def test_confidence_interval_with_sample_simulation(self):
grp1_sample = Sample()
grp2_sample = Sample()
for i in range(10):
if random() <= 0.6:
grp1_sample.add_category("OK")
else:
grp1_sample.add_category("CANCEL")
for i in range(9):
if random() <= 0.61:
grp2_sample.add_category("OK")
else:
grp2_sample.add_category("CANCEL")
sampling_distribution = ProportionDiffSamplingDistribution(
grp1_sample_distribution=SampleDistribution(
grp1_sample, categorical_value="OK"),
grp2_sample_distribution=SampleDistribution(
grp2_sample, categorical_value="OK"))
self.assertEqual(sampling_distribution.distribution_family,
DistributionFamily.simulation)
print('sampling distribution: (point_estimate = ' +
str(sampling_distribution.point_estimate) +
', standard_error = ' +
str(sampling_distribution.standard_error) + ')')
print('confidence level for 95% confidence level: ' +
str(sampling_distribution.confidence_interval(0.95)))
def test_confidence_interval_with_sample_student(self):
grp1_mu = 0.0
grp1_sigma = 1.0
grp1_sample_size = 29
grp1_sample = Sample()
grp2_mu = 0.08
grp2_sigma = 1.1
grp2_sample_size = 27
grp2_sample = Sample()
for i in range(grp1_sample_size):
grp1_sample.add_numeric(normal(grp1_mu, grp1_sigma))
for i in range(grp2_sample_size):
grp2_sample.add_numeric(normal(grp2_mu, grp2_sigma))
sampling_distribution = MeanDiffSamplingDistribution(
grp1_sample_distribution=SampleDistribution(grp1_sample),
grp2_sample_distribution=SampleDistribution(grp2_sample))
self.assertEqual(sampling_distribution.distribution_family,
DistributionFamily.student_t)
print('sampling distribution: (point_estimate = ' +
str(sampling_distribution.point_estimate) +
', standard_error = ' +
str(sampling_distribution.standard_error) + ')')
print('confidence interval for 95% confidence level: ' +
str(sampling_distribution.confidence_interval(0.95)))
def test_normal(self):
grp1_sample = Sample()
grp2_sample = Sample()
for i in range(100):
if random() <= 0.6:
grp1_sample.add_category("OK")
else:
grp1_sample.add_category("CANCEL")
for i in range(100):
if random() <= 0.61:
grp2_sample.add_category("OK")
else:
grp2_sample.add_category("CANCEL")
sampling_distribution = ProportionDiffSamplingDistribution(
grp1_sample_distribution=SampleDistribution(
grp1_sample, categorical_value="OK"),
grp2_sample_distribution=SampleDistribution(
grp2_sample, categorical_value="OK"))
self.assertEqual(sampling_distribution.distribution_family,
DistributionFamily.normal)
testing = ProportionDiffTesting(
sampling_distribution=sampling_distribution)
print('one tail p-value: ' + str(testing.p_value_one_tail))
print('two tail p-value: ' + str(testing.p_value_two_tail))
reject_one_tail, reject_two_tail = testing.will_reject(0.01)
print('will reject p_1 == p_2 (one-tail) ? ' + str(reject_one_tail))
print('will reject p_1 == p_2 (two-tail) ? ' + str(reject_two_tail))
self.assertFalse(reject_one_tail)
self.assertFalse(reject_two_tail)
def test_student(self):
grp1_mu = 0.0
grp1_sigma = 1.0
grp1_sample_size = 29
grp1_sample = Sample()
grp2_mu = 0.09
grp2_sigma = 2.0
grp2_sample_size = 28
grp2_sample = Sample()
for i in range(grp1_sample_size):
grp1_sample.add_numeric(normal(grp1_mu, grp1_sigma))
for i in range(grp2_sample_size):
grp2_sample.add_numeric(normal(grp2_mu, grp2_sigma))
sampling_distribution = MeanDiffSamplingDistribution(
grp1_sample_distribution=SampleDistribution(grp1_sample),
grp2_sample_distribution=SampleDistribution(grp2_sample))
self.assertEqual(sampling_distribution.distribution_family,
DistributionFamily.student_t)
testing = MeanDiffTesting(sampling_distribution=sampling_distribution)
print('one tail p-value: ' + str(testing.p_value_one_tail))
print('two tail p-value: ' + str(testing.p_value_two_tail))
reject_one_tail, reject_two_tail = testing.will_reject(0.01)
print('will reject mean_1 == mean_2 (one-tail) ? ' +
str(reject_one_tail))
print('will reject mean_1 == mean_2 (two-tail) ? ' +
str(reject_two_tail))
self.assertFalse(reject_one_tail)
self.assertFalse(reject_two_tail)
def __init__(self, sample, significance_level=None):
if significance_level is not None:
self.significance_level = significance_level
self.sample = sample
self.individual_sampling_distributions = TernarySearchTrie()
self.individual_sample_distributions = TernarySearchTrie()
self.individual_samples = sample.split_by_group_id()
for group_id in self.individual_samples.keys():
sample_distribution = SampleDistribution(
sample=self.individual_samples.get(group_id),
group_id=group_id)
sampling_distribution = MeanSamplingDistribution(
sample_distribution=sample_distribution)
self.individual_sample_distributions.put(group_id,
sample_distribution)
self.individual_sampling_distributions.put(group_id,
sampling_distribution)
self.overall_sample_distribution = SampleDistribution(sample=sample,
group_id=None)
self.overall_sampling_distribution = MeanSamplingDistribution(
self.overall_sample_distribution)
self.build()
def test_confidence_interval_with_sample_normal(self):
mu = 0.0
sigma = 1.0
sample_size = 31
sample = Sample()
for i in range(sample_size):
sample.add_numeric(normal(mu, sigma))
sampling_distribution = MeanSamplingDistribution(
sample_distribution=SampleDistribution(sample))
self.assertEqual(sampling_distribution.distribution_family,
DistributionFamily.normal)
print('sampling distribution: (point_estimate = ' +
str(sampling_distribution.point_estimate) +
', standard_error = ' +
str(sampling_distribution.standard_error) + ')')
print('confidence interval for 95% confidence level: ' +
str(sampling_distribution.confidence_interval(0.95)))
def test_mean_student(self):
mu = 0.0
sigma = 1.0
sample_size = 29
sample = Sample()
for i in range(sample_size):
sample.add_numeric(normal(mu, sigma))
sampling_distribution = MeanSamplingDistribution(sample_distribution=SampleDistribution(sample))
testing = MeanTesting(sampling_distribution=sampling_distribution, mean_null=0.0)
print('one tail p-value: ' + str(testing.p_value_one_tail))
print('two tail p-value: ' + str(testing.p_value_two_tail))
reject_one_tail, reject_two_tail = testing.will_reject(0.01)
print('will reject mean = 0 (one-tail) ? ' + str(reject_one_tail))
print('will reject mean = 0 (two-tail) ? ' + str(reject_two_tail))
self.assertFalse(reject_one_tail)
self.assertFalse(reject_two_tail)
def test_proportion_simulation(self):
sample = Sample()
for i in range(10):
if random() <= 0.6:
sample.add_category("OK")
else:
sample.add_category("CANCEL")
sampling_distribution = ProportionSamplingDistribution(
sample_distribution=SampleDistribution(sample, categorical_value="OK"))
testing = ProportionTesting(sampling_distribution=sampling_distribution, p_null=0.6)
print('one tail p-value: ' + str(testing.p_value_one_tail))
print('two tail p-value: ' + str(testing.p_value_two_tail))
reject_one_tail, reject_two_tail = testing.will_reject(0.01)
print('will reject p = 0.6 (one-tail) ? ' + str(reject_one_tail))
print('will reject p = 0.6 (two-tail) ? ' + str(reject_two_tail))
self.assertFalse(reject_one_tail)
self.assertFalse(reject_two_tail)