Practice sheet
Fresh questions from the whole chapter, to do on paper.
To save a PDF, choose “Save as PDF” in the print dialog.
- A survey asked 145 people whether they exercise weekly. Under 30: 22 yes, 43 no. Age 30 or over: 27 yes, 53 no. What proportion of the under-30s exercise weekly?A survey asked 121 people whether they exercise weekly. Under 30: 59 yes, 12 no. Age 30 or over: 23 yes, 27 no. What proportion of the under-30s exercise weekly?A survey asked 150 people whether they exercise weekly. Under 30: 41 yes, 40 no. Age 30 or over: 19 yes, 50 no. What proportion of the under-30s exercise weekly?A survey asked 121 people whether they exercise weekly. Under 30: 33 yes, 20 no. Age 30 or over: 25 yes, 43 no. What proportion of the under-30s exercise weekly?A survey asked 193 people whether they exercise weekly. Under 30: 51 yes, 49 no. Age 30 or over: 37 yes, 56 no. What proportion of the under-30s exercise weekly?A survey asked 143 people whether they exercise weekly. Under 30: 50 yes, 24 no. Age 30 or over: 12 yes, 57 no. What proportion of the under-30s exercise weekly?A survey asked 114 people whether they exercise weekly. Under 30: 35 yes, 34 no. Age 30 or over: 11 yes, 34 no. What proportion of the under-30s exercise weekly?A survey asked 96 people whether they exercise weekly. Under 30: 37 yes, 10 no. Age 30 or over: 26 yes, 23 no. What proportion of the under-30s exercise weekly?
- A survey asked 124 people whether they exercise weekly. Under 30: 21 yes, 50 no. Age 30 or over: 31 yes, 22 no. What proportion of all the people exercise weekly?A survey asked 134 people whether they exercise weekly. Under 30: 52 yes, 12 no. Age 30 or over: 45 yes, 25 no. What proportion of all the people exercise weekly?A survey asked 130 people whether they exercise weekly. Under 30: 22 yes, 32 no. Age 30 or over: 29 yes, 47 no. What proportion of all the people exercise weekly?A survey asked 167 people whether they exercise weekly. Under 30: 25 yes, 45 no. Age 30 or over: 46 yes, 51 no. What proportion of all the people exercise weekly?A survey asked 145 people whether they exercise weekly. Under 30: 60 yes, 28 no. Age 30 or over: 29 yes, 28 no. What proportion of all the people exercise weekly?A survey asked 113 people whether they exercise weekly. Under 30: 23 yes, 48 no. Age 30 or over: 13 yes, 29 no. What proportion of all the people exercise weekly?A survey asked 110 people whether they exercise weekly. Under 30: 35 yes, 14 no. Age 30 or over: 38 yes, 23 no. What proportion of all the people exercise weekly?A survey asked 182 people whether they exercise weekly. Under 30: 58 yes, 47 no. Age 30 or over: 44 yes, 33 no. What proportion of all the people exercise weekly?
- A survey asked 140 people whether they exercise weekly. Under 30: 47 yes, 17 no. Age 30 or over: 37 yes, 39 no. What proportion of all the people are under 30 and exercise weekly?A survey asked 135 people whether they exercise weekly. Under 30: 44 yes, 25 no. Age 30 or over: 10 yes, 56 no. What proportion of all the people are under 30 and exercise weekly?A survey asked 113 people whether they exercise weekly. Under 30: 35 yes, 28 no. Age 30 or over: 11 yes, 39 no. What proportion of all the people are under 30 and exercise weekly?A survey asked 126 people whether they exercise weekly. Under 30: 57 yes, 22 no. Age 30 or over: 13 yes, 34 no. What proportion of all the people are under 30 and exercise weekly?A survey asked 121 people whether they exercise weekly. Under 30: 39 yes, 19 no. Age 30 or over: 40 yes, 23 no. What proportion of all the people are under 30 and exercise weekly?A survey asked 131 people whether they exercise weekly. Under 30: 41 yes, 28 no. Age 30 or over: 39 yes, 23 no. What proportion of all the people are under 30 and exercise weekly?A survey asked 160 people whether they exercise weekly. Under 30: 24 yes, 35 no. Age 30 or over: 49 yes, 52 no. What proportion of all the people are under 30 and exercise weekly?A survey asked 144 people whether they exercise weekly. Under 30: 49 yes, 46 no. Age 30 or over: 10 yes, 39 no. What proportion of all the people are under 30 and exercise weekly?
