Unit 1 · 20–30% of the exam Beta

Unit 1 practice test: Exploring One-Variable Data and Collecting Data

12 exam-style questions from the unit, free, with an explanation for every option. Most have four answer choices, as on the real exam, and a few ask you to type a value, an interval or the setup; sets share one data set, plot or table.

Covers: Introducing Statistics: What Can We Learn from Data?; Variables; Tabular Representation and Summary Statistics for One Categorical Variable; Graphical Representations for One Categorical Variable; Graphical Representations for One Quantitative Variable; Descriptions for One Quantitative Variable Distributions; Summary Statistics for One Quantitative Variable; Graphical Representations of Summary Statistics for One Quantitative Variable; Comparisons of the Distributions for One Quantitative Variable; The Investigative Question Revisited and Data Collection; Random Sampling; Potential Problems with Sampling; Experimental Design.

Table

Final exam scores

The five-number summary of the final exam scores of 120 students (invented data).
Five-number summary of 120 exam scores
MinQ1MedianQ3Max
4163727998

1. Would a boxplot of these scores show any outliers?

  1. Yes: the score of 41 is far below the median of 72
  2. Yes: the score of 98 is far above the third quartile of 79
  3. No: the fences are 39 and 103, and every score is between them
  4. It is impossible to decide without the mean and standard deviation
Show the answer

IQR=79−63=16\text{IQR} = 79 - 63 = 16; fences at 63−1.5(16)=3963 - 1.5(16) = 39 and 79+1.5(16)=10379 + 1.5(16) = 103. The min and max are inside, so the whiskers reach 41 and 98.

  • Yes: the score of 41 is far below the median of 72: Far below the median is not enough; 41 is above the lower fence of 39.
  • Yes: the score of 98 is far above the third quartile of 79: 98 is below the upper fence of 103, so it is not an outlier.
  • Correct: No: the fences are 39 and 103, and every score is between them: Right: IQR=16\text{IQR} = 16, so the fences are 63−24=3963 - 24 = 39 and 79+24=10379 + 24 = 103. The minimum 41 and maximum 98 are inside.
  • It is impossible to decide without the mean and standard deviation: The 1.5×IQR1.5 \times \text{IQR} rule needs only Q1Q_1 and Q3Q_3, and the extremes.

2. About how many of the 120 students scored between 63 and 79?

  1. About 30
  2. About 90
  3. About 60
  4. About 16
Show the answer

The box spans the middle 50% of the data: about 0.5×120=600.5 \times 120 = 60 students.

  • About 30: A quarter lies in each whisker section; the box holds two quarters.
  • About 90: About three quarters scored 79 or less; between 63 and 79 is the middle half.
  • Correct: About 60: Right: the box, from Q1Q_1 to Q3Q_3, holds the middle half of the data: about half of 120.
  • About 16: 16 points is the width of the box, not a count of students.

3. A student scored 85. What can you say about this score?

  1. It is in the top quarter of the scores
  2. It is an outlier
  3. It is near the median, since it is near the middle of 41 and 98
  4. It is in the middle half of the scores, inside the box
Show the answer

85 lies between Q3=79Q_3 = 79 and the maximum 98, the top quarter of the scores.

  • Correct: It is in the top quarter of the scores: Right: 85 is above Q3=79Q_3 = 79, so it is higher than about 75% of the scores.
  • It is an outlier: Values above Q3Q_3 are ordinary parts of the data; 85 is well inside the upper fence of 103.
  • It is near the median, since it is near the middle of 41 and 98: The median is 72. The middle of the min and max is not the median.
  • It is in the middle half of the scores, inside the box: The box ends at 79; 85 is beyond it.

4. Which statement compares the spread of the lower and upper quarters of the scores?

  1. The top quarter has more students than the lowest quarter
  2. The two quarters are equally spread, as each holds a quarter of the scores
  3. The top quarter is more spread out, since it reaches the highest score
  4. The lowest quarter (41 to 63) is more spread out than the top quarter (79 to 98)
Show the answer

Each quarter holds the same number of values; a wider section means those values are more spread out. Here 63 − 41 = 22 and 98 − 79 = 19.

  • The top quarter has more students than the lowest quarter: Each quarter holds about 30 students; the quarters differ in width, not in count.
  • The two quarters are equally spread, as each holds a quarter of the scores: Equal counts do not mean equal widths: 22 points against 19.
  • The top quarter is more spread out, since it reaches the highest score: Reaching the maximum is not the same as being wide: 79 to 98 is 19 points.
  • Correct: The lowest quarter (41 to 63) is more spread out than the top quarter (79 to 98): Right: 22 points against 19 points, so the lowest quarter of scores is more spread out.

Graph

Heights of 30 athletes

A sports camp measured the heights of the 30 athletes in two of its groups, in centimeters (invented data).
1501601701801902002100246cm

5. What is the shape of the distribution of heights?

  1. Skewed right
  2. Uniform
  3. Bimodal
  4. Unimodal
Show the answer

Two peaks with a gap between them make the distribution bimodal.

  • Skewed right: A long tail would be a few large values trailing off; here there is a whole second group.
  • Uniform: A uniform shape has bars of about equal height everywhere; this histogram has an empty stretch in the middle.
  • Correct: Bimodal: Right: there are two separate peaks, one near 155 cm and one near 190 cm.
  • Unimodal: The two sides match, but there are two peaks and almost no one near 175.

