diff --git a/pandas/src/hash.pyx b/pandas/src/hash.pyx
index a393e0df96954..06ed947808e39 100644
--- a/pandas/src/hash.pyx
+++ b/pandas/src/hash.pyx
@@ -40,7 +40,8 @@ def hash_object_array(ndarray[object] arr, object key, object encoding='utf8'):
         Py_ssize_t i, l, n
         ndarray[uint64_t] result
         bytes data, k
-        uint8_t *kb, *lens
+        uint8_t *kb
+        uint64_t *lens
         char **vecs, *cdata
         object val
 
@@ -55,7 +56,7 @@ def hash_object_array(ndarray[object] arr, object key, object encoding='utf8'):
 
     # create an array of bytes
     vecs = <char **> malloc(n * sizeof(char *))
-    lens = <uint8_t*> malloc(n * sizeof(uint8_t))
+    lens = <uint64_t*> malloc(n * sizeof(uint64_t))
 
     cdef list datas = []
     for i in range(n):
diff --git a/pandas/tools/tests/test_hashing.py b/pandas/tools/tests/test_hashing.py
index 4e05ae7007c80..6e5f30fb7a52d 100644
--- a/pandas/tools/tests/test_hashing.py
+++ b/pandas/tools/tests/test_hashing.py
@@ -142,7 +142,36 @@ def test_alternate_encoding(self):
         obj = Series(list('abc'))
         self.check_equal(obj, encoding='ascii')
 
-    def test_long_strings(self):
-
-        obj = Index(tm.rands_array(nchars=10000, size=100))
-        self.check_equal(obj)
+    def test_same_len_hash_collisions(self):
+
+        for l in range(8):
+            length = 2**(l + 8) + 1
+            s = tm.rands_array(length, 2)
+            result = hash_array(s, 'utf8')
+            self.assertFalse(result[0] == result[1])
+
+        for l in range(8):
+            length = 2**(l + 8)
+            s = tm.rands_array(length, 2)
+            result = hash_array(s, 'utf8')
+            self.assertFalse(result[0] == result[1])
+
+    def test_hash_collisions(self):
+
+        # hash collisions are bad
+        # https://github.com/pandas-dev/pandas/issues/14711#issuecomment-264885726
+        L = ['Ingrid-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',  # noqa
+             'Tim-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']  # noqa
+
+        # these should be different!
+        result1 = hash_array(np.asarray(L[0:1], dtype=object), 'utf8')
+        expected1 = np.array([14963968704024874985], dtype=np.uint64)
+        self.assert_numpy_array_equal(result1, expected1)
+
+        result2 = hash_array(np.asarray(L[1:2], dtype=object), 'utf8')
+        expected2 = np.array([16428432627716348016], dtype=np.uint64)
+        self.assert_numpy_array_equal(result2, expected2)
+
+        result = hash_array(np.asarray(L, dtype=object), 'utf8')
+        self.assert_numpy_array_equal(
+            result, np.concatenate([expected1, expected2], axis=0))