- Of 40 drivers who texted, 30 had a near-miss; of 40 who did not text, 10 had one. Is there an association between texting and near-misses in these data?
- Yes: 75% of texters vs 25% of non-texters had a near-miss
- No: both groups have 40 drivers
- Yes, and it proves texting causes near-misses
Of 44 drivers who texted, 33 had a near-miss; of 44 who did not text, 11 had one. Is there an association between texting and near-misses in these data?- Yes: 75% of texters vs 25% of non-texters had a near-miss
- No: both groups have 44 drivers
- Yes, and it proves texting causes near-misses
Of 20 drivers who texted, 15 had a near-miss; of 20 who did not text, 5 had one. Is there an association between texting and near-misses in these data?- Yes: 75% of texters vs 25% of non-texters had a near-miss
- No: both groups have 20 drivers
- Yes, and it proves texting causes near-misses
Of 32 drivers who texted, 24 had a near-miss; of 32 who did not text, 8 had one. Is there an association between texting and near-misses in these data?- Yes: 75% of texters vs 25% of non-texters had a near-miss
- No: both groups have 32 drivers
- Yes, and it proves texting causes near-misses
Of 60 drivers who texted, 45 had a near-miss; of 60 who did not text, 15 had one. Is there an association between texting and near-misses in these data?- Yes: 75% of texters vs 25% of non-texters had a near-miss
- No: both groups have 60 drivers
- Yes, and it proves texting causes near-misses
Of 28 drivers who texted, 21 had a near-miss; of 28 who did not text, 7 had one. Is there an association between texting and near-misses in these data?- Yes: 75% of texters vs 25% of non-texters had a near-miss
- No: both groups have 28 drivers
- Yes, and it proves texting causes near-misses
Of 64 drivers who texted, 48 had a near-miss; of 64 who did not text, 16 had one. Is there an association between texting and near-misses in these data?- Yes: 75% of texters vs 25% of non-texters had a near-miss
- No: both groups have 64 drivers
- Yes, and it proves texting causes near-misses
Of 56 drivers who texted, 42 had a near-miss; of 56 who did not text, 14 had one. Is there an association between texting and near-misses in these data?- Yes: 75% of texters vs 25% of non-texters had a near-miss
- No: both groups have 56 drivers
- Yes, and it proves texting causes near-misses
- In a school, 50 of 125 girls and 100 of 250 boys walk to school. What does this suggest?
