One of our favorite activities of the year is to make AP Exam predictions for our students. We spend all year earning their trust, so that they believe in our clairvoyant abilities. Inevitably, some of our predictions will be __better__ than __others__ (we're still mad about chi-square test two years in a row!). With the __2020 AP Stats Exam being much different format__ than a traditional AP Stats Exam, we will make some predictions about formatting and grading, as well as the usual predictions about content.

So here is what our AP Statistics crystal ball is telling us for 2020.

**It Will Cover All 7 Units From the CED**

This means that students can expect at least part of a question to cover (1) One-variable Data, (2) Two-variable Data, (3) Collecting Data, (4) Probability, (5) Sampling Distributions, (6) Inference for Proportions, and (7) Inference for Means. Of these units, the ones that are more likely to get 2+ parts would be (1), (3), (6), and (7).

The College Board has communicated that Question #1 will be worth 55% of the overall score and Question #2 will be worth 45% of the overall score. If each part of the question is worth 1 point, a total of 11 parts would make this possible (6/11 = 55% and 5/11 = 45%). With 25 minutes for the first question and 15 minutes for the second question, this means that students will need to be working a bit faster on the parts of the second question.

**Inference Questions Will Look Different**

In the past, students could expect to see one question where they constructed and interpreted a confidence interval and one question where they performed a full significance test. There is no room for this in 2020. Instead, the exam is likely to ask about specific elements within each of these inference procedures, such as:

Confidence Interval

Define parameter(s)

Name the procedure.

Check conditions or explain why we check conditions.

Interpret a confidence interval.

Interpret a confidence level.

Based on a confidence interval, do we have convincing evidence for a claim?

Significance Test

Write hypotheses (including defining parameters).

Name the procedure.

Check conditions or explain why we check conditions.

Use a test statistic to calculate a

*P*-value.Interpret a

*P*-value.Make a conclusion.

**How to Assess a Full Stats Course in Two Questions**

One question about means and one question about proportions.

One question that is one-sample and one question that is two-sample (or two groups).

One question that includes elements of a confidence interval and one question that includes elements of a significance test.

One question that involves sampling and one question that involves an experiment.

**How Will It Be Graded?**

Each part of the question should be worth 1 point and will be graded as E - essentially correct (+1), P - partially correct (+1/2), or I - incorrect (+0) and we are predicting 11 points total. Cutoff values for overall scores of 1 - 5 will be determined after the College Board looks at the overall distribution of points.

For a specific example of what we think the 2020 Exam might look like, check out our __2020 Practice Exam__.

**One Final Prediction **

With over 200,000 students logging in and uploading answers in 5-minute windows, there are going to be tech problems for some students. We will hear all of these stories and none of the stories of the uploads that went smoothly. Let's remember that voluntary response often does not create a representative sample.

Good luck 2020 AP Stats teachers and students!

## Comments