Hypothesis Setup Companion

How to Use This Companion

Hypothesis testing begins with clearly defined hypotheses. This guided worksheet will walk you through clarifying your research question, identifying the correct population parameter, and crafting compliant null and alternative hypotheses. Each step summarizes key reminders from the hypothesis testing handbook so you can stay aligned with best practices.

Step 1. Clarify Your Research Question

Keep your question focused on one measurable characteristic of a single population. Avoid wording that implies causes, relationships, or comparisons across groups.

What is your research question?

Reminder: Look for language such as causes, affects, or compared to. If you find any, rephrase the question so it only describes one population characteristic.

Step 2. Identify the Population Parameter

Determine whether you will describe a population mean (μ) or a population proportion (p). Choose one parameter only.

Select the parameter you will test

Population mean (μ): Use for numerical data like heights, prices, or hours.

Population proportion (p): Use for categorical data such as yes/no responses.

What claimed value will you test against?

Choose a specific value

Draw from historical claims, previous studies, or neutral benchmarks.
Avoid ranges or vague descriptions—hypotheses require an exact number.

Step 3. Confirm Your Data Is Obtainable

Ensure you can gather a sample ethically, with the resources you have available, and in a way that yields reliable measurements.

Describe how you will collect the data.

Checklist: Is the data accessible? Can you measure it objectively? Do you have permission to collect it? If not, adjust your question before moving forward.

Step 4. Build the Null Hypothesis (H₀)

The null hypothesis always uses an equals sign and states that the population parameter equals the value you selected.

Format reminder

H₀: parameter = value

There is no <, >, or ≠ in the null hypothesis.
Think of this as the “no change” or “status quo” position.

Step 5. Choose Your Alternative Hypothesis (H₁)

Decide whether you are testing for any difference (two-tailed) or a specific direction (one-tailed). When unsure, select the two-tailed option.

What kind of difference are you testing?

Two-tailed: H₁ states the parameter is different (≠) from the null value.

Upper-tailed: H₁ states the parameter is greater than (>) the null value.

Lower-tailed: H₁ states the parameter is less than (<) the null value.

Directional choice tips

Use ≠ when you want to detect any difference.
Use > only with a strong reason to look for an increase.
Use < only with a strong reason to look for a decrease.

Step 6. Select the Test Type

Match your hypotheses to the correct statistical procedure before collecting data.

Recommended test

Select a parameter above to view the suggested test.

Step 7. Pick a Significance Level (α)

Choose your tolerance for false alarms before you analyze data. Classroom projects typically use α = 0.05.

Significance level (α)

Interpretation: α is the chance of rejecting a true null hypothesis. Decide upfront and stick with it.

Your Draft Hypotheses

H₀: —

H₁: —

Suggested test: —

Chosen α: —