- No association: 40% of each group walks
- Boys are more likely to walk: 100 > 50
- Girls are more likely to walk
In a school, 18 of 45 girls and 36 of 90 boys walk to school. What does this suggest?- No association: 40% of each group walks
- Boys are more likely to walk: 36 > 18
- Girls are more likely to walk
In a school, 52 of 130 girls and 104 of 260 boys walk to school. What does this suggest?- No association: 40% of each group walks
- Boys are more likely to walk: 104 > 52
- Girls are more likely to walk
In a school, 48 of 120 girls and 96 of 240 boys walk to school. What does this suggest?- No association: 40% of each group walks
- Boys are more likely to walk: 96 > 48
- Girls are more likely to walk
In a school, 12 of 30 girls and 24 of 60 boys walk to school. What does this suggest?- No association: 40% of each group walks
- Boys are more likely to walk: 24 > 12
- Girls are more likely to walk
In a school, 24 of 60 girls and 48 of 120 boys walk to school. What does this suggest?- No association: 40% of each group walks
- Boys are more likely to walk: 48 > 24
- Girls are more likely to walk
In a school, 42 of 105 girls and 84 of 210 boys walk to school. What does this suggest?- No association: 40% of each group walks
- Boys are more likely to walk: 84 > 42
- Girls are more likely to walk
In a school, 34 of 85 girls and 68 of 170 boys walk to school. What does this suggest?- No association: 40% of each group walks
- Boys are more likely to walk: 68 > 34
- Girls are more likely to walk
- A survey asked 135 people whether they exercise weekly. Under 30: 44 yes, 40 no. Age 30 or over: 18 yes, 33 no. Find the proportion of under-30s who exercise minus the proportion of those 30 or over who exercise.A survey asked 163 people whether they exercise weekly. Under 30: 45 yes, 37 no. Age 30 or over: 48 yes, 33 no. Find the proportion of under-30s who exercise minus the proportion of those 30 or over who exercise.A survey asked 112 people whether they exercise weekly. Under 30: 28 yes, 48 no. Age 30 or over: 13 yes, 23 no. Find the proportion of under-30s who exercise minus the proportion of those 30 or over who exercise.A survey asked 167 people whether they exercise weekly. Under 30: 53 yes, 42 no. Age 30 or over: 13 yes, 59 no. Find the proportion of under-30s who exercise minus the proportion of those 30 or over who exercise.A survey asked 175 people whether they exercise weekly. Under 30: 55 yes, 30 no. Age 30 or over: 39 yes, 51 no. Find the proportion of under-30s who exercise minus the proportion of those 30 or over who exercise.A survey asked 139 people whether they exercise weekly. Under 30: 39 yes, 30 no. Age 30 or over: 40 yes, 30 no. Find the proportion of under-30s who exercise minus the proportion of those 30 or over who exercise.A survey asked 135 people whether they exercise weekly. Under 30: 30 yes, 26 no. Age 30 or over: 49 yes, 30 no. Find the proportion of under-30s who exercise minus the proportion of those 30 or over who exercise.A survey asked 154 people whether they exercise weekly. Under 30: 54 yes, 28 no. Age 30 or over: 13 yes, 59 no. Find the proportion of under-30s who exercise minus the proportion of those 30 or over who exercise.
- A scatterplot of car age against resale value has . How would you describe the relationship?
- Strong, negative, linear: older cars tend to be worth less
- Weak, because r is negative
- Each extra year causes a fixed loss of value
A scatterplot of car age against resale value has . How would you describe the relationship?- Strong, negative, linear: older cars tend to be worth less
- Weak, because r is negative
- Each extra year causes a fixed loss of value
A scatterplot of car age against resale value has . How would you describe the relationship?- Strong, negative, linear: older cars tend to be worth less
- Weak, because r is negative
- Each extra year causes a fixed loss of value
A scatterplot of car age against resale value has . How would you describe the relationship?- Strong, negative, linear: older cars tend to be worth less
- Weak, because r is negative
- Each extra year causes a fixed loss of value
A scatterplot of car age against resale value has . How would you describe the relationship?- Strong, negative, linear: older cars tend to be worth less
- Weak, because r is negative
- Each extra year causes a fixed loss of value
A scatterplot of car age against resale value has . How would you describe the relationship?- Strong, negative, linear: older cars tend to be worth less
- Weak, because r is negative
- Each extra year causes a fixed loss of value
A scatterplot of car age against resale value has . How would you describe the relationship?- Strong, negative, linear: older cars tend to be worth less
- Weak, because r is negative
- Each extra year causes a fixed loss of value
A scatterplot of car age against resale value has . How would you describe the relationship?- Strong, negative, linear: older cars tend to be worth less
- Weak, because r is negative
- Each extra year causes a fixed loss of value
- Heights (cm) and weights (kg) of students have . Heights are converted to inches. What is the new correlation?
