def Cochrans(set):
set = list((1, 2, 3, 4, 5, 6, 7, 8, 9, 10))
p = 0.5
q = 1 - p
me = marginerror(set)
samplesize = (square(1.96) * p * q) / (square(me))
return samplesize
def ConfInt(set):
set = list((1, 2, 3, 4, 5, 6, 7, 8, 9, 10))
ci_mean = mean(set)
s_dev = sd(set)
ci_list = []
ci1 = round((ci_mean + 1.96*(s_dev / square(len(set)))), 4)
ci2 = round((ci_mean - 1.96*(s_dev / square(len(set)))), 4)
ci_list.append(ci1)
ci_list.append(ci2)
return ci_list
def cochran(sample, confidence_level):
# Validations
check_for_valid_numbers(sample)
empty_list_check(sample)
# Formula: (Z^2)(p)(q) / (e^2) -> https://www.statisticshowto.com/probability-and-statistics/find-sample-size/
# Assuming p is 0.5
# calculate z from a given confidence interval
z = CalculateZValue.calculate_zvalue(confidence_level)
margin_of_error_result = square(margin_of_error(sample, confidence_level))
return division(margin_of_error_result,
multiplication(multiplication(square(z), 0.5), 0.5))
def Sample_Correlation(list1, list2):
n = len(list1)
avg_x = average(list1)
avg_y = average(list2)
rod = 0
x2 = 0
y2 = 0
for i in range(n):
x = subtraction(list1[i], avg_x)
y = subtraction(list2[i], avg_y)
rod += product(x, y)
x2 += square(x)
y2 += square(y)
return rod / squareRoot(x2 * y2)
def ssk(set):
set = list((1, 2, 3, 4, 5, 6, 7, 8, 9, 10))
s_dev = sd(set)
width = 0.6
me = width / 2
samplesize = square((1.96 * s_dev) / me)
return samplesize
def StdDevSample(data):
Sum1 = 0
for i in data:
x = abs(i - mean(data))
Sum1 = square(x) + Sum1
n = len(data)
stdDev = math.sqrt(Sum1 / (n - 1))
return stdDev
def StdDevPop(data):
Sum2 = 0
for i in data:
x = abs(i - mean(data))
Sum2 = square(x) + Sum2
n = len(data)
stdDev = math.sqrt(Sum2) / n
return stdDev
def ssu(set):
set = list((1, 2, 3, 4, 5, 6, 7, 8, 9, 10))
p = 0.5
q = 1 - p
width = 0.6
me = width / 2
samplesize = square(1.96 / me) * p * q
return samplesize
def st_dev(lst):
diffs = 0
m = mean(lst)
for l in lst:
diffs = addition(diffs, square(subtraction(l, m)))
sd = division(diffs, subtraction(1, len(lst)))
x = root(sd)
return x
def cochranSample(data):
p = 0.5
q = 1 - p
p_q = product(p, q)
List1 = []
List2 = []
for i in marginErr(data):
List1.append(square(i))
for i in zScores(zValues(data)):
List2.append(square(i))
i = 0
n = []
while i < len(List1):
n.append(round(product(List1[i], p_q) / List2[i]))
i += 1
return n
def sample_size_ci(z, p, w):
var_1 = divide(z, 2)
z_score = get_z_score(var_1)
e = divide(w, 2)
q = subtract(1, p)
var_2 = multiply(p, q)
var_3 = divide(float(z_score), e)
var_5 = square(var_3)
return multiply(var_2, var_5)
def CochranSampleSize(data):
p = 0.5
q = 1 - p
PQ = product(p, q)
List = []
List1 = []
for i in MarginError(data):
List.append(square(i))
for i in Z_scores(z_values(data)):
List1.append(square(i))
i = 0
n = []
while i < len(List):
n.append(round(product(List[i], PQ) / List1[i]))
i += 1
return n
def standard_deviation(numbers): # complete
n = len(numbers)
c = 0
t = 0
for i in range(0, n, 1):
c = subtraction(mean(numbers), numbers[i])
t = addition(square(c), t)
x = division((n - 1), t)
return root(x)
def sample_correlation(data, data1):
try:
mean1 = mean(data)
mean2 = mean(data1)
List1 = []
List2 = []
for num in data:
a = subtraction(int(round(mean1, 0)), num)
List1.append(a)
for num in data1:
b = subtraction(mean2, num)
List2.append(b)
c = np.multiply(List1, List2)
cc = 0
for num in c:
cc = cc + num
d = 0
e = 0
# pprint(List1)
# pprint(List2)
for num in List1:
d = d + square(num)
for num in List2:
e = e + square(num)
f = multiplication(int(d), e)
g = square_root(int(f))
h = division(int(g), cc)
# pprint(float(cc))
# pprint(e)
# pprint(f)
# pprint(float(g))
# pprint(str(round(h,9)))
nCorrelation = round(h, 9)
# pprint(nCorrelation)
return nCorrelation
except ZeroDivisionError:
print("Error - Cannot divide by 0")
except ValueError:
print("Error - Invalid data inputs")
def popstand(numbers):
num_values = len(numbers)
result = mean(numbers)
total = 0
for numb in numbers:
result2 = subtraction(numb, result)
sq = square(result2)
total = addition(total, sq)
return squar_rot(division(num_values, total))
def sample_size_unknown_pop(confidence_level, width):
p = 0.5
q = 1 - p
return round(
multiplication(
square(
division(division(2, width),
calculate_zvalue(confidence_level))),
multiplication(p, q)), 2)
def samplevariance(num):
try:
pop_mean = populationmean(num)
num_values = len(num)
x = 0
