Part 1: Multiple choice
42 questions · 1 hour 30 minutes · 50%
Rehearse with the same timing, calculator, and reference conditions.Use the revised 2026–27 five-unit framework to formulate questions, collect data, analyze uncertainty, perform inference, and communicate defensible conclusions.
Unit review: Define the vocabulary you need to explain, connect it to the unit's representations, then solve a changed item.
Formula review: connect each reference relationship to its meaning, conditions, and a worked example before exam day.
After the diagnostic, continue through the statistics subject guide, statistics practice questions, the statistics formula sheet, the Probability and Statistics course. Pick the page that matches the first decision you could not make confidently.
42 questions · 1 hour 30 minutes · 50%
Rehearse with the same timing, calculator, and reference conditions.4 questions · 1 hour 30 minutes · 50%
Rehearse with the same timing, calculator, and reference conditions.These questions examine how you approach a unit, not whether one isolated fact is familiar.
Use exam weighting to allocate review time, while preserving prerequisites that later areas depend on.
One-Variable Data and Collecting Data: Name the objects and notation before applying a rule.
Probability, Random Variables, and Distributions: Connect the symbolic form to a graph, diagram, table, or example.
Inference for Categorical Data: Proportions: Compare two methods and record when each one is valid.
Inference for Quantitative Data: Means: Finish with an unfamiliar problem and an independent check.
Regression Analysis: Name the objects and notation before applying a rule.
Study a relationship with its meaning and limits attached; isolated symbols are difficult to retrieve under pressure.
Before using it, name every quantity, confirm the permitted conditions, and predict the sign or scale.
Before using it, name every quantity, confirm the permitted conditions, and predict the sign or scale.
Before using it, name every quantity, confirm the permitted conditions, and predict the sign or scale.
Before using it, name every quantity, confirm the permitted conditions, and predict the sign or scale.
Do not schedule review by comfort. Schedule the activity that will reveal whether the repair transferred.
Locate the earliest uncertain decision.
Rehearse selection and pacing across units.
Convert remaining time into review and rehearsal blocks.
Turn the guide into exam-day skill by practising with the section timing, permitted tools, and task verbs below.
| Exam part | Rule | How to prepare |
|---|---|---|
| Multiple choice | Graphing calculator with statistics functions | Use it for normalcdf, invNorm, and binomial probabilities instead of the tables when speed matters. |
| Free response | Graphing calculator with statistics functions | The calculator gives the number; the rubric pays for the name of the procedure and the conditions. |
| Provided for the whole exam | Formula sheet and tables | Formulas and the normal, t, and chi-square tables are given. Do not spend study time memorising them - Spend it on when each applies. |
| Verb | What earns credit |
|---|---|
| State the hypotheses | Write them about parameters, using mu, p, or beta. Hypotheses written with x-bar or p-hat lose the point automatically. |
| Justify your choice of procedure | Name the test or interval AND check each condition with the numbers from this problem, not a generic list. |
| Interpret the confidence interval | 'We are 95% confident that the true [parameter in context] is between ... and ...' Anything about 95% of the data or a 95% chance is wrong. |
| Describe the distribution | Shape, centre, spread, and unusual features - All four, all in context, with units. |
| Explain whether the conclusion is reasonable | Compare the p-value to alpha, then answer the researcher's actual question in their words. |
What it tells you: Expresses a value in population standard-deviation units from the mean.
Conditions: $\sigma>0$ and the context must justify the distribution model used afterward.
Example: $x=85,\mu=70,\sigma=10$ gives $z=1.5$.
What it tells you: Estimates a population proportion with a long-run confidence procedure.
Conditions: Check randomization or representative sampling, independence, and large expected success and failure counts.
Example: With $\hat p=.60,n=400$, the standard error is about $.0245$.
What it tells you: Compares a sample mean with a null population mean when population spread is unknown.
Conditions: Observations should be independent and the sampling distribution sufficiently regular.
Example: $\bar x=52,\mu_0=50,s=8,n=16$ gives $t=1$.
What it tells you: Predicts a response and defines each vertical residual.
Conditions: A linear model should fit the scatterplot and residuals; extrapolation needs justification.
Example: If $\hat y=4+2x$ and $x=3$, the prediction is $10$.
Rules change from section to section. Multiple choice: graphing calculator with statistics functions. Free response: graphing calculator with statistics functions. Provided for the whole exam: formula sheet and tables. Practise each section under its own rule.
Multiple choice: 1 hour 30 minutes, 42 questions. Free response: 1 hour 30 minutes, 4 questions. Multiple choice - About 2.1 minutes each. Reading the scenario is most of the work; the arithmetic is usually small. Free response - About 22 minutes per question. These are long, multi-part scenarios - Read all parts before writing part (a).
One-Variable Data and Collecting Data (20–30%) carries the largest published weighting. Use the weighting to order your review, not to skip a prerequisite that a heavier unit depends on.
Yes. The AP Statistics exam gives you the formula sheet and tables. Formulas and the normal, t, and chi-square tables are given. Do not spend study time memorising them - Spend it on when each applies.