- Still : changing units does not change
- Smaller, since inches are bigger units
- It cannot be known without the data
Heights (cm) and weights (kg) of students have . Heights are converted to inches. What is the new correlation?- Still : changing units does not change
- Smaller, since inches are bigger units
- It cannot be known without the data
Heights (cm) and weights (kg) of students have . Heights are converted to inches. What is the new correlation?- Still : changing units does not change
- Smaller, since inches are bigger units
- It cannot be known without the data
Heights (cm) and weights (kg) of students have . Heights are converted to inches. What is the new correlation?- Still : changing units does not change
- Smaller, since inches are bigger units
- It cannot be known without the data
Heights (cm) and weights (kg) of students have . Heights are converted to inches. What is the new correlation?- Still : changing units does not change
- Smaller, since inches are bigger units
- It cannot be known without the data
Heights (cm) and weights (kg) of students have . Heights are converted to inches. What is the new correlation?- Still : changing units does not change
- Smaller, since inches are bigger units
- It cannot be known without the data
Heights (cm) and weights (kg) of students have . Heights are converted to inches. What is the new correlation?- Still : changing units does not change
- Smaller, since inches are bigger units
- It cannot be known without the data
Heights (cm) and weights (kg) of students have . Heights are converted to inches. What is the new correlation?- Still : changing units does not change
- Smaller, since inches are bigger units
- It cannot be known without the data
- , and . Find the slope of the least-squares regression line of on ., and . Find the slope of the least-squares regression line of on ., and . Find the slope of the least-squares regression line of on ., and . Find the slope of the least-squares regression line of on ., and . Find the slope of the least-squares regression line of on ., and . Find the slope of the least-squares regression line of on ., and . Find the slope of the least-squares regression line of on ., and . Find the slope of the least-squares regression line of on .
- The least-squares line has slope , and , . Find its intercept.The least-squares line has slope , and , . Find its intercept.The least-squares line has slope , and , . Find its intercept.The least-squares line has slope , and , . Find its intercept.The least-squares line has slope , and , . Find its intercept.The least-squares line has slope , and , . Find its intercept.The least-squares line has slope , and , . Find its intercept.The least-squares line has slope , and , . Find its intercept.
- The regression line is . Predict for .The regression line is . Predict for .The regression line is . Predict for .The regression line is . Predict for .The regression line is . Predict for .The regression line is . Predict for .The regression line is . Predict for .The regression line is . Predict for .
- . A data point is . Find its residual.. A data point is . Find its residual.. A data point is . Find its residual.. A data point is . Find its residual.. A data point is . Find its residual.. A data point is . Find its residual.. A data point is . Find its residual.. A data point is . Find its residual.
- The residual plot of a linear model fitted to 56 points shows a clear U-shaped curve. What does that tell you?
- A straight line is not a good model: the relationship is curved
- The model is good, because residuals are both positive and negative
- There is one outlier
The residual plot of a linear model fitted to 80 points shows a clear U-shaped curve. What does that tell you?- A straight line is not a good model: the relationship is curved
- The model is good, because residuals are both positive and negative
- There is one outlier
The residual plot of a linear model fitted to 67 points shows a clear U-shaped curve. What does that tell you?- A straight line is not a good model: the relationship is curved
- The model is good, because residuals are both positive and negative
- There is one outlier
The residual plot of a linear model fitted to 84 points shows a clear U-shaped curve. What does that tell you?- A straight line is not a good model: the relationship is curved
- The model is good, because residuals are both positive and negative
- There is one outlier
The residual plot of a linear model fitted to 27 points shows a clear U-shaped curve. What does that tell you?- A straight line is not a good model: the relationship is curved
- The model is good, because residuals are both positive and negative
- There is one outlier
The residual plot of a linear model fitted to 64 points shows a clear U-shaped curve. What does that tell you?- A straight line is not a good model: the relationship is curved
- The model is good, because residuals are both positive and negative
- There is one outlier
The residual plot of a linear model fitted to 25 points shows a clear U-shaped curve. What does that tell you?- A straight line is not a good model: the relationship is curved
- The model is good, because residuals are both positive and negative
- There is one outlier
The residual plot of a linear model fitted to 58 points shows a clear U-shaped curve. What does that tell you?- A straight line is not a good model: the relationship is curved
- The model is good, because residuals are both positive and negative
- There is one outlier
- A point has residual . Where is it relative to the regression line?
