Biostatistics Quiz: Interpreting Boxplots
20 questions · exam conditions
0:00
Interpreting BoxplotsQuestion 1 of 20

A researcher notices that in their boxplot, exactly 25% of the data points lie between the median and Q3, but more than 25% of the points lie between Q1 and the median. What error has most likely occurred?

The sample size is not divisible by 4, causing unequal quartile intervals in the dataset
The quartiles have been incorrectly calculated or the boxplot has been mislabeled incorrectly
The dataset contains tied values that distort the normal quartile calculation process significantly
This is normal behavior for skewed distributions and indicates no computational error
The median has been calculated using the mean instead of the middle value
← Back to quizzes

Biostatistics Quiz

Biostatistics Quiz: Interpreting Boxplots

Practice Interpreting Boxplots in Biostatistics with focused quiz questions that help you check what you know, review explanations, and build confidence with test-style prompts.

What this quiz covers

This quiz focuses on Interpreting Boxplots, giving you a quick way to practice the rules, question types, and explanations that matter most for Biostatistics.

How to use this quiz

Try each quiz question before looking at the correct answer. Use the explanations to review missed ideas, then come back to similar questions until the pattern feels familiar.

All questions

Question 1

A researcher notices that in their boxplot, exactly 25% of the data points lie between the median and Q3, but more than 25% of the points lie between Q1 and the median. What error has most likely occurred?

  1. The sample size is not divisible by 4, causing unequal quartile intervals in the dataset
  2. The quartiles have been incorrectly calculated or the boxplot has been mislabeled incorrectly (correct answer)
  3. The dataset contains tied values that distort the normal quartile calculation process significantly
  4. This is normal behavior for skewed distributions and indicates no computational error
  5. The median has been calculated using the mean instead of the middle value
Explanation: When you encounter boxplot questions, remember that quartiles divide your data into four equal groups by definition. Each quartile interval should contain exactly 25% of the data points, making this a fundamental property you can use to check for errors. The scenario described here violates this basic principle. If exactly 25% of data points lie between the median and Q3, but more than 25% lie between Q1 and the median, then the quartiles cannot be correct. By definition, Q1 marks the 25th percentile, the median marks the 50th percentile, and Q3 marks the 75th percentile. This means each interval (Q1 to median, median to Q3) must contain exactly 25% of the observations. When this doesn't happen, you're looking at incorrectly calculated quartiles or mislabeled boxplot elements, making B correct. Option A is wrong because sample size being indivisible by 4 doesn't change the quartile definition - statistical software uses interpolation methods to handle this routinely. Option C incorrectly suggests tied values distort quartile calculations significantly, but modern statistical methods handle ties appropriately without breaking the fundamental 25% rule. Option D represents a dangerous misconception - while skewed distributions affect the spacing between quartiles, they never change the fact that each quartile interval contains exactly 25% of the data. Study tip: Whenever you see unusual quartile behavior described in exam questions, first ask yourself: "Does this violate the basic 25% rule?" If yes, look for calculation or labeling errors rather than accepting it as normal statistical behavior.

Question 2

A quality control engineer examines a boxplot of product weights where the median is 500g, Q1 is 495g, Q3 is 505g, and there are outliers at 480g and 525g. If the specification limits are 485g to 515g, what percentage of products definitely fall within specifications based on this information?

  1. At least 50% because the interquartile range falls entirely within the specification limits established (correct answer)
  2. At least 75% because both the IQR and the whisker regions likely fall within specifications
  3. Exactly 50% because half the products are above and half are below the median value
  4. Cannot be determined because boxplots don't provide information about specification limit compliance rates
  5. Less than 50% because the outliers at 480g and 525g fall outside the specification limits
Explanation: When analyzing boxplots for quality control, you need to understand what each component tells you about data distribution and use only the definitive information provided. Let's examine what we know for certain: the median (500g) and interquartile range (Q1=495g to Q3=505g) both fall entirely within the specification limits of 485g to 515g. Since the IQR contains the middle 50% of all data points, we can definitively say that at least 50% of products meet specifications. Answer A is correct because it states the minimum percentage we can guarantee based on the boxplot information. The IQR encompasses exactly 50% of the data, and since this entire range falls within specifications, at least 50% of products definitely comply. Answer B overstates what we can conclude. While 75% might be true, we cannot definitively determine this from the boxplot alone, since we don't know the exact distribution of data in the whisker regions relative to the specification limits. Answer C misinterprets what "exactly 50%" means. This answer confuses the median's role (dividing data in half) with specification compliance. We know at least 50% comply, but potentially more do. Answer D is incorrect because boxplots do provide useful specification limit information. While they don't give exact percentages, they can establish minimum compliance rates when quartiles fall within specification ranges. Study tip: In quality control problems, focus on what boxplot components guarantee rather than what they suggest. Use quartile positions to establish minimum compliance rates with confidence.

