Linear Regression Models - AP Statistics

A streaming service sampled 20 users and recorded age ( $x$ , years, from 13 to 62) and average hours streamed per week ( $y$ ). A scatterplot with the least-squares regression line is shown, with fitted equation $\hat{y}=18.0-0.15x$ . The purpose of the linear model is to describe the linear association and predict typical weekly streaming time from age within the observed range. Which interpretation of the model is correct?
Answer: For each additional year of age, the predicted weekly streaming time decreases by about 0.15 hours, on average, for users like those sampled. This question tests interpretation of age-related regression models. The equation $\hat{y}=18.0-0.15x$ predicts weekly streaming hours from user age. The correct interpretation (A) states that for each additional year of age, predicted weekly streaming time decreases by about 0.15 hours on average. This properly acknowledges the associative and average nature of the relationship. Choice B incorrectly implies causation from aging itself. Choice C attempts to apply the model to newborns (age 0), far outside the observed range of 13-62 years. Choice D extrapolates to 120 years, well beyond the data range. Choice E completely misinterprets what the intercept represents. Linear models should only be used within the range of observed data - extrapolation to extreme ages produces unreliable and often nonsensical predictions.
A botanist measured sunlight exposure ( $x$ , hours/day, from 3 to 11) and plant height after 6 weeks ( $y$ , cm) for 10 plants of the same species. The least-squares regression line predicting height from sunlight is $\hat{y}=12.5+2.8x$ . The purpose of this linear model is to summarize the linear association and predict typical height for sunlight values in the observed range. Which interpretation of the model is correct?
Answer: Plants that get 1 more hour of sunlight per day are predicted to be about 2.8 cm taller after 6 weeks, on average, among plants like those studied. This question tests proper interpretation of slope in a biological context. The regression equation $\hat{y}=12.5+2.8x$ predicts plant height from sunlight exposure. The correct interpretation (A) states that plants getting 1 more hour of sunlight per day are predicted to be about 2.8 cm taller on average. This properly uses predictive language and acknowledges the average nature of the relationship. Choice B incorrectly treats the intercept prediction at 0 hours as reliable, when 0 is outside the observed range of 3-11 hours. Choice C wrongly claims the slope applies exactly to every plant. Choices D and E incorrectly imply causation - while the experiment might suggest causation, the regression model itself only describes association. Remember that regression models summarize average patterns and should not be used for predictions outside the data range.
A school counselor collected data from 12 students on the number of hours they studied for a final exam ( $x$ , from 1 to 9 hours) and their exam score ( $y$ , from 58 to 96). A least-squares regression line was fit to predict score from study time: $\hat{y}=52.0+4.8x.$ The purpose of this linear model is to summarize the association between study time and score and to predict typical exam score for a given study time within the observed range. Which interpretation of the model is correct?
Answer: For each additional hour studied, the predicted exam score increases by about 4.8 points, on average, for students in the range of 1–9 hours. This question tests understanding of slope interpretation in a linear regression model. The model $\hat{y}=52.0+4.8x$ has a slope of 4.8, which represents the average change in predicted exam score for each one-unit increase in study hours. Choice A correctly interprets this as "for each additional hour studied, the predicted exam score increases by about 4.8 points, on average" and appropriately limits this interpretation to the observed range of 1-9 hours. Choice B incorrectly treats the y-intercept as an exact prediction rather than a model estimate. Choice C incorrectly implies causation and claims the effect applies to every student exactly. Choice D incorrectly extrapolates far beyond the observed data range (1-9 hours) to 20 hours. Choice E confuses the slope coefficient with R-squared. Remember that regression models describe average relationships within the observed data range, not exact predictions or causal effects.
A fitness researcher recorded resting heart rate ( $y$ , beats per minute) and weekly minutes of aerobic exercise ( $x$ , from 0 to 240 minutes) for 14 adults. A scatterplot with the least-squares regression line is shown, with fitted equation $\hat{y}=78.0-0.06x$ . The purpose of the linear model is to describe the linear relationship and predict typical heart rate from exercise time within the observed range. Which interpretation of the model is correct?