- 8 units above the line: the model underpredicts it
- 8 units below the line
- On the line
A point has residual . Where is it relative to the regression line?- 9 units above the line: the model underpredicts it
- 9 units below the line
- On the line
A point has residual . Where is it relative to the regression line?- 4 units above the line: the model underpredicts it
- 4 units below the line
- On the line
A point has residual . Where is it relative to the regression line?- 7 units above the line: the model underpredicts it
- 7 units below the line
- On the line
A point has residual . Where is it relative to the regression line?- 1 units above the line: the model underpredicts it
- 1 units below the line
- On the line
A point has residual . Where is it relative to the regression line?- 6 units above the line: the model underpredicts it
- 6 units below the line
- On the line
A point has residual . Where is it relative to the regression line?- 2 units above the line: the model underpredicts it
- 2 units below the line
- On the line
A point has residual . Where is it relative to the regression line?- 3 units above the line: the model underpredicts it
- 3 units below the line
- On the line
- For trees, (feet, years). What does mean?
- For each extra year of age, the predicted height increases by 8 feet
- Every tree grows exactly 8 feet each year
- A tree of age 0 is 8 feet tall
For trees, (feet, years). What does mean?- For each extra year of age, the predicted height increases by 5 feet
- Every tree grows exactly 5 feet each year
- A tree of age 0 is 5 feet tall
For trees, (feet, years). What does mean?- For each extra year of age, the predicted height increases by 7 feet
- Every tree grows exactly 7 feet each year
- A tree of age 0 is 7 feet tall
For trees, (feet, years). What does mean?- For each extra year of age, the predicted height increases by 2 feet
- Every tree grows exactly 2 feet each year
- A tree of age 0 is 2 feet tall
For trees, (feet, years). What does mean?- For each extra year of age, the predicted height increases by 9 feet
- Every tree grows exactly 9 feet each year
- A tree of age 0 is 9 feet tall
For trees, (feet, years). What does mean?- For each extra year of age, the predicted height increases by 3 feet
- Every tree grows exactly 3 feet each year
- A tree of age 0 is 3 feet tall
For trees, (feet, years). What does mean?- For each extra year of age, the predicted height increases by 4 feet
- Every tree grows exactly 4 feet each year
- A tree of age 0 is 4 feet tall
For trees, (feet, years). What does mean?- For each extra year of age, the predicted height increases by 6 feet
- Every tree grows exactly 6 feet each year
- A tree of age 0 is 6 feet tall
- A regression has . What fraction of the variation in is explained by the linear model ()?A regression has . What fraction of the variation in is explained by the linear model ()?A regression has . What fraction of the variation in is explained by the linear model ()?A regression has . What fraction of the variation in is explained by the linear model ()?A regression has . What fraction of the variation in is explained by the linear model ()?A regression has . What fraction of the variation in is explained by the linear model ()?A regression has . What fraction of the variation in is explained by the linear model ()?A regression has . What fraction of the variation in is explained by the linear model ()?
- A model for children aged 2 to 6 predicts height from age. Is it reasonable to use it for a 40-year-old?