6. What is the most likely explanation for the shape of this distribution?

  1. The athletes come from two sports with very different typical heights
  2. Some athletes were measured in inches instead of centimeters
  3. The heights were rounded to the nearest 5 centimeters
  4. Tall athletes are more likely to be chosen for the camp
Show the answer

Two clusters usually point to two kinds of individuals in one data set. Here that is two sports.

  • Correct: The athletes come from two sports with very different typical heights: Right: a bimodal distribution often signals that two groups have been mixed together, such as gymnasts and basketball players.
  • Some athletes were measured in inches instead of centimeters: Heights in inches would be near 60 to 80, far below the values here.
  • The heights were rounded to the nearest 5 centimeters: Rounding would change bars a little; it would not create two groups 30 cm apart.
  • Tall athletes are more likely to be chosen for the camp: That would push the data up, not split it into two separate groups.

7. Which unusual feature does the histogram show?

  1. An outlier at 202 centimeters, the tallest athlete in the camp
  2. An outlier at 148 centimeters, the shortest athlete in the camp
  3. A uniform stretch
  4. A gap: no athlete is between 165 and 180 centimeters
Show the answer

The empty bins between about 165 and 180 cm are a gap between two clusters.

  • An outlier at 202 centimeters, the tallest athlete in the camp: 202 is close to the other tall athletes, inside the upper cluster.
  • An outlier at 148 centimeters, the shortest athlete in the camp: 148 sits with the lower cluster of heights.
  • A uniform stretch: The stretch from 165 to 180 is empty, so the heights are far from uniform.
  • Correct: A gap: no athlete is between 165 and 180 centimeters: Right: the empty bins between the two clusters form a gap.

8. A coach says, "A typical athlete at this camp is about 175 cm tall." Why is this a poor summary?

  1. 175 centimeters is too tall to be a typical height for an athlete
  2. Hardly anyone is near 175; the heights form two groups
  3. A center is not defined for heights measured in centimeters
  4. It should be in inches
Show the answer

In a bimodal distribution a single center can fall in a gap where there are no values. Describe each cluster separately.

  • 175 centimeters is too tall to be a typical height for an athlete: The problem is not the size of 175 but that no athlete is near it.
  • Correct: Hardly anyone is near 175; the heights form two groups: Right: a single center hides the two groups. It is better to describe each group on its own.
  • A center is not defined for heights measured in centimeters: Centers can be given in any unit; this one just falls in the gap.
  • It should be in inches: The unit does not matter; a center in the gap misleads in any unit.

9. A quality team weighs 50 bags of rice taken from a day’s production of 8,000 bags. What is the population?

  1. The 50 bags weighed
  2. The 8,000 bags made that day
  3. The weight that is printed on each bag of rice
  4. The machine on the line that fills the bags
Show the answer

The population is every bag the question is about: all 8,000 made that day.

  • The 50 bags weighed: These are the sample.
  • Correct: The 8,000 bags made that day: Right: the team wants to know about the whole day’s production.
  • The weight that is printed on each bag of rice: That is a label, not a group of bags.
  • The machine on the line that fills the bags: The machine makes the bags; the question is about the bags themselves.

10. Which variable is quantitative?

  1. Jersey number printed on the back of each player’s shirt
  2. Height in centimeters
  3. Favorite sport
  4. Phone area code, such as 612 or 858, for each player
Show the answer

A quantitative variable takes numerical values that are amounts. Height is one; jersey numbers and area codes are labels.

  • Jersey number printed on the back of each player’s shirt: Jersey numbers are labels; the average jersey number tells you nothing.
  • Correct: Height in centimeters: Right: height is a measured amount, and averaging heights makes sense.
  • Favorite sport: Favorite sport puts people into groups, so it is categorical.
  • Phone area code, such as 612 or 858, for each player: Area codes are labels for places, so the variable is categorical.

11. In a sample of 220 shoppers, the relative frequency of paying with cash is 0.15. How many shoppers paid with cash?

  1. 15
  2. 33
  3. 1,467
  4. 187
Show the answer

Count = relative frequency × total = 0.15×220=330.15 \times 220 = 33.

  • 15: 0.15 is a part of 1, not a count. Multiply by 220.
  • Correct: 33: Right: 0.15×220=330.15 \times 220 = 33.
  • 1,467: A count from a relative frequency is a multiplication, not a division.
  • 187: That is 0.85 × 220, the shoppers who used other methods.

12. A survey asked 300 students, "Which school clubs do you belong to? Check every one." Why is a pie chart a poor choice for the results?

  1. Pie charts are allowed for counts and not for relative frequencies
  2. There are too few clubs at the school to fill a pie chart
  3. Students can be in several clubs, so the parts do not make one whole
  4. Pie charts are used for quantitative variables such as height
Show the answer

A pie chart needs categories that do not overlap and together cover everyone. "Check every one" breaks that.

  • Pie charts are allowed for counts and not for relative frequencies: A pie chart shows parts of a whole, which are relative frequencies.
  • There are too few clubs at the school to fill a pie chart: A pie chart can have few or many slices.
  • Correct: Students can be in several clubs, so the parts do not make one whole: Right: the relative frequencies can add to more than 1, so there is no single pie to cut.
  • Pie charts are used for quantitative variables such as height: Pie charts are for categorical variables; the issue here is overlap.

Keep going

Practice has every question in the unit, with feedback after each one; this unit's lessons are free. Other units: Unit 1 · Unit 2 · Unit 3 · Unit 4 · Unit 5.