Question 3

A researcher creates boxplots for test scores from three different classes. Class A shows several low outliers, Class B shows several high outliers, and Class C shows no outliers. If all classes have similar medians and IQRs, which statement about class performance is most justified?

  1. Class C has the most consistent performance because it lacks any outlying scores in the dataset
  2. Class B has the highest overall performance because high outliers indicate exceptional students are present
  3. Class A has the most problematic performance because low outliers indicate struggling students need help
  4. All classes have similar central performance, but Classes A and B have more extreme variation (correct answer)
  5. Class C likely has the smallest sample size, which reduces the probability of observing outliers
Explanation: When interpreting boxplots, you need to distinguish between measures of central tendency (median) and measures of variability. The presence or absence of outliers tells you about the distribution's shape and extreme values, but doesn't necessarily indicate better or worse overall performance. Since all three classes have similar medians and IQRs, their central 50% of students are performing comparably. The median shows where the "typical" student performs, while the IQR captures the spread of the middle half of the class. These are the most robust measures of central performance. The key insight is that outliers represent extreme variation beyond the typical range, not necessarily problems or advantages for the class as a whole. Option A incorrectly assumes that lack of outliers means better consistency overall. While Class C has no extreme scores, the similar IQRs across all classes indicate comparable variation in the main body of students. Option B makes the mistake of equating a few high-performing outliers with superior class performance, ignoring that the bulk of students (represented by the median and IQR) perform similarly across classes. Option C falls into the trap of viewing low outliers as inherently problematic when they simply represent the tail of the distribution. Option D correctly recognizes that central tendency measures (median, IQR) indicate similar typical performance, while outliers in Classes A and B show additional extreme variation in both directions. Remember: outliers affect the range and mean, but boxplot interpretation focuses on the median and quartiles as more reliable indicators of typical performance.

Question 4

A researcher creates a boxplot for patient recovery times (in days) and observes that the right whisker is considerably longer than the left whisker, while the median line is closer to Q1 than to Q3. What can be concluded about the shape of this distribution?

  1. The distribution is approximately symmetric with equal spread above and below the median
  2. The distribution is left-skewed because the median is closer to the lower quartile
  3. The distribution is right-skewed with a longer tail extending toward higher values (correct answer)
  4. The distribution is bimodal because the whiskers are unequal in length
  5. The distribution cannot be determined from boxplot characteristics alone without seeing raw data
Explanation: When interpreting boxplots, you need to understand how the position of key elements reveals the distribution's shape. The whiskers show the spread of data, while the median's position relative to the quartiles indicates where most values cluster. The key insight here is recognizing what each feature tells you about skewness. A longer right whisker indicates more extreme values extending toward higher recovery times. When the median sits closer to Q1 than Q3, it means the middle value is pulled toward the lower end of the data range. These features together create the classic signature of right skewness: most patients recover relatively quickly (clustering at lower values), but some take much longer, creating that extended tail toward higher values. Answer C correctly identifies this right-skewed pattern. The longer right whisker represents the tail extending toward higher recovery times, which defines right skewness. Answer A is wrong because unequal whiskers and an off-center median clearly indicate asymmetry, not symmetry. Answer B falls into a common trap—while the median is closer to Q1, this actually indicates right skewness, not left skewness. The median gets pulled toward the bulk of the data (lower values), while the tail extends right. Answer D incorrectly associates unequal whiskers with bimodality, but whisker length reflects spread and skewness, not the number of peaks in the distribution. Study tip: Remember that skewness is named for the direction of the tail, not where the median sits. Right-skewed = long right tail, even though the median appears shifted left toward the data cluster.

Question 5

A boxplot shows Q1 = 15, median = 22, Q3 = 35, with whiskers extending to 5 and 50, and outliers at 60 and 65. If you were to identify potential outliers using the 1.5×IQR rule, which values would be flagged?