- No: 40 is far outside the ages used to fit the model (extrapolation)
- Yes, if r is close to 1
- Yes: a line can be extended forever
A model for children aged 2 to 12 predicts height from age. Is it reasonable to use it for a 40-year-old?- No: 40 is far outside the ages used to fit the model (extrapolation)
- Yes, if r is close to 1
- Yes: a line can be extended forever
A model for children aged 2 to 13 predicts height from age. Is it reasonable to use it for a 40-year-old?- No: 40 is far outside the ages used to fit the model (extrapolation)
- Yes, if r is close to 1
- Yes: a line can be extended forever
A model for children aged 2 to 9 predicts height from age. Is it reasonable to use it for a 40-year-old?- No: 40 is far outside the ages used to fit the model (extrapolation)
- Yes, if r is close to 1
- Yes: a line can be extended forever
A model for children aged 2 to 15 predicts height from age. Is it reasonable to use it for a 40-year-old?- No: 40 is far outside the ages used to fit the model (extrapolation)
- Yes, if r is close to 1
- Yes: a line can be extended forever
A model for children aged 2 to 8 predicts height from age. Is it reasonable to use it for a 40-year-old?- No: 40 is far outside the ages used to fit the model (extrapolation)
- Yes, if r is close to 1
- Yes: a line can be extended forever
A model for children aged 2 to 5 predicts height from age. Is it reasonable to use it for a 40-year-old?- No: 40 is far outside the ages used to fit the model (extrapolation)
- Yes, if r is close to 1
- Yes: a line can be extended forever
A model for children aged 2 to 10 predicts height from age. Is it reasonable to use it for a 40-year-old?- No: 40 is far outside the ages used to fit the model (extrapolation)
- Yes, if r is close to 1
- Yes: a line can be extended forever
Answers
- Yes: 75% of texters vs 25% of non-texters had a near-missYes: 75% of texters vs 25% of non-texters had a near-missYes: 75% of texters vs 25% of non-texters had a near-missYes: 75% of texters vs 25% of non-texters had a near-missYes: 75% of texters vs 25% of non-texters had a near-missYes: 75% of texters vs 25% of non-texters had a near-missYes: 75% of texters vs 25% of non-texters had a near-missYes: 75% of texters vs 25% of non-texters had a near-miss
- No association: 40% of each group walksNo association: 40% of each group walksNo association: 40% of each group walksNo association: 40% of each group walksNo association: 40% of each group walksNo association: 40% of each group walksNo association: 40% of each group walksNo association: 40% of each group walks
- Strong, negative, linear: older cars tend to be worth lessStrong, negative, linear: older cars tend to be worth lessStrong, negative, linear: older cars tend to be worth lessStrong, negative, linear: older cars tend to be worth lessStrong, negative, linear: older cars tend to be worth lessStrong, negative, linear: older cars tend to be worth lessStrong, negative, linear: older cars tend to be worth lessStrong, negative, linear: older cars tend to be worth less
- Still : changing units does not change Still : changing units does not change Still : changing units does not change Still : changing units does not change Still : changing units does not change Still : changing units does not change Still : changing units does not change Still : changing units does not change
- A straight line is not a good model: the relationship is curvedA straight line is not a good model: the relationship is curvedA straight line is not a good model: the relationship is curvedA straight line is not a good model: the relationship is curvedA straight line is not a good model: the relationship is curvedA straight line is not a good model: the relationship is curvedA straight line is not a good model: the relationship is curvedA straight line is not a good model: the relationship is curved
- 8 units above the line: the model underpredicts it9 units above the line: the model underpredicts it4 units above the line: the model underpredicts it7 units above the line: the model underpredicts it1 units above the line: the model underpredicts it6 units above the line: the model underpredicts it2 units above the line: the model underpredicts it3 units above the line: the model underpredicts it
- For each extra year of age, the predicted height increases by 8 feetFor each extra year of age, the predicted height increases by 5 feetFor each extra year of age, the predicted height increases by 7 feetFor each extra year of age, the predicted height increases by 2 feetFor each extra year of age, the predicted height increases by 9 feetFor each extra year of age, the predicted height increases by 3 feetFor each extra year of age, the predicted height increases by 4 feetFor each extra year of age, the predicted height increases by 6 feet
- No: 40 is far outside the ages used to fit the model (extrapolation)No: 40 is far outside the ages used to fit the model (extrapolation)No: 40 is far outside the ages used to fit the model (extrapolation)No: 40 is far outside the ages used to fit the model (extrapolation)No: 40 is far outside the ages used to fit the model (extrapolation)No: 40 is far outside the ages used to fit the model (extrapolation)No: 40 is far outside the ages used to fit the model (extrapolation)No: 40 is far outside the ages used to fit the model (extrapolation)