <module>()
----> 1 tab.columns = tab.columns.get_level_values(1)

NameError: name 'tab' is not defined

In [35]: print(tab)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-35-05dd83975d7b> in <module>()
----> 1 print(tab)

NameError: name 'tab' is not defined

Next we create a SquareTable object from the contingency table.

In [36]: sqtab = sm.stats.SquareTable(tab)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-36-5f46247189bc> in <module>()
----> 1 sqtab = sm.stats.SquareTable(tab)

NameError: name 'tab' is not defined

In [37]: row, col = sqtab.marginal_probabilities
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-37-71324058bc5a> in <module>()
----> 1 row, col = sqtab.marginal_probabilities

NameError: name 'sqtab' is not defined

In [38]: print(row)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-38-e1bf2d8dc4a4> in <module>()
----> 1 print(row)

NameError: name 'row' is not defined

In [39]: print(col)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-39-9a769a44a6f2> in <module>()
----> 1 print(col)

NameError: name 'col' is not defined

The summary method prints results for the symmetry and homogeneity testing procedures.

In [40]: print(sqtab.summary())
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-40-8d0c6fc13a84> in <module>()
----> 1 print(sqtab.summary())

NameError: name 'sqtab' is not defined

If we had the individual case records in a dataframe called data, we could also perform the same analysis by passing the raw data using the SquareTable.from_data class method.

sqtab = sm.stats.SquareTable.from_data(data[['left', 'right']])
print(sqtab.summary())

A single 2x2 table

Several methods for working with individual 2x2 tables are provided in the sm.stats.Table2x2 class. The summary method displays several measures of association between the rows and columns of the table.

In [41]: table = np.asarray([[35, 21], [25, 58]])

In [42]: t22 = sm.stats.Table2x2(table)

In [43]: print(t22.summary())
               Estimate   SE   LCB   UCB  p-value
-------------------------------------------------
Odds ratio        3.867       1.890 7.912   0.000
Log odds ratio    1.352 0.365 0.636 2.068   0.000
Risk ratio        2.075       0.636 2.068   0.000
Log risk ratio    0.730 0.197 0.345 1.115   0.000
-------------------------------------------------

Note that the risk ratio is not symmetric so different results will be obtained if the transposed table is analyzed.

In [44]: table = np.asarray([[35, 21], [25, 58]])

In [45]: t22 = sm.stats.Table2x2(table.T)

In [46]: print(t22.summary())
               Estimate   SE   LCB   UCB  p-value
-------------------------------------------------
Odds ratio        3.867       1.890 7.912   0.000
Log odds ratio    1.352 0.365 0.636 2.068   0.000
Risk ratio        2.194       0.636 2.068   0.000
Log risk ratio    0.786 0.216 0.362 1.210   0.000
-------------------------------------------------

Stratified 2x2 tables

Stratification occurs when we have a collection of contingency tables defined by the same row and column factors. In the example below, we have a collection of 2x2 tables reflecting the joint distribution of smoking and lung cancer in each of several regions of China. It is possible that the tables all have a common odds ratio, even while the marginal probabilities vary among the strata. The ‘Breslow-Day’ procedure tests whether the data are consistent with a common odds ratio. It appears below as the Test of constant OR. The Mantel-Haenszel procedure tests whether this common odds ratio is equal to one. It appears below as the Test of OR=1. It is also possible to estimate the common odds and risk ratios and obtain confidence intervals for them. The summary method displays all of these results. Individual results can be obtained from the class methods and attributes.

In [47]: data = sm.datasets.china_smoking.load()

In [48]: mat = np.asarray(data.data)

In [49]: tables = [np.reshape(x, (2, 2)) for x in mat]
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-49-e0bdaa1c571f> in <module>()
----> 1 tables = [np.reshape(x, (2, 2)) for x in mat]

<ipython-input-49-e0bdaa1c571f> in <listcomp>(.0)
----> 1 tables = [np.reshape(x, (2, 2)) for x in mat]

/usr/lib/python3/dist-packages/numpy/core/fromnumeric.py in reshape(a, newshape, order)
    255            [5, 6]])
    256     """
--> 257     return _wrapfunc(a, 'reshape', newshape, order=order)
    258 
    259 

/usr/lib/python3/dist-packages/numpy/core/fromnumeric.py in _wrapfunc(obj, method, *args, **kwds)
     50 def _wrapfunc(obj, method, *args, **kwds):
     51     try:
---> 52         return getattr(obj, method)(*args, **kwds)
     53 
     54     # An AttributeError occurs if the object does not have

ValueError: cannot reshape array of size 1 into shape (2,2)

In [50]: st = sm.stats.StratifiedTable(tables)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-50-60660fbf798b> in <module>()
----> 1 st = sm.stats.StratifiedTable(tables)

NameError: name 'tables' is not defined

In [51]: print(st.summary())
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-51-ea1038fa2051> in <module>()
----> 1 print(st.summary())

NameError: name 'st' is not defined

Module Reference

Table(table[, shift_zeros]) Analyses that can be performed on a two-way contingency table.
Table2x2(table[, shift_zeros]) Analyses that can be performed on a 2x2 contingency table.
SquareTable(table[, shift_zeros]) Methods for analyzing a square contingency table.
StratifiedTable(tables[, shift_zeros]) Analyses for a collection of 2x2 contingency tables.
mcnemar(table[, exact, correction]) McNemar test of homogeneity.
cochrans_q(x[, return_object]) Cochran’s Q test for identical binomial proportions.

See also

Scipy has several functions for analyzing contingency tables, including Fisher’s exact test which is not currently in Statsmodels.