Business Analytics > Statistical Inference > What is an Hypothesis?

What is an Hypothesis?

Hypothesis: A hypothesis is an informed guess or a statement about a characteristic of a population. The purpose of hypothesis testing is to study sample data and decide which population characteristics are likely to be true and which are unlikely to be true.

Example of Hypothesis and Hypothesis Testing:

Suppose a company claims that the average lifetime of a light bulb is 1000 hours.

• Hypothesis (claim): The average lifetime = 1000 hours
• You take a sample of bulbs and measure their lifetimes

Now, based on the sample results, you decide:

• Is it likely that the true average is 1000 hours?
• Or is it unlikely, meaning the claim may be wrong?

So, you use sample data to accept or question the company’s claim about the population.

Null and alternative hypotheses

Null Hypothesis (H₀): The default assumption is the null hypothesis. It usually states that there is no effect, no difference, or no change in the population.

Alternative Hypothesis (H₁ or Hₐ): This is the opposite of the null hypothesis. It suggests that there is an effect, difference, or change.

Example: A company claims that the average lifetime of a light bulb is 1000 hours.

• H₀ (Null Hypothesis): The average lifetime = 1000 hours
• H₁ (Alternative Hypothesis): The average lifetime ≠ 1000 hours (or > 1000, or < 1000)

In hypothesis testing, we use sample data to decide whether to reject H₀ or not reject H₀.

 

Prev

Concept of Statistical Inference

No More

Feedback

Submit