  1. Only 60 and 65, because they are plotted as outliers on the boxplot
  2. Only 65, because it exceeds the upper fence by the greatest margin (correct answer)
  3. Values 5, 60, and 65, because 5 is at the lower boundary and 60, 65 exceed upper boundary
  4. Both 60 and 65, because they both exceed the upper fence of 65
  5. No values would be flagged because all points fall within reasonable ranges for this dataset
Explanation: When analyzing outliers in boxplot data, you need to apply the 1.5×IQR rule independently of what the boxplot visually shows. This rule uses calculated fence values to determine which data points fall outside the expected range. First, calculate the interquartile range: IQR=Q3−Q1=35−15=20IQR = Q3 - Q1 = 35 - 15 = 20. Then find the fence boundaries: Lower fence = Q1−1.5×IQR=15−30=−15Q1 - 1.5 \times IQR = 15 - 30 = -15, and Upper fence = Q3+1.5×IQR=35+30=65Q3 + 1.5 \times IQR = 35 + 30 = 65. Any values below -15 or above 65 are outliers by this rule. Checking each data point: 5 > -15 (not an outlier), 60 < 65 (not an outlier), but 65 = 65 (exactly at the boundary, typically considered an outlier), making only 65 flagged as an outlier. Answer A incorrectly assumes that visual outliers on a boxplot automatically match the 1.5×IQR rule, but boxplots can show outliers based on different criteria. Answer C wrongly flags 5 and 60 - while 5 is at the whisker end, it's well within the lower fence, and 60 doesn't exceed the upper fence. Answer D contains a calculation error, stating the upper fence is 65 when that's correct, but then incorrectly claiming both 60 and 65 exceed it. Remember that the 1.5×IQR rule is a mathematical calculation independent of boxplot appearance. Always calculate the fences yourself rather than relying on visual cues, and pay attention to whether boundary values are included as outliers.

Question 6

In the boxplot shown, the median is 45, Q1 is 30, Q3 is 60, and there are data points at 5, 10, and 95. Which statement about this distribution is most accurate?

  1. The value 95 is an outlier because it exceeds Q3 + 1.5(IQR)
  2. The values 5 and 10 are both outliers because they are below Q1 - 1.5(IQR)
  3. Only the value 5 is an outlier because it is the most extreme low value (correct answer)
  4. All three values (5, 10, and 95) are outliers based on the IQR criterion
  5. The value 10 is not an outlier because it falls within the whisker range
Explanation: To identify outliers, calculate Q1 - 1.5(IQR) and Q3 + 1.5(IQR). IQR = Q3 - Q1 = 60 - 30 = 30. Lower fence: 30 - 1.5(30) = 30 - 45 = -15. Upper fence: 60 + 1.5(30) = 60 + 45 = 105. Values below -15 or above 105 are outliers. Since 5 < -15, it is an outlier. Since 10 > -15, it is not an outlier. Since 95 < 105, it is not an outlier. Therefore, only the value 5 is an outlier.

Question 7

Examining the boxplot displayed below, if a new data point with value 42 were added to this dataset, which boxplot component would be most likely to change?

  1. The position of Q1 would shift substantially because 42 is in the lower half of the data
  2. The median would change significantly since 42 falls between Q1 and the current median
  3. The length of the upper whisker would increase because 42 extends the range
  4. The exact effect depends on the current sample size and how 42 ranks among existing values (correct answer)
  5. No components would change because 42 falls within the existing interquartile range
Explanation: The impact of adding a new data point depends critically on the sample size and where the new value ranks among existing data. For small samples, adding one point can shift quartiles and median significantly. For large samples, the effect may be minimal. The position of 42 relative to existing data points determines which quartiles might shift. Choice A assumes 42 will substantially affect Q1 without knowing sample size. Choice B assumes significant median change without considering sample size. Choice C is wrong because 42 is not at an extreme value that would affect whiskers. Choice E is wrong because values within IQR can still affect quartile positions depending on sample size.

Question 8

Comparing the two boxplots shown for treatment groups, Group X has a smaller IQR than Group Y, but Group X's whiskers extend further in both directions. Which interpretation is most appropriate?

