Step-by-step worked examples and graded practice questions on representing data — identifying outliers and cleaning data, drawing and comparing box plots, cumulative frequency diagrams, estimating the median, quartiles and percentiles of grouped data by linear interpolation, and histograms with unequal class widths. Written to the Edexcel Statistics Year 1 specification and equally suitable for AQA and OCR A.
📚 Statistics Year 1 (AS)✅ 15 Practice Questions🔍 8 Worked Examples⚠️ Common Mistakes
Struggling with statistical diagrams?
Alamin diagnoses exactly which skills are missing and builds a structured plan to fix them — backed by AI-powered practice between sessions.
This topic builds on the GCSE skills in box plots, cumulative frequency and histograms, and uses the quartiles and interquartile range from Measures of Location & Spread. At A-Level the emphasis moves from drawing diagrams to interpreting them: deciding which values are outliers, estimating statistics from grouped data, and comparing distributions in context.
Four skills make up this topic:
Outliers and cleaning data — applying an outlier rule, and deciding whether an extreme value is an error or a genuine reading
Box plots — drawing them with outliers marked separately, and using them to compare two distributions
Cumulative frequency and interpolation — estimating the median, quartiles and percentiles of grouped data, from a graph or by calculation
Histograms — using frequency density so that the area of each bar represents frequency, including unequal class widths
Outliers and cleaning data
An outlier is a value that is very different from the rest of the data. The question will tell you which rule to use. The most common rule is that a value is an outlier if it lies more than \(1.5 \times \text{IQR}\) beyond the nearer quartile, that is below \(Q_1 - 1.5 \times \text{IQR}\) or above \(Q_3 + 1.5 \times \text{IQR}\). Another common rule uses the mean and standard deviation: for example, a value more than 2 standard deviations from the mean, outside \(\bar{x} \pm 2\sigma\).
Cleaning data means dealing with values that should not be analysed as they stand: obvious errors (a human height of 17.2 m), missing values, and outliers. An outlier that is a recording error should be corrected or removed. An outlier that is a genuine, if unusual, value should normally be kept, because removing it would misrepresent the population.
📋 Exam board note
Conventions differ between exam boards and textbooks
Outlier rules vary: \(1.5 \times \text{IQR}\) beyond the quartiles is common, but a question may use a different multiple of the IQR, or a rule based on the mean and standard deviation. Always use the rule the question states. For grouped, continuous data, this page estimates the median and quartiles at positions \(\dfrac{n}{2}\), \(\dfrac{n}{4}\) and \(\dfrac{3n}{4}\) with no rounding; some textbooks use \(\dfrac{n+1}{2}\) and similar positions instead, which give slightly different estimates. Use the method your question or exam board expects.
Worked Example 1
The times, in minutes, taken by 15 students to complete a puzzle are: 4, 12, 14, 15, 17, 18, 19, 20, 21, 22, 24, 25, 27, 30, 44. An outlier is a value more than \(1.5 \times \text{IQR}\) below \(Q_1\) or above \(Q_3\). Identify any outliers.
1
The data is discrete and sorted, so use the position rule from Measures of Location & Spread. \(Q_1\): \(\dfrac{15}{4} = 3.75\), not whole, so take the 4th value, \(Q_1 = 15\). Median: \(\dfrac{15}{2} = 7.5\), so the 8th value, \(20\). \(Q_3\): \(\dfrac{3(15)}{4} = 11.25\), so the 12th value, \(Q_3 = 25\)
\(4 > 0\), so 4 is not an outlier. \(44 > 40\), so 44 is an outlier
Answer44 is the only outlier
Box plots
A box plot shows five values on a scale: the box runs from \(Q_1\) to \(Q_3\) with a line at the median, and the whiskers extend to the lowest and highest values that are not outliers. Each outlier is marked separately with a cross. Box plots are drawn on a scale, so they can be compared directly when two are drawn on the same axis.
Worked Example 2
Draw a box plot for the puzzle times in Worked Example 1.
1
The box: \(Q_1 = 15\), median \(=20\), \(Q_3 = 25\)
2
The lower whisker goes to the lowest value, 4, which is not an outlier
3
44 is an outlier, so the upper whisker stops at the highest value that is not an outlier, 30, and 44 is marked with a cross
AnswerWhiskers at 4 and 30, box from 15 to 25 with the median at 20, and a cross at 44
Box plot of the puzzle times from Worked Example 2. The upper whisker ends at 30, the highest value that is not an outlier, and the outlier 44 is marked with a cross.