Answer: An additional minute of aerobic exercise per week is associated with about a 0.06 bpm decrease in the predicted resting heart rate, on average, for adults like those sampled. This question examines interpretation of a health-related regression model. The equation $\hat{y}=78.0-0.06x$ predicts resting heart rate from weekly exercise minutes. The correct answer (A) properly interprets the slope: an additional minute of exercise per week is associated with about a 0.06 bpm decrease in predicted resting heart rate, on average. This uses appropriate statistical language avoiding causal claims. Choice B misinterprets the intercept as an exact value for all non-exercisers. Choice C demonstrates the danger of extrapolation - 1000 minutes is far beyond the observed range of 0-240 minutes. Choice D incorrectly implies causation and exact effects for everyone. Choice E confuses the intercept with R-squared. Linear models describe average associations within the observed data range, not causal mechanisms or guarantees for individuals.
A city analyst records average daily temperature ( $x$ , in $^\circ$ F) and electricity use ( $y$ , in kWh) for 15 spring days. A least-squares regression line is fit to predict electricity use from temperature: $\hat{y}=980-7.5x$ . The purpose of this linear model is to describe the linear relationship and predict typical electricity use for temperatures within the observed range. Which interpretation of the model is correct?
Answer: For each 1 $^\circ$ F increase in temperature, the predicted electricity use decreases by about 7.5 kWh, on average, for days with temperatures like those observed. This question assesses proper interpretation of a negative slope in linear regression. The equation $\hat{y}=980-7.5x$ has a slope of -7.5, meaning that for each 1°F increase in temperature, the predicted electricity use decreases by 7.5 kWh on average. Choice B correctly states this relationship using appropriate statistical language: "predicted," "about," and "on average." These qualifiers are crucial because regression models describe typical patterns, not exact values for every observation. Choice A incorrectly uses "exactly" and "every day," Choice C misinterprets the y-intercept as a guaranteed value, Choice D implies causation rather than association, and Choice E incorrectly equates the slope with correlation (correlation is unitless and bounded between -1 and 1). Remember that regression slopes describe average associations within the observed data range, not causal relationships or exact predictions.
A manager tracked advertising spending ( $x$ , in hundreds of dollars, from 2 to 25) and weekly sales ( $y$ , in thousands of dollars) for 11 weeks. The least-squares regression line predicting sales from ad spending is $\hat{y}=4.6+0.32x$ . The purpose of this linear model is to describe the linear association and predict typical weekly sales for ad spending values in the observed range. Which interpretation of the model is correct?
Answer: Spending an additional $100 on advertising is associated with an increase of about $0.32 thousand in predicted weekly sales, on average, for weeks like those observed. This question tests understanding of slope interpretation in a business context. The regression equation $\hat{y}=4.6+0.32x$ predicts weekly sales (in thousands) from advertising spending (in hundreds of dollars). The correct interpretation (A) states that spending an additional $100 on advertising is associated with an increase of about $0.32 thousand ($320) in predicted weekly sales, on average. This properly acknowledges the associative nature and average relationship. Choice B incorrectly claims causation and exact effects. Choice C misinterprets the intercept at $x=0$ as reliable when the data range is 2-25. Choice D misunderstands what the intercept represents. Choice E incorrectly extrapolates to $x=100$ (i.e., $10,000), far beyond the observed range. Remember that regression models are descriptive tools for the observed data range, not prescriptive formulas guaranteeing specific outcomes.
An ecologist measured 10 ponds for water temperature ( $x$ , in °C, from 12 to 24) and dissolved oxygen ( $y$ , in mg/L, from 5.1 to 10.8). The least-squares regression line predicting dissolved oxygen from temperature is $\hat{y}=13.2-0.30x.$ The purpose of this linear model is to summarize the linear association and predict typical dissolved oxygen for temperatures in the observed range. Which interpretation of the model is correct?