  1. Group X has both lower central variability and higher extreme variability than Group Y (correct answer)
  2. Group X is more variable overall because its total range exceeds that of Group Y
  3. Group Y is more variable overall because its interquartile range is larger than Group X's
  4. The groups have equivalent variability since the smaller IQR in Group X balances the longer whiskers
  5. Group X has more outliers than Group Y, indicating greater measurement error in that group
Explanation: This scenario describes Group X having tighter clustering in the middle 50% of data (smaller IQR) but more extreme values at the tails (longer whiskers). This represents lower central variability but higher extreme variability. Choice B oversimplifies by focusing only on total range. Choice C focuses only on IQR and ignores the whisker information. Choice D incorrectly suggests these effects 'balance out' - they represent different types of variability. Choice E makes an unfounded assumption about outliers and measurement error without information about actual outlier counts.

Question 9

In the boxplot shown, the distance from Q1 to the median is much smaller than the distance from the median to Q3. However, the whiskers appear roughly equal in length. What does this pattern suggest about the data distribution?

  1. The distribution is left-skewed with concentration of values in the upper portion of the range
  2. The distribution is right-skewed with a longer tail extending toward higher values in the dataset
  3. The distribution has moderate right skewness in the central region but symmetric tails beyond the quartiles (correct answer)
  4. The distribution is approximately normal since the whiskers are equal, indicating symmetric tail behavior overall
  5. The pattern indicates bimodality with peaks near Q1 and Q3 in the underlying data distribution
Explanation: The smaller distance from Q1 to median compared to median to Q3 indicates right skewness in the central portion (the box), while equal whisker lengths suggest more symmetric behavior in the tails. This describes moderate skewness that's more pronounced in the central region. Choice A incorrectly identifies this as left skewness. Choice B ignores the symmetric whisker information. Choice D incorrectly concludes normality based only on whiskers while ignoring the asymmetric box. Choice E incorrectly infers bimodality from quartile spacing patterns.

Question 10

In the boxplot shown, the whiskers extend to values that are not the absolute minimum and maximum of the dataset. Which statement best explains this observation?

  1. The boxplot is incorrectly constructed because whiskers must always extend to the extreme values
  2. Some data points beyond the whiskers are classified as outliers using the 1.5×IQR criterion (correct answer)
  3. The whiskers are truncated to improve visual clarity of the central distribution
  4. The dataset contains missing values that prevent whiskers from reaching true extremes
  5. The whiskers extend only to the 10th and 90th percentiles by standard convention
Explanation: In standard boxplot construction, whiskers extend to the farthest points that are within 1.5×IQR from the box edges, not necessarily to the absolute extremes. Points beyond this range are plotted separately as outliers. Choice A is incorrect because this is actually the standard way to construct boxplots. Choice C suggests arbitrary truncation for visual purposes, which is not the systematic rule. Choice D incorrectly relates whisker length to missing data. Choice E describes a different type of boxplot (percentile-based) but this is not the standard 1.5×IQR method.

Question 11

The boxplot shown represents patient blood pressure readings where several values appear as outliers beyond both whiskers. If these outliers represent measurement errors rather than true extreme values, what would be the most appropriate next step?

  1. Remove all outliers automatically and reconstruct the boxplot with the remaining valid data points
  2. Investigate each outlier individually to determine if it represents measurement error or true variation (correct answer)
  3. Apply a data transformation to reduce the impact of extreme values on the distribution
  4. Increase the outlier detection threshold from 1.5×IQR to 3×IQR for more conservative identification
  5. Report the data as-is since boxplots are designed to handle outliers appropriately without modification
Explanation: When outliers might represent measurement errors, each should be investigated individually to determine its validity before any action is taken. Automatic removal or transformation without investigation could eliminate valid extreme values or retain actual errors. Choice A is wrong because automatic removal without investigation is inappropriate. Choice C addresses symptoms rather than the underlying data quality issue. Choice D changes the detection criterion arbitrarily without addressing whether outliers are errors. Choice E ignores the possibility that these are measurement errors that should be corrected.

Question 12

Two boxplots are shown comparing test scores for Group A and Group B. Both groups have identical medians and interquartile ranges, but Group A shows three outliers on the high end while Group B shows no outliers. What is the most appropriate conclusion about these distributions?

