Worksheets · AP Statistics · Unit 5

AP Statistics Unit 5 FRQ Practice: Regression

Unit 5: Regression Analysis

Two exam-style free-response questions on regression, each scored out of 10 points with a scoring guide and a printable PDF with room to write, free to use in class. Good practice before the Unit 5 Progress Check in AP Classroom. Multiple choice for this unit: Unit 5 worksheet.

Sigma Prep · sigmaprep.io/worksheets/ap-statistics

Name

AP Statistics Unit 5 Free Response: Regression

Date

Directions: Show all your work. Indicate clearly the methods you use, because you will be scored on the correctness of your methods as well as on the accuracy and completeness of your results and explanations. Answer in the context of the question. Each question is worth 10 points, and each point is earned on its own. A graphing calculator with statistical capabilities may be used, and the exam’s formula sheet and tables apply.

Questions 1 and 2 practice the kinds of questions in Questions 2 and 4 of the exam’s free-response section. The exam’s Questions 1 and 3 (data collection and inference) carry little of Unit 5’s official free-response points, so the set has no question in their style.

Free response

Questions 1–2
  1. 1.
    A poultry farmer recorded the age, in months, of 19 laying hens and the number of eggs each hen laid in one month. The computer output below is from a least-squares regression of number of eggs laid in a month on age. A scatterplot of the data and the residual plot, with the residuals plotted against age, are shown.
    {"xs":[8,9,11,13,14,16,18,20,21,23,26,27,29,30,32,34,36,37,39],"ys":[25,26,28,24,25,26,25,25,22,23,20,24,22,20,19,20,21,20,18]}182022242628Number of eggs laid in a month010203040Age (months){"xs":[8,9,11,13,14,16,18,20,21,23,26,27,29,30,32,34,36,37,39],"ys":[-1.6332716749209375,-0.3823020466614935,2.119637209857391,-1.3784235336237245,-0.12745390536428403,1.374485351154604,0.8764246076734885,1.378363864192373,-1.370666507548183,0.1312727489707015,-2.11581836625097,2.1351512620084705,0.6370905185273585,-1.111939853213201,-1.610000596694313,-0.10806134017543201,1.393877916343456,0.6448475446028965,-0.8532131988782155]}-3-2-10123Residual010203040Age (months){"xName":"Age","yName":"Eggs","a":28.64102870099648,"b":-0.25096962825944263,"seA":0.8246687719720768,"seB":0.032688073313160364,"tA":34.730342259117656,"tB":-7.677712474977874,"pA":3.148816832918861e-17,"pB":6.359697264995741e-7,"s":1.372940041039551,"r2":0.7761604826905999,"r2adj":0.7629934522606352,"dpA":3,"dpB":4,"short":true}PredictorCoefSE CoefConstant28.6410.8247Age-0.25100.03269S = 1.373R-Sq = 77.6%R-Sq(adj) = 76.3%
    1. (A)
      Describe the association between age and number of eggs laid in a month shown in the scatterplot.
    2. (B)
      (i) Write the equation of the least-squares regression line, defining any variables used. (ii) Interpret the slope of the line in context.
    1. (C)
      (i) Use the line to predict the number of eggs laid in a month for a hen that was 19 months old. (ii) One hen in the data was 11 months old and laid 28 eggs that month. Calculate and interpret the residual for this hen.
    2. (D)
      (i) Find the correlation between age and number of eggs laid in a month. (ii) Interpret R-Sq and S in context.
    1. (E)
      Is a linear model appropriate for these data? Justify your answer using the residual plot.
  2. 2.
    A city's electric utility selected a simple random sample of 18 homes from its list of all 85,000 homes it serves and recorded the floor area, in square meters, and the electricity used in January, in kilowatt-hours. A scatterplot of the data is shown. The mean floor area is xˉ=139.8\bar{x} = 139.8 square meters with standard deviation sx=46.87s_x = 46.87 square meters; the mean monthly electricity use is yˉ=499.6\bar{y} = 499.6 kilowatt-hours with standard deviation sy=141.26s_y = 141.26 kilowatt-hours; and the correlation is r=0.925r = 0.925.
    {"xs":[62,75,82,92,102,112,118,125,137,145,152,160,172,180,187,195,205,216],"ys":[311,288,345,475,351,361,366,472,436,583,573,543,538,715,615,629,668,723]}200300400500600700800Monthly electricity use (kilowatt-hours)50100150200250Floor area (square meters)
    1. (A)
      (i) Describe how the city's electric utility could use a random number generator to select the simple random sample of 18 homes from its list of all 85,000 homes it serves. (ii) Another plan would use strata based on heating type. Explain one benefit of a stratified random sample here.
    2. (B)
      (i) Use the summary statistics to calculate the slope of the least-squares regression line for predicting monthly electricity use from floor area. (ii) Calculate the intercept, and write the equation of the line. (iii) Explain what the correlation tells you about the predicted monthly electricity use for a floor area one standard deviation above the mean.
    1. (C)
      Suppose the floor area had been recorded in square feet instead. Would the correlation change? Explain.
    2. (D)
      Does the intercept of the line have a reasonable interpretation in this context? Explain.
    1. (E)
      (i) To what population can the results of this study be generalized? Explain. (ii) A news report says that the data show that changing the floor area of a home would change its monthly electricity use. Explain why the study does not support this claim. (iii) Identify a variable that could be confounded with the floor area, and explain how it could account for the association.