Comparing distributions
When you compare two box plots, make one comment on location (compare the medians) and one on spread (compare the interquartile ranges), and put each comment in the context of the question. The median and IQR are not affected by outliers, which is why they are used to compare data that contains extreme values.
Worked Example 3
The box plots below show the reaction times, in milliseconds, of two groups of students. Group A: lowest 210, \(Q_1 = 240\), median 255, \(Q_3 = 270\), highest 300. Group B: lowest 190, \(Q_1 = 215\), median 228, \(Q_3 = 250\), highest non-outlier 290, with one outlier at 340. Compare the reaction times of the two groups.
1
Location: Group B's median (228 ms) is lower than Group A's (255 ms), so Group B generally reacted faster
2
Spread: Group A's IQR is \(270 - 240 = 30\) ms and Group B's is \(250 - 215 = 35\) ms, so Group A's times were slightly more consistent
3
Group B's outlier (340 ms) does not affect its median or IQR, so the comparison above still holds
AnswerGroup B reacted faster on average (lower median); Group A's times were slightly more consistent (smaller IQR)
Box plots of the reaction times in Worked Example 3 on one shared scale. Group B's median is lower, and its outlier at 340 ms is marked with a cross.
Cumulative frequency diagrams
For grouped data, the cumulative frequency is the running total of the frequencies. To draw a cumulative frequency diagram, plot each cumulative frequency against the upper class boundary of its class, start at the lower boundary of the first class with a cumulative frequency of 0, and join the points with a smooth curve. Joining the points with straight lines is also accepted. Any value read from the graph is an estimate: on this page, a reading is accepted if it is within \(\pm 1\) minute of the value given on the time axis, or within \(\pm 2\) of the value given on the cumulative frequency axis. A reading from the curve can differ slightly from the value calculated by linear interpolation (see the next section); both are accepted.
Worked Example 4
The table shows the times, in minutes, taken by 80 runners to complete a fun run.(a) Draw a cumulative frequency diagram.(b) Estimate how many runners took more than 50 minutes.
Time, \(t\) (min)
\(0 \le t < 10\)
\(10 \le t < 20\)
\(20 \le t < 30\)
\(30 \le t < 40\)
\(40 \le t < 60\)
Frequency
8
14
24
20
14
1
Cumulative frequencies: 8, 22, 46, 66, 80
2
Plot \((0, 0)\), \((10, 8)\), \((20, 22)\), \((30, 46)\), \((40, 66)\) and \((60, 80)\), using the upper class boundaries, and join them
3
(b) Read up from \(t = 50\) to the curve and across: the cumulative frequency is approximately 74 (accept 72 to 76), so about 74 runners took less than 50 minutes
4
\(80 - 74 = 6\) (accept 4 to 8)
Answer(a) See the diagram below(b) Approximately 6 runners took more than 50 minutes (accept 4 to 8)
Cumulative frequency curve for the fun-run times in Worked Example 4. Reading up from 50 minutes gives a cumulative frequency of approximately 74.
Estimating the median and quartiles by interpolation
For grouped, continuous data you can also estimate the median, quartiles and percentiles by calculation. For \(n\) values, the median is at position \(\dfrac{n}{2}\), \(Q_1\) at \(\dfrac{n}{4}\) and \(Q_3\) at \(\dfrac{3n}{4}\) (the \(k\)th percentile is at \(\dfrac{kn}{100}\)), with no rounding. Find the class that contains the position, then assume the values in that class are spread evenly across it (linear interpolation):
\[\text{estimate} = L + \dfrac{\text{position} - F}{f} \times w\]
where \(L\) is the lower class boundary, \(F\) is the cumulative frequency before the class, \(f\) is the frequency of the class and \(w\) is the class width. This is the grouped-data method that the Measures of Location & Spread page refers to; its discrete-data rule (average two values, or round up) applies to individual data values, not to grouped data.
Worked Example 5
Using the fun-run data from Worked Example 4 (\(n = 80\)), estimate the median and the interquartile range by linear interpolation.
1
\(Q_1\) position \(=\dfrac{80}{4} = 20\), in the class \(10 \le t < 20\) (\(F = 8\), \(f = 14\)): \(Q_1 = 10 + \dfrac{20 - 8}{14} \times 10 = 18.57\) (2 d.p.)