  1. Group A has higher overall performance because it contains the highest individual scores
  2. Group B has more consistent performance since it lacks outliers in the dataset
  3. The groups have identical central tendency and spread in the middle 50% of scores (correct answer)
  4. Group A's mean score is necessarily higher than Group B's mean score due to outliers
  5. Group B has lower variability overall because its total range is smaller than Group A's
Explanation: Since both groups have identical medians (same central tendency) and identical IQRs (same spread in middle 50%), this is the only definitive conclusion. Choice A is misleading because outliers don't necessarily indicate better overall performance. Choice B confuses outliers with consistency - the middle 50% have identical spreads. Choice D assumes the outliers pull the mean higher, but we don't know if Group B might have more moderate high values that aren't outliers. Choice E incorrectly equates smaller range with lower overall variability when the core distributions (boxes and whiskers) might be identical.

Question 13

The boxplot shows reaction times where Q1=200ms, median=250ms, Q3=300ms, with whiskers extending to 150ms and 400ms. Based on this information, what is the most reasonable estimate for the mean reaction time?

  1. Exactly 250ms because the distribution appears to be perfectly symmetric around the median
  2. Slightly less than 250ms because the left whisker is shorter than the right whisker
  3. Slightly more than 250ms because the right whisker is longer than the right whisker (correct answer)
  4. Cannot be determined from boxplot information because mean and median can differ substantially
  5. Approximately 225ms based on the average of Q1 and Q3 values shown
Explanation: The left whisker extends 50ms below Q1 (200-150=50), while the right whisker extends 100ms above Q3 (400-300=100). This asymmetry suggests slight right skewness, which typically pulls the mean above the median. Choice A incorrectly assumes perfect symmetry. Choice B reverses the direction of the effect. Choice D is overly conservative - while mean and median can differ, we can make reasonable estimates from boxplot shape. Choice E incorrectly suggests using (Q1+Q3)/2 as an estimate for the mean.

Question 14

In the boxplot shown, the median line is not visible within the box. Given that this represents a valid dataset with no calculation errors, what is the most likely explanation?

  1. The median equals either Q1 or Q3, causing the median line to overlap with a box edge (correct answer)
  2. The dataset has an even number of observations, making median calculation impossible for boxplot construction
  3. The median value falls outside the interquartile range due to extreme skewness in the distribution
  4. The boxplot software has a display error that failed to render the median line properly
  5. The dataset contains too many tied values at the median position to display clearly
Explanation: When the median line is not visible in a boxplot, it typically means the median equals either Q1 or Q3, causing the line to coincide with the edge of the box and become invisible. This can occur with datasets that have many tied values. Choice B is incorrect because median can always be calculated for any dataset size. Choice C is impossible because median must fall between Q1 and Q3 by definition. Choice D assumes a technical error rather than a mathematical explanation. Choice E describes tied values but doesn't explain why the line would be invisible rather than just thick.

Question 15

In the boxplot displayed below, the left whisker is absent (does not extend from Q1). Assuming standard boxplot construction rules, what does this indicate about the data distribution?

  1. The minimum value of the dataset equals the first quartile value exactly (correct answer)
  2. All data points below Q1 have been identified and removed as outliers from the dataset
  3. The dataset is severely right-skewed with no values in the lower tail region
  4. There is insufficient data in the lower 25% to construct a reliable whisker estimate
  5. The minimum value falls exactly at Q1 - 1.5×IQR, creating a whisker of zero length
Explanation: When a whisker is absent, it means the whisker would have zero length - the extreme value in that direction equals the quartile position. Since whiskers extend to the farthest point within 1.5×IQR of the box edge, a missing left whisker means the minimum value equals Q1. Choice B incorrectly suggests outlier removal. Choice C confuses the absence of a whisker with skewness. Choice D incorrectly relates this to sample size adequacy. Choice E describes a different scenario where the minimum happens to fall at the fence boundary.

Question 16

The boxplot displayed below shows patient ages in a clinical study where Q3=65, the median=50, and Q1=35. If the research protocol excludes patients under 30 and over 70, and there are outliers visible at ages 25 and 75, what can be concluded about protocol compliance?