for i in num:
x = x + square(i - pop_mean)
return round(division(x, num_values), 7)
except ZeroDivisionError:
print("Error: Enter numbers greater than 0")
except ValueError:
print("Error: insert correct data type")
def variance(data):
# Validations
empty_list_check(data)
check_for_valid_numbers(data)
n = len(data)
calculated_mean = mean(data)
result = 0
for x in data:
result = addition(square(subtraction(calculated_mean, x)), result)
return division(n, result)
def variance(num):
try:
pop_mean = populationmean(num)
num_values = len(num)
x = 0
for i in num:
x = x + square(i - pop_mean)
return division(x, num_values)
except ZeroDivisionError:
print("Error: Can't Divide by 0")
except ValueError:
print("Error: Check your data inputs")
def samp_st_dev(numbers):
ss = random.randint(1, len(numbers))
new_values = getSample(numbers, ss)
c = 0
t = 0
n = len(new_values)
for i in range(0, n, 1):
c = subtraction(new_values[i], mean(new_values))
t = addition(square(c), t)
x = division(subtraction(1, n), t)
actual_sd = statistics.stdev(new_values) # Calculated using stat library to compare
return root(x), actual_sd
def variance(data):
if is_valid(data):
size = len(data)
x = mean(data)
tmp = []
for i in data:
diff = subtract(i, x)
tmp.append(square(diff))
total = add_list(tmp)
return divide(total, size)
else:
raise TypeError("Data contains non-numeric values")
def sample_std_dev(data):
total = 0
samples = random.randint(1, len(data))
new_samples = get_sample(data, samples)
new_mean = population_mean(new_samples)
for number in new_samples:
result = subtraction(number, new_mean)
sq = square(result)
total = addition(total, sq)
n = len(new_samples)
d = division(subtraction(1, n), total)
sample_sd = sq_rt(d)
return sample_sd
def sample_st_deviation(data, sample_size):
dev = 0
sample = getSample(data, sample_size)
sample_values = len(sample)
x_bar = sample_mean()
x = sample_values
n = subtraction(sample_values, 1)
for dev in sample:
dev = subtraction(x, x_bar)
square_x_bar = square(dev)
add = addition(square_x_bar, square_x_bar)
divide = division(add, n)
return squareroot(divide)
def variance(num):
try:
pop_mean = populationmean(num)
num_values = len(num)
x = 0
for i in num:
# x = x + square(i-pop_mean)
x = addition(x, square(subtraction(i, pop_mean)))
return division(x, num_values)
except ZeroDivisionError:
print("Error: Enter number greater than 0")
except ValueError:
print("Error: Enter correct data type")
def ssd(data):
total = 0
sample = random.randint(1, len(data))
new_sample = Getsample(data, sample)
new_mean = mean(new_sample)
for numb in new_sample:
result = subtraction(numb, new_mean)
sq = square(result)
total = addition(total, sq)
n = len(new_sample)
d = division(subtraction(1, n), total)
samp_sd = squareroot(d)
return samp_sd
def get_variance(data):
x1 = get_mean(data)
num_values = len(data)
total = 0
total1 = 0
data1 = []
for i in range(0, len(data)):
a = data[i - 1]
total_sum = subtraction(a, x1)
total = square(total_sum)
data1.append(total)
for i in range(0, len(data1)):
total1 = total1 + addition(0, data1[i])
return round(division(num_values - 1, total1), 1)
def variance(num):
Mean_var = mean(num)
Man = []
for n in num:
Variables = subtraction(n, Mean_var)
Man.append(Variables)
Squares = []
for Variables in Man:
Square_var = square(Variables)
Squares.append(Square_var)
return mean(Squares)
def sample_yes_std(data):
List1 = []
List2 = []
e = marginErr(data)
k = c_i(data)
for i in k:
Z = i[1] / 2
List1.append(scipy.stats.norm.cdf(Z))
i = 0
while i < len(List1):
x = product(List1[i], StdDevSample(data))
y = round(division(x, e[i]))
List2.append((square(y)))
i += 1
return List2
def SampleSize_withStd(data):
List = []
List1 = []
E = MarginError(data)
K = mean_confidence_interval(data)
for i in K:
Z = i[1] / 2
List.append(scipy.stats.norm.cdf(Z))
i = 0
while i < len(List):
x = product(List[i], StdDevSample(data))
y = round(division(x, E[i]))
List1.append((square(y)))
i += 1
return List1
def variance(data):
try:
# 1. find the mean of the data
calculatedMean = mean(data)
# pprint(calculatedMean)
distanceArray = []
meanDeviationValue = 0
for item in data:
distanceArray.append(abs(subtraction(item, calculatedMean)))
num_values = len(data)
x = 0
for i in distanceArray:
x = x + square(i)
return int(division(num_values, x))
except ZeroDivisionError:
print("Error - Cannot divide by 0")
except ValueError:
print("Error - Invalid data inputs")