      End of the free-response questions

Free AP Statistics worksheets at sigmaprep.io/worksheets/ap-statisticsOriginal questions written by Sigma Prep. AP is a registered trademark of the College Board, which is not affiliated with this sheet.

Scoring guide

Each point is earned on its own: a response earns a point when it meets that point’s requirement, whatever it earned on the others. The model answers are one complete response; “Also acceptable” names other responses that earn the same point.

Question 1: Reading a regressionLike exam Question 2 (Practices 3 and 4: analyzing data and drawing conclusions) · 10 points

(A) 1 point

  1. Point 1. Direction, form and strength, with any unusual feature, in context. (Practice 4)

    Model answer: There is a strong, negative, linear association between age and number of eggs laid in a month, with no unusual points: older hens tend to have lower monthly egg counts.

    Also acceptable: Any other correct, complete description in context earns the point.

(B) 2 points

  1. Point 2. Correct equation from the output, with the variables defined. (Practice 3)

    Model answer: (i) Eggs^=28.641−0.2510(Age)\widehat{\text{Eggs}} = 28.641 - 0.2510(\text{Age}), where Age is the age in months and Eggs is the predicted number of eggs laid in a month (intercept a=28.641a = 28.641, slope b=−0.2510b = -0.2510).

  2. Point 3. The slope as a predicted (average) change per unit of xx, in context. (Practice 4)

    Model answer: (ii) For each additional month of age, the predicted number of eggs laid in a month decreases by 0.2510 eggs.

    Also acceptable: “On average” in place of “predicted”.

    Also acceptable: Any other correct, complete interpretation in context earns the point.

(C) 3 points

  1. Point 4. Correct prediction. (Practice 3)

    Model answer: (i) Eggs^=28.641−0.2510(19)=23.87\widehat{\text{Eggs}} = 28.641 - 0.2510(19) = 23.87 eggs.

  2. Point 5. Correct residual, observed minus predicted. (Practice 3)

    Model answer: (ii) The predicted value is 28.641−0.2510(11)=25.8828.641 - 0.2510(11) = 25.88, so the residual is 28−25.88=2.1228 - 25.88 = 2.12 eggs.

  3. Point 6. The residual interpreted: the actual value is above or below the prediction, by how much, in context. (Practice 4)

    Model answer: The actual number of eggs laid in a month for this hen is 2.12 eggs more than the line predicts.

    Also acceptable: Any other correct, complete interpretation in context earns the point.

    Also acceptable: Carried-forward credit: a response that uses its own value from Point 5 (here 2.12) earns this point when its answer here is correct for that value.

(D) 3 points

  1. Point 7. rr from R-Sq, with the sign of the slope. (Practice 3)

    Model answer: (i) r=−0.776=−0.881r = -\sqrt{0.776} = -0.881; it is negative because the slope is negative.

  2. Point 8. R-Sq: percent of the variation in the response explained by the linear relationship with xx. (Practice 4)

    Model answer: (ii) About 77.6% of the variation in number of eggs laid in a month is explained by the linear relationship with age.

    Also acceptable: Any other correct, complete interpretation in context earns the point.

  3. Point 9. S: the typical distance between actual and predicted values, in context and units. (Practice 4)

    Model answer: The actual number of eggs laid in a month typically differs from the number of eggs laid in a month predicted by the line by about 1.373 eggs.

    Also acceptable: Any other correct, complete interpretation in context earns the point.

(E) 1 point

  1. Point 10. Yes, with the residual plot showing no pattern (random scatter around 0). (Practice 4)

    Model answer: Yes. The residual plot shows no curved or other pattern; the residuals are scattered randomly around 0, so a linear model is appropriate.

    Also acceptable: Also noting that the spread of the residuals grows (or shrinks) across the plot, as long as the answer still says a linear model is appropriate because there is no curved pattern.

    Also acceptable: Any other correct, complete justification in context earns the point.