Answer: For each 1°C increase in water temperature, the predicted dissolved oxygen decreases by about 0.30 mg/L, on average, for ponds between 12°C and 24°C. This question tests understanding of slope interpretation with appropriate scope limitations. The model $\hat{y}=13.2-0.30x$ has a slope of -0.30, indicating that for each 1°C increase in temperature, the predicted dissolved oxygen decreases by 0.30 mg/L on average. Choice A correctly interprets this relationship and limits it to the observed temperature range of 12-24°C. Choice B incorrectly claims an exact decrease for every pond, ignoring natural variation. Choice C incorrectly extrapolates to 0°C (far outside the data range) and treats the prediction as fact. Choice D confuses the y-intercept value with R-squared percentage. Choice E extrapolates to 50°C, producing a negative dissolved oxygen value, which is physically impossible and demonstrates the danger of extrapolation. Regression models describe average trends within the data range, not exact relationships or predictions outside that range.
A teacher compared 11 students' average homework completion rate ( $x$ , in percent, from 60 to 100) with their course average ( $y$ , in percent, from 62 to 98). The least-squares regression line predicting course average from homework completion is $\hat{y}=25.0+0.70x.$ The purpose of this linear model is to summarize the linear association and predict a typical course average for a given completion rate within the observed range. Which interpretation of the model is correct?
Answer: For each 1 percentage point increase in homework completion, the predicted course average increases by about 0.70 percentage points, on average, for completion rates between 60% and 100%. This question tests interpretation of slope in percentage contexts. The model $\hat{y}=25.0+0.70x$ has a slope of 0.70, meaning for each 1 percentage point increase in homework completion, the predicted course average increases by 0.70 percentage points. Choice A correctly states this relationship and limits it to the observed range of 60-100% completion. Choice B incorrectly treats the y-intercept as an exact prediction for 0% completion, which is far outside the observed data range. Choice C incorrectly implies causation and exact effects for every student. Choice D misinterprets the y-intercept as a minimum requirement. Choice E extrapolates to an impossible 140% completion rate and suggests a course average above 100% is realistic. When both variables are percentages, the slope represents the change in one percentage for each unit change in the other percentage.
A school counselor collects data from 12 students on weekly study time ( $x$ , hours) and their quiz score ( $y$ , points). A least-squares regression line is fit to predict quiz score from study time, with equation $\hat{y}=58+3.2x$ . The purpose of this linear model is to summarize the linear association and predict typical quiz scores for students with study times similar to those observed. Which interpretation of the model is correct?
Answer: For each additional hour studied per week, the predicted quiz score increases by about 3.2 points, on average, for students with study times like those in the data. This question tests understanding of slope interpretation in linear regression models. The regression equation $\hat{y}=58+3.2x$ has a slope of 3.2, which represents the average change in predicted quiz score for each one-unit increase in study time. Choice A correctly interprets this as "for each additional hour studied per week, the predicted quiz score increases by about 3.2 points, on average." The key phrases "predicted," "on average," and "for students with study times like those in the data" properly acknowledge that this is a statistical model describing typical patterns, not exact values or causal relationships. Choices B and D incorrectly treat predictions as exact values, Choice C incorrectly implies causation, and Choice E confuses the slope with R-squared. Linear regression models describe associations and make predictions about typical values within the observed data range, not exact outcomes or causal effects.
A school counselor collected data from 12 students on the number of hours they studied for a final exam ( $x$ , from 1 to 9 hours) and their exam score ( $y$ , in points). A least-squares regression line was fit to predict score from study hours: $\hat{y}=58.2+4.1x$ . The purpose of this linear model is to summarize the linear association and predict typical exam score from study time within the observed range. Which interpretation of the model is correct?
Answer: For each additional hour studied, the predicted exam score increases by about 4.1 points, on average, for students similar to those in the data. This question tests understanding of slope interpretation in a linear regression model. The regression equation $\hat{y}=58.2+4.1x$ models the relationship between study hours and exam scores. The correct interpretation (B) states that for each additional hour studied, the predicted exam score increases by about 4.1 points on average for students similar to those in the data. This properly acknowledges that the slope represents an average association, not a guarantee for individuals. Choice C incorrectly implies causation and exact outcomes for every student. Choice A misinterprets the intercept as a guarantee rather than a prediction. Choice D incorrectly extrapolates to 20 hours, which is far beyond the observed range of 1-9 hours. Choice E confuses the intercept with R-squared. Remember that regression models describe average relationships within the observed data range, not causal effects or guarantees for individuals.