  1. Protocol violations occurred since outliers at 25 and 75 fall outside the acceptable age range (correct answer)
  2. The protocol was followed correctly since outliers are automatically excluded from analysis by definition
  3. At least 75% of patients fall within the protocol age requirements of 30-70 years
  4. The whiskers indicate the actual age range of compliant patients in the study population
  5. Protocol compliance cannot be assessed from boxplot information without knowing the whisker endpoints exactly
Explanation: The outliers at ages 25 and 75 represent actual patients in the dataset who fall outside the protocol requirements of 30-70 years, indicating protocol violations occurred during patient recruitment or data collection. Choice B incorrectly suggests outliers are automatically excluded - they represent real data points that violate the protocol. Choice C focuses on compliant patients but ignores the protocol violations. Choice D incorrectly interprets whisker meaning. Choice E is overly conservative since the outliers clearly show protocol violations regardless of whisker positions.

Question 17

Two boxplots are compared below, where Dataset 1 has a median of 40 and Dataset 2 has a median of 60. Both datasets show identical box heights (IQR = 20) and identical whisker lengths, but Dataset 1 shows three outliers while Dataset 2 shows none. Which statement about the relationship between these datasets is most accurate?

  1. Dataset 2 is simply Dataset 1 shifted upward by 20 units with outliers removed during transformation
  2. Dataset 2 represents a different population since identical variability with different outlier patterns is unlikely
  3. The datasets have identical shapes and spreads but different central locations and outlier characteristics
  4. Dataset 1 has greater overall variability due to the presence of outliers extending the total range
Explanation: C

Question 18

Two variables are displayed in side-by-side boxplots below. Variable A shows Q1=10, median=15, Q3=25, while Variable B shows Q1=40, median=45, Q3=55. Both variables have identical whisker lengths and no outliers. Which comparison is most accurate?

  1. Variable B has greater absolute variability because its values are higher than Variable A's values
  2. The variables have identical variability since their IQRs and whisker lengths are the same
  3. Variable A has greater relative variability when considering the coefficient of variation for each distribution
  4. Variable B is more normally distributed because its values are more tightly clustered around the median
Explanation: B

Question 19

A clinical researcher compares boxplots of hemoglobin levels between two treatment groups. Group A shows Q1 = 11.5 g/dL, median = 13.0 g/dL, Q3 = 14.2 g/dL, while Group B shows Q1 = 12.8 g/dL, median = 13.1 g/dL, Q3 = 13.7 g/dL. Both groups have the same range (9.5 to 16.8 g/dL). Which statement about the variability and distribution characteristics is most accurate?

  1. Group A has greater variability than Group B because its interquartile range is larger (correct answer)
  2. Group B has greater variability than Group A because its median is closer to Q3 than Q1
  3. Both groups have equal variability since they have identical ranges and similar medians
  4. Group A shows less variability than Group B because its median is more centered between quartiles
Explanation: To compare variability, we calculate the IQR for each group. Group A: IQR = 14.2 - 11.5 = 2.7 g/dL. Group B: IQR = 13.7 - 12.8 = 0.9 g/dL. Since Group A has a larger IQR (2.7 vs 0.9), it has greater variability in the central 50% of the data. Choice B is incorrect because the position of median relative to quartiles indicates skewness, not overall variability. Choice C is wrong because equal ranges don't imply equal variability when the quartile spreads differ significantly. Choice D is incorrect because median centering relates to symmetry, not variability magnitude.

Question 20

A researcher analyzing patient age distributions notices that one boxplot has whiskers of unequal length, with the right whisker being notably shorter than the left whisker, while both extend to the maximum allowable distance (1.5 IQR) from their respective quartiles. What does this pattern most likely indicate about the underlying data structure?

  1. The data contains outliers only on the right side, causing the right whisker to appear shorter
  2. The data is right-skewed with a long tail extending toward higher values beyond the whisker (correct answer)
  3. The data is left-skewed with the bulk of observations concentrated toward higher values
  4. The data contains more observations between Q3 and the maximum than between the minimum and Q1
Explanation: When whiskers extend to their maximum allowable length (Q1 - 1.5 IQR and Q3 + 1.5 IQR) but appear unequal, with the right whisker being shorter, this indicates that the rightmost non-outlier data point is closer to Q3 than the leftmost non-outlier is to Q1. This pattern, combined with unequal whisker lengths, typically indicates right-skewness where there are outliers extending beyond the right whisker (creating a long right tail), while the left side has data points that extend closer to the maximum allowable distance. Choice A is partially correct about right-side outliers but doesn't explain the whisker length difference. Choice C describes left-skewness, which would show the opposite pattern. Choice D describes density differences but misses the key implication about skewness and outliers.