Scribd
Upload
9 views

Hypothesis Testing

University Mathematics I: Olaniyi Evans

Uploaded by

Olaniyi Evans
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
9 views

Hypothesis Testing

University Mathematics I: Olaniyi Evans

Uploaded by

Olaniyi Evans
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

27

HYPOTHESIS TESTING

CONTENTS
Hypothesis Testing 249
z-Tests: Large Sample Tests 250
t-Tests: Small Sample Tests 252
Chi-Square Tests 254
Chi-Square Test of Goodness of Fit 254
Chi-Square Test of Independence 256
F-Tests: One-Way ANOVA 257

HYPOTHESIS TESTING
Hypothesis testing is a statistical method used to make inferences about a
population parameter based on a sample of data. The choice of test depends on
the type of data and the research question. Common tests include t-tests, z-tests,
chi-square tests, and F-tests (ANOVA).

Types of Tests
• One-tailed test: Tests if a parameter is greater than or less than a value.
Example: Testing if a new TikTok feature increases likes. 𝐻0 : 𝜇 ≤ 50, 𝐻𝐴 : 𝜇 >
50
• Two-tailed test: Tests if a parameter is different from a value (either higher
or lower).
Example: Testing if TikTok user engagement changes, without specifying
direction. 𝐻0 : 𝜇 = 50, 𝐻𝐴 : 𝜇 ≠ 50

NOTE: Think of hypotheses as TikTok features you want to test. Is the new
feature better? Set 𝐻0 as the status quo and 𝐻𝐴 as the new feature. Collect and
analyze data to see if you can reject 𝐻0 and support 𝐻𝐴 .
Hypothesis testing helps determine if a new feature makes a real impact. Only
one hypothesis can be true at a time.

Errors in Hypothesis Testing


Type I Error (α) occurs when H0 is true but is rejected. Example: Concluding a
new TikTok feature increases watch time when it doesn’t.
Level of Significance (α) is the probability of making a Type I error, often set at
0.05 or 0.01.
Type II Error (β) occurs when H0 is false but is accepted. Example: Concluding
the new TikTok feature does not increase watch time when it does.
Managing Errors
Control Type I Error by setting a low α if the cost of this error is high.
Typically, only Type I error is controlled; hence, statisticians recommend using
"do not reject H0" instead of "accept H0" to avoid Type II errors.

Steps in hypothesis testing


1. State the Hypotheses:
• Null Hypothesis (H0): A statement that there is no effect or no
difference.
• Alternative Hypothesis (HA): A statement that there is an effect or a
difference.
250 Olaniyi Evans | University Mathematics

2. Compute the Appropriate Test Statistic:


• Use sample data to calculate the value of the test statistic. This depends
on the type of data and the hypothesis. Common tests include t-tests,
chi-square tests, ANOVA, etc.
3. Formulate the Decision Rule:
• Determine the critical value(s) from the statistical distribution
corresponding to the test statistic and the chosen significance level α.
Common values of α are 0.05, 0.01, or 0.10, representing a 5%, 1%, or
10% risk of rejecting the null hypothesis when it is true.
4. Make a Decision:
• Compare the test statistic to the critical value(s):
o If the test statistic falls into the rejection region, reject H0
o Otherwise, do not reject H0
5. Draw a Conclusion:
• Interpret the results in the context of the research question.

Z -T E S T S : L A R G E S A M P L E T E S T S
The Central Limit Theorem states that the sample mean (𝑥̅ ) is approximately
normally distributed with mean 𝜇 and standard deviation 𝜎⁄√𝑛. When the
sample size is large (n ≥ 30), we can use the Central Limit Theorem to test a
population mean. The test statistic is calculated as
̅−𝝁
𝒙
If 𝜎 is known: 𝒛 =
𝝈⁄√𝒏
̅−𝝁
𝒙
If 𝜎 is unknown: 𝒛 =
𝒔⁄√𝒏

𝑥̅ = mean, 𝑛 = sample size, 𝑠 = population standard deviation, 𝜎 = population


standard deviation. The test statistic follows the standard normal distribution,
which allows us to use standard normal tables to find critical values.
The figure below illustrates the distribution of the standardized test statistic (𝑧)
and the corresponding shaded rejection regions for different alternative
hypotheses (left-tailed, right-tailed, or two-tailed).
Left-tailed test Right-tailed test Two-tailed test

The critical value (𝑧𝛼 or −𝑧𝛼 ) is chosen based on the desired significance level
(𝛼), which represents the probability of rejecting the null hypothesis when it is
true (Type I error).

 EXAMPLE 27.1
A social media marketing firm claims that their enhanced strategy has increased
the average number of likes per post. Previously, the mean number of likes per
post was 1900 with a standard deviation of 120 likes. After implementing the new
strategy, a sample of 64 posts is selected and the mean number of likes per post
is found to be 1960. Test, at the 1% level of significance, whether the mean
number of likes per post has increased due to the new strategy. Assume the
number of likes per post follows a normal distribution.
Chapter 27| Hypothesis Testing 251

Purchase the full book at:


https://unimath.5profz.com/

We donate 0.5% of the book sales


every year to charity, forever. When
you buy University Mathematics (I &
II) you are helping orphans and the
less privileged.

You might also like