A district analyzed 10 schools, recording average class size ( $x$ , students per class, from 18 to 34) and average standardized test score ( $y$ , points). A least-squares regression line was fit: $\hat{y}=610-3.5x$ . The purpose of this linear model is to summarize the linear association and predict typical test score from class size within the observed range. Which interpretation of the model is correct?
Answer: For each additional student in average class size, the predicted average test score decreases by about 3.5 points, on average, for schools like those studied. This question examines proper interpretation of regression in educational policy context. The equation $\hat{y}=610-3.5x$ predicts average test scores from average class size. The correct answer (B) properly interprets the slope: for each additional student in average class size, the predicted average test score decreases by about 3.5 points on average. This uses appropriate statistical language avoiding causal claims. Choice A incorrectly implies causation - while smaller classes might cause higher scores, the regression only shows association. Choice C misinterprets the intercept at 0 students per class as meaningful. Choice D wrongly claims class size is the only factor. Choice E incorrectly states that negative slope means zero correlation when it actually indicates negative correlation. Regression models describe associations in observational data but cannot prove causation without proper experimental design.
A nutrition researcher measures daily sugar intake ( $x$ , grams) and fasting blood glucose ( $y$ , mg/dL) for 13 adults. A least-squares regression line is fit to predict fasting glucose from sugar intake: $\hat{y}=84+0.15x$ . The purpose of this linear model is to summarize the association and predict typical fasting glucose for sugar intakes similar to those observed. Which interpretation of the model is correct?
Answer: For each additional gram of sugar consumed per day, the predicted fasting glucose increases by about 0.15 mg/dL, on average, for adults like those in the study. This question tests understanding of slope interpretation in a health research context. The equation $\hat{y}=84+0.15x$ indicates that for each additional gram of sugar consumed daily, the predicted fasting glucose increases by 0.15 mg/dL on average. Choice A correctly interprets this relationship using proper statistical language and acknowledges the model applies to "adults like those in the study." This phrasing is crucial because the model's validity depends on the study population and data range. Choice B incorrectly implies causation (observational studies can't prove causation), Choice C treats the y-intercept as an exact value, Choice D confuses the slope with a percentage of variance explained, and Choice E incorrectly links positive slope to perfect linearity. Linear regression models describe average associations in the observed data, not causal effects or exact individual outcomes.
A marine scientist records water salinity ( $x$ , parts per thousand) and the density of a certain plankton species ( $y$ , organisms per liter) at 12 sampling sites. A least-squares regression line is fit to predict plankton density from salinity: $\hat{y}=210-4.6x$ . The purpose of this linear model is to describe the linear relationship and predict typical plankton density for salinity values within the observed range. Which interpretation of the model is correct?
Answer: At sites with salinity values like those observed, an increase of 1 part per thousand in salinity is associated with a decrease of about 4.6 organisms per liter in the predicted plankton density, on average. This question tests interpretation of a negative slope in an ecological context. The equation $\hat{y}=210-4.6x$ shows that for each one-unit increase in salinity (parts per thousand), the predicted plankton density decreases by 4.6 organisms per liter on average. Choice A correctly interprets this relationship, using proper statistical language including "predicted," "about," and "on average," while specifying "at sites with salinity values like those observed." This acknowledges the model's limited scope to the observed data range. Choice B incorrectly implies causation, Choice C treats the y-intercept as an exact value, Choice D confuses slope with correlation (correlation is unitless), and Choice E makes an incorrect mathematical claim about proportional relationships. Remember that linear regression describes average associations within the data, not causal effects or exact predictions.
A real-estate agent records home size ( $x$ , in hundreds of square feet) and sale price ( $y$ , in thousands of dollars) for 11 recently sold homes in one neighborhood. A least-squares regression line is fit to predict sale price from size: $\hat{y}=45+18x$ . The purpose of this linear model is to summarize the linear relationship and predict typical sale price for home sizes within the observed range in this neighborhood. Which interpretation of the model is correct?
