HTML tutorial
CSS3 tutorial
Bootstrap tutorial
JavaScript tutorial
JQuery tutorial
AngularJS tutorial
React tutorial
NodeJS tutorial
PHP tutorial
Python tutorial
Python3 tutorial
Django tutorial
Linux tutorial
Docker tutorial
Ruby tutorial
Java tutorial
C tutorial
C ++ tutorial
Perl tutorial
JSP tutorial
Lua tutorial
Scala tutorial
Go tutorial
ASP.NET tutorial
C # tutorial
A population proportion is the share of a population that belongs to a particular category.Hypothesis tests are used to check a claim about the size of that population proportion
The following steps are used for a hypothesis test:
For example:
And we want to check the claim:
"The share of Nobel Prize winners that are women is not 50%"
By taking a sample of 100 randomly selected Nobel Prize winners we could find that:
10 out of 100 Nobel Prize winners in the sample were women
The sample proportion is then: \(\displaystyle \frac{10}{100} = 0.1\), or 10%.
From this sample data we check the claim with the steps below.
The conditions for calculating a confidence interval for a proportion are:
In our example, we randomly selected 10 people that were women.
The rest were not women, so there are 90 in the other category.
The conditions are fulfilled in this case.
Note: It is possible to do a hypothesis test without having 5 of each category. But special adjustments need to be made.
We need to define a null hypothesis (\(H_{0}\)) and an alternative hypothesis (\(H_{1}\)) based on the claim we are checking.
The claim was:
"The share of Nobel Prize winners that are women is not 50%"
In this case, the parameter is the proportion of Nobel Prize winners that are women (\(p\)).
The null and alternative hypothesis are then:
Null hypothesis: 50% of Nobel Prize winners were women.
Alternative hypothesis: The share of Nobel Prize winners that are women is not 50%
Which can be expressed with symbols as:
\(H_{0}\): \(p = 0.50 \)
\(H_{1}\): \(p \neq 0.50 \)
This is a 'two-tailed' test, because the alternative hypothesis claims that the proportion is different (larger or smaller) than in the null hypothesis.
If the data supports the alternative hypothesis, we reject the null hypothesis and accept the alternative hypothesis.
The significance level (\(\alpha\)) is the uncertainty we accept when rejecting the null hypothesis in a hypothesis test.
The significance level is a percentage probability of accidentally making the wrong conclusion.
Typical significance levels are:
A lower significance level means that the evidence in the data needs to be stronger to reject the null hypothesis.
There is no "correct" significance level - it only states the uncertainty of the conclusion.
Note: A 5% significance level means that when we reject a null hypothesis:
We expect to reject a true null hypothesis 5 out of 100 times.
The test statistic is used to decide the outcome of the hypothesis test.
The test statistic is a standardized value calculated from the sample.
The formula for the test statistic (TS) of a population proportion is:
\(\displaystyle \frac{\hat{p} - p}{\sqrt{p(1-p)}} \cdot \sqrt{n} \)
\(\hat{p}-p\) is the difference between the sample proportion (\(\hat{p}\)) and the claimed population proportion (\(p\)).
\(n\) is the sample size.
In our example:
The claimed (\(H_{0}\)) population proportion (\(p\)) was \( 0.50 \)
The sample proportion (\(\hat{p}\)) was 10 out of 100, or: \(\displaystyle \frac{10}{100} = 0.10\)
The sample size (\(n\)) was \(100\)
So the test statistic (TS) is then:
\(\displaystyle \frac{0.1-0.5}{\sqrt{0.5(1-0.5)}} \cdot \sqrt{100} = \frac{-0.4}{\sqrt{0.5(0.5)}} \cdot \sqrt{100} = \frac{-0.4}{\sqrt{0.25}} \cdot \sqrt{100} = \frac{-0.4}{0.5} \cdot 10 = \underline{-8}\)
You can also calculate the test statistic using programming language functions:
With Python use the scipy and math libraries to calculate the test statistic for a proportion.
import scipy.stats as stats
import math
# Specify the number of occurrences (x), the sample size (n), and the proportion claimed in the null-hypothesis (p)
x = 10
n = 100
p = 0.5
# Calculate the sample proportion
p_hat = x/n
# Calculate and print the test statistic
print((p_hat-p)/(math.sqrt((p*(1-p))/(n))))
With R use the built-in math functions to calculate the test statistic for a proportion.
# Specify the sample occurrences (x), the sample size (n), and the null-hypothesis claim (p)
x <- 10
n <- 100
p <- 0.5
# Calculate the sample proportion
p_hat = x/n
# Calculate and output the test statistic
(p_hat-p)/(sqrt((p*(1-p))/(n)))
There are two main approaches for making the conclusion of a hypothesis test:
Note: The two approaches are only different in how they present the conclusion.
The Critical Value Approach
For the critical value approach we need to find the critical value (CV) of the significance level (\(\alpha\)).
For a population proportion test, the critical value (CV) is a Z-value from a standard normal distribution.
This critical Z-value (CV) defines the rejection region for the test.
