def samplestddev(a):
try:
variance = samplevariance(a)
return round(squarerooting(variance), 5)
except ZeroDivisionError:
print("Error: Can't Divide by 0")
except ValueError:
print("Error: Check your data inputs")
def stddev(num):
try:
variance_float = variance(num)
return round(squarerooting(variance_float), 5)
except ZeroDivisionError:
print("Error: Can't Divide by 0")
except ValueError:
print("Error: Check your data inputs")
def marginoferror(a, conf):
n = len(a)
z_critical = scipy.stats.norm.ppf(1 - (1 - conf) / 2)
sample_stdev = samplestddev(a)
se = sample_stdev/squarerooting(n)
margin_of_error = z_critical * se
return margin_of_error
def confidence_interval_top(num):
try:
num_values = len(num)
z = 1.96
sd = stddev(num)
avg = populationmean(num)
return round(avg + (z * sd / squarerooting(num_values)), 5)
except ZeroDivisionError:
print("Error: Can't Divide by 0")
except ValueError:
print("Error: Check your data inputs")
def findsamplesize(conf, width):
z_critical = z_critical = scipy.stats.norm.ppf(1 - (1 - conf) / 2)
z_critical_squared = squarerooting(z_critical)
moe = width / 2
p_hat = .5
q_hat = 1 - p_hat
p_times_q = p_hat * q_hat
z_div_moe = z_critical / moe
z_div_moe_squared = squaring(z_div_moe)
n = ceil(p_times_q * z_div_moe_squared)
return n
def squareroot(self, a):
self.result = squarerooting(a)
return self.result
def stddev(num):
variance_num = variance(num)
return round(squarerooting(variance_num), 4)
def confidence_low(num):
values = len(num)
z = 1.96
stdev1 = stddev(num)
avg = populationmean(num)
return (avg - (z * stdev1)) / (squarerooting(values))