Answer: For each additional 100 square feet of home size, the predicted sale price increases by about $18,000, on average, for homes like those in the data. This question assesses understanding of slope interpretation in a real estate context where units matter. The equation $\hat{y}=45+18x$ with x in hundreds of square feet and y in thousands of dollars means the slope of 18 represents an $18,000 increase per 100 square feet. Choice B correctly interprets this as "for each additional 100 square feet, the predicted sale price increases by about $18,000, on average." The phrases "predicted," "about," and "on average" properly acknowledge statistical variability, while "for homes like those in the data" recognizes the model's limited scope. Choice A incorrectly uses "exactly," Choice C implies causation, Choice D misunderstands that x=0 is likely outside the data range (no 0-square-foot homes), and Choice E confuses slope with correlation. Linear regression describes average patterns within the observed data, not exact values or causal relationships.
An environmental scientist models ozone level ( $y$ , in ppb) from traffic volume ( $x$ , in thousands of cars per day) using data from days with traffic between 10 and 60 (thousand cars). The regression line is $\hat{y}=18+1.1x$ . The purpose of the linear model is to describe the association and predict typical ozone levels for traffic volumes in the observed range. Which interpretation of the model is correct?
Answer: For each additional 1,000 cars per day (within 10–60 thousand), the predicted ozone level increases by about 1.1 ppb, on average. This question tests understanding of slope interpretation in an environmental science context. The regression equation $\hat{y}=18+1.1x$ models predicted ozone levels from traffic volume (in thousands of cars), where the slope 1.1 represents the average change in predicted ozone per thousand cars. Choice A correctly states "for each additional 1,000 cars per day, the predicted ozone level increases by about 1.1 ppb, on average." Choice B incorrectly treats the intercept as an actual value rather than a prediction outside the data range. Choice C reverses causation, suggesting ozone causes traffic changes. Choice D claims direct causation from an observational study. Choice E extrapolates to 100 thousand cars, well beyond the observed range of 10-60 thousand. Regression models from observational data describe associations, not causal relationships, and should not be extrapolated beyond their data range.
A fitness coach records resting heart rate ( $y$ , beats per minute) and weekly aerobic exercise time ( $x$ , minutes) for 14 clients. A least-squares regression line is fit to predict resting heart rate from exercise time: $\hat{y}=78.4-0.06x$ . The purpose of this linear model is to describe the association and predict typical resting heart rate for clients with exercise times similar to those observed. Which interpretation of the model is correct?
Answer: For each additional minute of weekly aerobic exercise, the predicted resting heart rate decreases by about 0.06 beats per minute, on average, for clients like those in the data. This question tests interpretation of a regression model with a negative slope in a health context. The equation $\hat{y}=78.4-0.06x$ indicates that for each additional minute of weekly exercise, the predicted resting heart rate decreases by 0.06 beats per minute on average. Choice A correctly interprets this relationship using appropriate statistical language and acknowledges the model applies to "clients like those in the data." Choice B incorrectly treats the y-intercept as an exact value, Choice C implies causation, Choice D incorrectly links negative slope to nonlinearity (linear models can have negative slopes), and Choice E confuses the y-intercept value with R-squared percentage. Remember that regression models describe average associations, not individual outcomes or causal effects, and their reliability depends on staying within the observed data range.
A real estate agent uses a linear model to predict selling price ( $y$ , in thousands of dollars) from house size ( $x$ , in square feet) based on homes between 1,200 and 3,000 sq ft. The regression equation is $\hat{y}=45+0.18x$ . The purpose of the model is to describe the linear relationship and predict typical prices for sizes in the observed range. Which interpretation of the model is correct?