The rejection region is an area of probability in the tails of the standard normal distribution.
Because the claim is that the population proportion is different from 50%, the rejection region is split into both the left and right tail:
The size of the rejection region is decided by the significance level (\(\alpha\)).
Choosing a significance level (\(\alpha\)) of 0.01, or 1%, we can find the critical Z-value from a Z-table, or with a programming language function:
Note: Because this is a two-tailed test the tail area (\(\alpha\)) needs to be split in half (divided by 2).
With Python use the Scipy Stats library norm.ppf()
function find the Z-value for an \(\alpha\)/2 = 0.005 in the left tail.
import scipy.stats as stats
print(stats.norm.ppf(0.005))
With R use the built-in qnorm()
function to find the Z-value for an \(\alpha\) = 0.005 in the left tail.
qnorm(0.005)
Using either method we can find that the critical Z-value in the left tail is \(\approx \underline{-2.5758}\)
Since a normal distribution i symmetric, we know that the critical Z-value in the right tail will be the same number, only positive: \(\underline{2.5758}\)
For a two-tailed test we need to check if the test statistic (TS) is smaller than the negative critical value (-CV), or bigger than the positive critical value (CV).
If the test statistic is smaller than the negative critical value, the test statistic is in the rejection region.
If the test statistic is bigger than the positive critical value, the test statistic is in the rejection region.
When the test statistic is in the rejection region, we reject the null hypothesis (\(H_{0}\)).
Here, the test statistic (TS) was \(\approx \underline{-8}\) and the critical value was \(\approx \underline{-2.5758}\)
Here is an illustration of this test in a graph:
Since the test statistic was smaller than the negative critical value we reject the null hypothesis.
This means that the sample data supports the alternative hypothesis.
And we can summarize the conclusion stating:
The sample data supports the claim that "The share of Nobel Prize winners that are women is not 50%" at a 1% significance level.
The P-Value Approach
For the P-value approach we need to find the P-value of the test statistic (TS).
If the P-value is smaller than the significance level (\(\alpha\)), we reject the null hypothesis (\(H_{0}\)).
The test statistic was found to be \( \approx \underline{-8} \)
For a population proportion test, the test statistic is a Z-Value from a standard normal distribution.
Because this is a two-tailed test, we need to find the P-value of a Z-value smaller than -8 and multiply it by 2.
We can find the P-value using a Z-table, or with a programming language function:
With Python use the Scipy Stats library norm.cdf()
function find the P-value of a Z-value smaller than -8 for a two tailed test:
import scipy.stats as stats
print(2*stats.norm.cdf(-8))
With R use the built-in pnorm()
function find the P-value of a Z-value smaller than -8 for a two tailed test:
2*pnorm(-8)
Using either method we can find that the P-value is \(\approx \underline{1.25 \cdot 10^{-15}}\) or \(0.00000000000000125\)
This tells us that the significance level (\(\alpha\)) would need to be bigger than 0.000000000000125%, to reject the null hypothesis.
Here is an illustration of this test in a graph:
This P-value is smaller than any of the common significance levels (10%, 5%, 1%).
So the null hypothesis is rejected at all of these significance levels.
And we can summarize the conclusion stating:
The sample data supports the claim that "The share of Nobel Prize winners that are women is not 50%" at a 10%, 5%, and 1% significance level.
Many programming languages can calculate the P-value to decide outcome of a hypothesis test.
Using software and programming to calculate statistics is more common for bigger sets of data, as calculating manually becomes difficult.
The P-value calculated here will tell us the lowest possible significance level where the null-hypothesis can be rejected.
With Python use the scipy and math libraries to calculate the P-value for a two-tailed tailed hypothesis test for a proportion.
Here, the sample size is 100, the occurrences are 10, and the test is for a proportion different from than 0.50.
import scipy.stats as stats
import math
# Specify the number of occurrences (x), the sample size (n), and the proportion claimed in the null-hypothesis (p)
x = 10
n = 100
p = 0.5
# Calculate the sample proportion
p_hat = x/n
# Calculate the test statistic
test_stat = (p_hat-p)/(math.sqrt((p*(1-p))/(n)))
# Output the p-value of the test statistic (two-tailed test)
print(2*stats.norm.cdf(test_stat))
With R use the built-in prop.test()
function find the P-value for a left tailed hypothesis test for a proportion.
Here, the sample size is 100, the occurrences are 10, and the test is for a proportion different from 0.50.
# Specify the sample occurrences (x), the sample size (n), and the null-hypothesis claim (p)
x <- 10
n <- 100
p <- 0.5
# P-value from left-tail proportion test at 0.01 significance level
prop.test(x, n, p, alternative = c("two.sided"), conf.level = 0.99, correct = FALSE)$p.value
Note: The conf.level
in the R code is the reverse of the significance level.
Here, the significance level is 0.01, or 1%, so the conf.level is 1-0.01 = 0.99, or 99%.
This was an example of a two tailed test, where the alternative hypothesis claimed that parameter is different from the null hypothesis claim.
You can check out an equivalent step-by-step guide for other types here: