Hypothesis Testing on the TI-84: The Complete Workflow
Quick answer: To run a hypothesis test on the TI-84, press STAT, go to TESTS, and pick your test (Z-Test, T-Test, 1-PropZTest, or χ²-Test). Enter the null and alternative hypotheses, the data or summary statistics, and your significance level, then select Calculate. The calculator gives you the test statistic and the p-value — if the p-value is below your significance level (usually 0.05), reject the null hypothesis; if it is above, fail to reject it.
Most students learn hypothesis testing as a pile of disconnected formulas — and then freeze on exam day. The truth is, it’s one repeatable workflow with six steps, and your TI-84 does the heavy arithmetic. This hypothesis testing TI-84 guide covers the full process: from writing hypotheses to interpreting the result in plain English.
What Hypothesis Testing Actually Is
Hypothesis testing answers one question: does my sample give enough evidence to reject what I assumed was true? You start by assuming nothing interesting is happening (the null hypothesis), then check whether your data disagrees strongly enough to abandon that assumption.
Your TI-84 can’t do the thinking for you — but once you know which test to run, this hypothesis testing TI-84 workflow computes the test statistic and p-value in seconds.
Step 1: State Your Hypotheses (H₀ vs Hₐ)
Every hypothesis testing TI-84 session starts with two competing statements:
- H₀ (null hypothesis): the “nothing is happening” claim — usually an equality, like μ = 50
- Hₐ (alternative hypothesis): what you’re actually trying to show — μ ≠ 50, μ > 50, or μ < 50
The direction of Hₐ determines the tail of the test:
| Hₐ statement | Test type | When to use it |
|---|---|---|
| μ ≠ 50 | Two-tailed | You’re checking for *any* difference |
| μ > 50 | Right-tailed | You’re checking for an *increase* |
| μ < 50 | Left-tailed | You’re checking for a *decrease* |
Tip: the words in the question tell you the tail. “Different from” means two-tailed; “greater than” or “more than” means right-tailed; “less than” or “fewer than” means left-tailed.
Step 2: Choose the Right Test on Your TI-84
This is where most marks are lost — picking the wrong test. Use this decision table:
| Your situation | TI-84 test | Menu path |
|---|---|---|
| Testing one mean, σ known (or n ≥ 30) | Z-Test | STAT → ◄ TESTS → 1:Z-Test |
| Testing one mean, σ unknown (small sample) | T-Test | STAT → ◄ TESTS → 2:T-Test |
| Testing one proportion | 1-PropZTest | STAT → ◄ TESTS → 5:1-PropZTest |
| Comparing two means | 2-SampTTest | STAT → ◄ TESTS → 4:2-SampTTest |
| Comparing two proportions | 2-PropZTest | STAT → ◄ TESTS → 6:2-PropZTest |
The golden rule: means with unknown σ → T-Test; proportions → PropZTest. If the problem gives you a population standard deviation (σ) or a large sample, reach for the Z-Test.
Step 3: Pick Your Significance Level (α)
The significance level α is your threshold for “strong enough evidence.” In most classes it’s α = 0.05 (5%). If the question doesn’t specify one, use 0.05. Stricter tests sometimes use α = 0.01.
Think of α as your tolerance for being wrong: at α = 0.05, you accept a 5% chance of rejecting H₀ when it was actually true.
Step 4: Run the Test and Get the P-Value
On the TI-84, the workflow is the same for every test:
- Press STAT, then ◄ to reach the TESTS menu
- Select your test (e.g., 2:T-Test)
- Choose Data (values in a list) or Stats (you have x̄, s, n already)
- Enter H₀’s value as μ₀, pick the correct alternative (≠, <, >), and select Calculate
The output gives you two numbers that matter: the test statistic (t or z) and the p-value. The p-value is the star of the show — it’s the probability of seeing data this extreme *if H₀ were true*.
For the full keystroke-by-keystroke walkthrough of each test screen, see our T-Test and Z-Test guide. And if your p-value work involves normal distributions, our normalcdf guide shows how those tail areas are computed.
Step 5: Make the Decision (Reject or Fail to Reject)
Compare the p-value to α. There are only two possible outcomes:
| Condition | Decision | Meaning |
|---|---|---|
| p-value ≤ α | Reject H₀ | The evidence is strong enough |
| p-value > α | Fail to reject H₀ | The evidence isn’t strong enough |
Two things examiners love to test: you never “accept” H₀ — you only fail to reject it. And “fail to reject” is not proof H₀ is true; it just means your data didn’t contradict it convincingly.
Step 6: Write the Conclusion in Plain English
Always finish with a conclusion sentence tied to the original context. Use these templates:
- Reject H₀: “There is sufficient evidence at the α = 0.05 level to support the claim that [context, e.g., the mean battery life exceeds 50 hours].”
- Fail to reject H₀: “There is not sufficient evidence at the α = 0.05 level to support the claim that [context].”
Notice the conclusion references the alternative hypothesis in context — never just “we reject H₀.” That context sentence is where the final mark lives.
5 Hypothesis Testing TI-84 Mistakes That Cost Marks
- Wrong test choice — running a Z-Test when σ is unknown. Re-check the hypothesis testing TI-84 decision table in Step 2 every time.
- Wrong tail — “different from” is two-tailed, not one-tailed. Read the question’s wording.
- Saying “accept H₀” — the phrase doesn’t exist in hypothesis testing. It’s always “fail to reject.”
- Forgetting the context — a conclusion of “reject H₀” with no real-world meaning loses the interpretation mark.
- Mixing up p and α — the p-value comes from your data; α is chosen before you start. Compare p *against* α.
Frequently Asked Questions
When do I use a T-Test vs a Z-Test on the TI-84?
Use the T-Test when the population standard deviation is unknown (the usual case with small samples). Use the Z-Test when σ is known or your sample is large (n ≥ 30). When in doubt in an AP Stats class, it’s almost always the T-Test for hypothesis testing TI-84 students.
What does the p-value actually mean?
It’s the probability of getting a test statistic at least as extreme as yours, assuming the null hypothesis is true. A tiny p-value means your data would be very surprising under H₀ — so you reject it.
Can the TI-84 do a two-tailed test?
Yes. On any test screen, select the ≠μ₀ (or ≠p₀) alternative option before choosing Calculate. The calculator adjusts the p-value automatically.
What’s the difference between 1-PropZTest and 2-PropZTest?
1-PropZTest compares one sample proportion against a claimed value. 2-PropZTest compares proportions from two independent samples — for example, testing whether two teaching methods have different success rates.
Why does my calculator say ERR:DATA TYPE?
Usually a list problem — check that your data list contains only numbers and that the list name is entered correctly (2ND → STAT → select the list). A quick RAM reset also clears corrupted list entries.
*Practice this hypothesis testing TI-84 workflow anytime with our free TI-84 calculator online — no download needed. More statistics help in our TI-84 guides hub.*