Answer: A 1 sq ft increase in size (within 1,200–3,000 sq ft) is associated with an increase of about $0.18$ thousand dollars ($$180) in the predicted selling price, on average. This question evaluates understanding of slope interpretation in a real estate context. The regression equation $\hat{y}=45+0.18x$ models predicted selling price (in thousands) from house size, where the slope 0.18 represents the average change in predicted price per square foot. Choice A correctly interprets this as "a 1 sq ft increase in size is associated with an increase of about $0.18$ thousand dollars ($180) in the predicted selling price, on average." Choice B misinterprets the intercept as a minimum value. Choice C claims causation and exactness rather than association and average prediction. Choice D extrapolates to 5,000 sq ft, beyond the observed range of 1,200-3,000 sq ft. Choice E reverses the roles of predictor and response variables. Linear models are descriptive tools for the observed data range and should not be extrapolated beyond that range.
A nutrition researcher models resting heart rate ( $y$ , beats per minute) from daily caffeine intake ( $x$ , in mg) for adults in a sample with intakes between 0 and 400 mg. The least-squares regression line is $\hat{y}=62+0.03x$ . The purpose of the linear model is to summarize the association and predict typical resting heart rate for given caffeine intake within the data range. Which interpretation of the model is correct?
Answer: For each additional 1 mg of caffeine (within 0–400 mg), the predicted resting heart rate increases by about 0.03 bpm, on average. This question tests understanding of slope interpretation in a health-related context. The regression equation $\hat{y}=62+0.03x$ models predicted resting heart rate from caffeine intake, where the slope 0.03 indicates the average change in predicted heart rate per mg of caffeine. Choice B correctly states "for each additional 1 mg of caffeine, the predicted resting heart rate increases by about 0.03 bpm, on average." Choice A misinterprets the slope as a comparison between groups. Choice C treats the prediction as an exact individual value rather than an average. Choice D incorrectly claims causation from an observational study. Choice E extrapolates to 1000 mg, well beyond the observed range of 0-400 mg. Remember that regression models describe average relationships and should not be used for predictions outside the data range, as the linear relationship may not hold.
A botanist recorded 13 plants' weekly sunlight exposure ( $x$ , in hours, from 10 to 45) and their weekly growth ( $y$ , in cm, from 1.2 to 9.5). The least-squares regression line predicting growth from sunlight is $\hat{y}=0.8+0.18x.$ The purpose of this linear model is to describe the linear trend and predict typical growth for plants within the observed sunlight range. Which interpretation of the model is correct?
Answer: For each additional hour of sunlight per week, the predicted weekly growth increases by about 0.18 cm, on average, for plants receiving 10–45 hours. This question assesses understanding of appropriate slope interpretation. The model $\hat{y}=0.8+0.18x$ has a slope of 0.18, indicating that for each additional hour of weekly sunlight, the predicted weekly growth increases by 0.18 cm on average. Choice A correctly interprets this relationship and appropriately restricts it to the observed range of 10-45 hours. Choice B incorrectly claims an exact increase for every plant, ignoring variation. Choice C inappropriately extrapolates to 0 hours (complete darkness) and treats the model prediction as fact outside the data range. Choice D incorrectly claims sunlight is the only factor affecting growth. Choice E incorrectly infers causation from correlation - while the model shows association, it cannot prove causation from observational data. Linear models describe average relationships, not exact predictions or causal mechanisms.
A researcher recorded the distance from a city center ( $x$ , in miles) and the monthly rent for a one-bedroom apartment ( $y$ , in dollars) for 13 apartments, with distances ranging from 1 to 18 miles. A least-squares regression line is $\hat{y}=1850-42x.$ The purpose of this linear model is to summarize the linear association and predict typical rents for apartments within the observed distance range. Which interpretation of the model is correct?
Answer: Each additional mile from the city center is associated with a decrease of about $42 in the predicted monthly rent, on average, for apartments like those observed. The skill is interpreting \hat{y} = 1850 - 42x for rent versus distance (x from 1 to 18 miles). The slope shows each mile farther associates with $42 lower predicted rent on average in the range. Choice A is correct, avoiding causation and sticking to data. Choice B distracts by claiming direct causation from distance to rent drop. Choice C misinterprets the intercept as exact for zero miles. Limitation: no extrapolation, unlike choice D to 40 miles. Intercepts estimate averages but may not reflect reality outside data.

Start this quiz