Question 2: A regression study and its designLike exam Question 4 (Practices 2, 3 and 4) · 10 points

(A) 2 points

  1. Point 1. Labels every unit in the list, uses a random number generator to choose labels, and ignores repeats until the sample size is reached. (Practice 2)

    Model answer: (i) Number the homes on the list from 1 to 85,000. Use a random number generator to pick whole numbers from 1 to 85,000, ignoring repeats, until 18 different numbers are chosen; the homes with those numbers are the sample.

    Also acceptable: Any equivalent use of a random number generator (for example, giving every home on the list a random number and taking the 18 smallest).

    Also acceptable: Any other correct, complete method earns the point.

  2. Point 2. Gives one correct benefit, in context: an estimate with less variability (because the strata differ in the response), or every stratum represented in the sample. (Practice 2)

    Model answer: (ii) Homes with the same heating type tend to use similar amounts of electricity, so a stratified sample gives estimates with less variability than a simple random sample of the same size.

    Also acceptable: The other benefit: sampling within each stratum makes sure every heating type is represented.

    Also acceptable: Any other correct, complete justification in context earns the point.

(B) 3 points

  1. Point 3. Correct slope, b=rsysxb = r\frac{s_y}{s_x}. (Practice 3)

    Model answer: (i) b=rsysx=0.925(141.2646.87)=2.7878b = r\frac{s_y}{s_x} = 0.925\left(\frac{141.26}{46.87}\right) = 2.7878 kilowatt-hours per square meter.

  2. Point 4. Correct intercept from the point of means, a=yˉ−bxˉa = \bar{y} - b\bar{x}, with the equation. (Practice 3)

    Model answer: (ii) The line passes through (xˉ,yˉ)(\bar{x}, \bar{y}), so a=499.6−(2.7878)(139.8)=109.87a = 499.6 - (2.7878)(139.8) = 109.87. The equation is kWh^=109.87+2.7878(Area)\widehat{\text{kWh}} = 109.87 + 2.7878(\text{Area}), where Area is the floor area in square meters and kWh is the predicted monthly electricity use in kilowatt-hours.

    Also acceptable: An intercept computed from the unrounded slope, or from a slope rounded to two or more decimal places, to rounding.

    Also acceptable: Carried-forward credit: a response that uses its own value from (B)(i) (here 2.7878) earns this point when its answer here is correct for that value.

  3. Point 5. The predicted monthly electricity use is 0.925 standard deviations of monthly electricity use above its mean: the slope in standard-deviation units is rr. (Practice 4)

    Model answer: (iii) Because b=rsysxb = r\frac{s_y}{s_x}, a floor area one standard deviation above the mean (46.87 square meters above 139.8) has a predicted monthly electricity use that is 0.925 standard deviations of monthly electricity use above the mean monthly electricity use.

    Also acceptable: Any other correct, complete justification in context earns the point.

(C) 1 point

  1. Point 6. No: rr has no units, and changing the units of a variable (a linear change with a positive factor) does not change rr. (Practice 4)

    Model answer: No. The correlation has no units: recording the floor area in square feet multiplies every value by the same positive number, which does not change the strength or direction of the linear relationship, so rr would still be 0.925.

    Also acceptable: Any other correct, complete justification in context earns the point.

(D) 1 point

  1. Point 7. No, with one correct reason: x=0x = 0 is outside the data (so the intercept is an extrapolation), or an xx of 0 is not meaningful in context. One reason is enough. (Practice 4)

    Model answer: No. A value of 0 for the floor area is outside the data's values (62 to 216 square meters), so the intercept is an extrapolation with no reasonable meaning here.

    Also acceptable: A context reason alone: an xx of 0 is not meaningful here, because no home has a floor area of 0 square meters, so the intercept describes no real home.

    Also acceptable: Any other correct, complete justification in context earns the point.

(E) 3 points

  1. Point 8. To the population listed, because the units were a simple random sample from it. (Practice 2)

    Model answer: (i) To all homes served by the city's electric utility, because the homes were a simple random sample from its list of all 85,000 homes it serves.

    Also acceptable: Any other correct, complete justification in context earns the point.

  2. Point 9. Observational: nothing was assigned, so the association does not show cause and effect. (Practice 4)

    Model answer: (ii) This is an observational study: the city's electric utility recorded the floor area of each home; it did not assign it. An association between the variables does not show that changing one causes a change in the other.

    Also acceptable: Any other correct, complete justification in context earns the point.

  3. Point 10. Names a plausible confounding variable and links it to both variables. (Practice 2)

    Model answer: (iii) One possible confounding variable is the number of people living in the home. Homes with more people tend to be larger, and more people use more electricity (more lights, appliances and hot water), so the number of people alone could produce a positive association between floor area and electricity use.

    Also acceptable: Any other variable plausibly linked to both, with the link explained.

    Also acceptable: Any other correct, complete justification in context earns the point.

What does the AP Statistics free response ask on Unit 5?

Unit 5 carries about a tenth of the AP Statistics free response: 94 of the 1,040 points on the 124 official free-response questions we counted (9.1%), and none of the 40 points in the four 2026 sample questions.

  • Question 2 is where regression shows up. On the 2027 exam, Question 2 assesses Practices 3 and 4: analyzing data and drawing conclusions. 11 official free-response questions from 2012 to 2026 that fit Question 2 had a Unit 5 part, most recently in 2026, and a regression was the whole setting of 7 of them, most recently in 2023.
  • Regression is asked less than it was. Unit 5 parts carried 15.1% of the free-response points on the 2012–2018 exams and 7.3% on the 2019–2026 exams.
  • Inference for the slope has left the course. The 2026 course drops the t-interval and t-test for the slope of a regression line. 4 official free-response questions we counted had a part on it (1 on an exam, in 2023, and 3 on practice exams); this set has none.
  • Every point is earned on its own. From 2027 each free-response question is worth 10 points, scored analytically: each point has its own requirement, and a later point does not depend on an earlier one.

The exam's Questions 1 and 3 carry little of Unit 5's official free-response points, so this set is practice for Question 2 of the exam, where regression shows up, and for a Question 4 built on a regression study: how its sample was chosen, its least-squares line from summary statistics, and what it allows you to conclude. No official question in the Question 4 slot has had a Unit 5 part yet. Every question and scoring guide is original.

Counted from the official AP Statistics free-response questions: the 2012–2026 exams, the practice exams and the 2026 course-description samples. No official question is reproduced here.

How often does the AP Statistics free response use each Unit 5 setting?

Settings of the questions on this set, and how many official AP Statistics free-response questions used each, 2012–2026
SettingQuestions on this setOfficial FRQs, 2012–2026Of them since 2019Last on the exam
Reading a regressionBivariate data and regression · exam Question 21 of 2722023
A regression study and its designQuestion 4 with a Unit 5 part · exam Question 41 of 200–

Counts are of the 84 operational free-response questions, 2012–2026 (no 2020 exam was released), by the setting of the whole question. The Question 4 row counts questions that fit the exam’s new Question 4 and have a Unit 5 part.

Questions about this free-response set

Unit 5, Regression Analysis, has 5 topics in the College Board's 2026 course and exam description: scatterplots of two quantitative variables and describing their direction, form, strength and unusual features; correlation; linear regression models, predicting with the line and the difference between interpolation and extrapolation; residuals and residual plots; and the least-squares regression line, its slope and intercept in context, the coefficient of determination r² and the standard deviation of the residuals s. Inference for the slope of a regression line is no longer in the course. The course description weights the unit at 10–20% of the multiple-choice section.

Each of the four free-response questions is worth 10 points, scored analytically: every point has its own requirement (a variable named and classified, a sampling method identified, a comparison made in context with values), and each is earned on its own. The scoring guide here lists all 10 points of every question, with a model answer for each and the other responses that also earn it. The free-response section is half of the exam score.

The 2027 exam's Section II has four questions: Question 1 on Practices 1 and 2 (the investigative question and collecting data), Question 2 on Practices 3 and 4 (analyzing data and drawing conclusions), Question 3 on inference, and Question 4 on Practices 2, 3 and 4. The exam's Questions 1 and 3 (data collection and inference) carry little of Unit 5's official free-response points, so this set has two questions, in the style of Questions 2 and 4.

Yes. A graphing calculator with statistical capabilities is allowed throughout the exam, and the exam supplies a formula sheet and tables. From 2027 the free-response answers are typed in Bluebook; this set prints with room to write so it can be done on paper in class.

We tagged every official free-response question from 2012 to 2026 (and the four 2026 course-description samples) by its setting and by the exam question it would fill from 2027. Each question here is in a setting the exam uses for that question: a regression read from computer output with a scatterplot and a residual plot, and a regression study on a random sample with its least-squares line from summary statistics.

No. Every question here is original, written by Sigma Prep in the style of the exam: the settings, data and wording are our own, and no official question or scoring guideline is copied or reworded. Every number and every claim a scoring point makes (the method, the bias, the direction, the scope of a conclusion) was checked by an independent computer check before the set was published.

AP is a registered trademark of the College Board, which was not involved in making these questions and does not endorse them. All questions and scoring guides are original to Sigma Prep. Frozen 2026-11-20.