2
Median position \(=\dfrac{80}{2} = 40\), in the class \(20 \le t < 30\) (\(F = 22\), \(f = 24\)): median \(= 20 + \dfrac{40 - 22}{24} \times 10 = 27.5\)
3
\(Q_3\) position \(=\dfrac{3(80)}{4} = 60\), in the class \(30 \le t < 40\) (\(F = 46\), \(f = 20\)): \(Q_3 = 30 + \dfrac{60 - 46}{20} \times 10 = 37\)
The same cumulative frequency curve with readings at cumulative frequencies 20, 40 and 60: \(Q_1 \approx 18.8\), median \(\approx 27.5\) and \(Q_3 \approx 36.3\) minutes (accept \(\pm 1\) minute). These graph readings are estimates. Linear interpolation (Worked Example 5) is the calculation method and gives 18.57, 27.5 and 37; small differences between the curve and the calculation are expected, and both are accepted.
Histograms
A histogram represents grouped continuous data with bars that touch. When the classes have different widths, the height of each bar is the frequency density:
This makes the area of each bar proportional to the frequency it represents, which is the key idea in every histogram question. If the vertical axis shows frequency density, the area of a bar is exactly its frequency; if the question gives a different scale, work out how many items one unit of area represents. A frequency polygon joins the midpoints of the tops of the bars with straight lines.
Worked Example 6
The lengths, \(L\) cm, of 60 fish are recorded. Draw a histogram of the data.
Draw touching bars from 10 to 20, 20 to 25, 25 to 30, 30 to 40 and 40 to 60, with these heights, and label the vertical axis "Frequency density"
AnswerBar heights 1.2, 3, 3.6, 1 and 0.25
Histogram of the fish lengths in Worked Example 6. The 25–30 cm bar is the tallest, but the area of each bar, not its height, gives the frequency: the 10–20 cm bar has area \(10 \times 1.2 = 12\).
Worked Example 7
Using the histogram in Worked Example 6, estimate the number of fish with lengths between 22 cm and 35 cm.
1
22 to 25 is part of the \(20 \le L < 25\) class: \(3 \times 3 = 9\) (width 3, frequency density 3)
2
25 to 30 is the whole \(25 \le L < 30\) class: 18
3
30 to 35 is half of the \(30 \le L < 40\) class: \(5 \times 1 = 5\)
4
\(9 + 18 + 5 = 32\). This is an estimate, because it assumes the values in each class are spread evenly
AnswerAbout 32 fish
Worked Example 8
On a histogram, the bar for one class is 2 cm wide and 6 cm tall, and represents 24 people. Another bar on the same histogram is 3 cm wide and 4.5 cm tall. How many people does it represent?
1
The first bar has area \(2 \times 6 = 12\) cm², so \(1\) cm² represents \(\dfrac{24}{12} = 2\) people
2
The second bar has area \(3 \times 4.5 = 13.5\) cm²
3
\(13.5 \times 2 = 27\)
Answer27 people
Choosing a representation
Each diagram suits a different purpose. A box plot shows the median, quartiles and outliers, and is the clearest way to compare two distributions side by side. A cumulative frequency diagram lets you estimate the median, quartiles and percentiles of grouped data, and how many values lie above or below a given value. A histogram shows the shape of a grouped continuous distribution, including where the data is most concentrated, and copes with unequal class widths. Statistics found from grouped data are always estimates, because the individual values are not known.
Exam tips
💡 Tip 1
Show your outlier limits
Write out \(Q_1 - 1.5 \times \text{IQR}\) and \(Q_3 + 1.5 \times \text{IQR}\) (or whichever rule the question gives) before deciding whether a value is an outlier. The limits earn method marks even if a later step slips.
💡 Tip 2
Plot cumulative frequency at upper class boundaries
The cumulative frequency up to the end of a class belongs at the end of that class, never at its midpoint. Start the graph at the lower boundary of the first class with a cumulative frequency of 0.
💡 Tip 3
Check that an interpolated value lies inside its class
A median found in the class \(20 \le t < 30\) must be between 20 and 30. If it is not, you have used the wrong cumulative frequency \(F\) or class width \(w\).
💡 Tip 4
In a histogram, think area, not height
Frequency is the area of a bar. To find a frequency from a histogram, multiply the frequency density by the class width, and check the total area against the total frequency if it is given.
💡 Tip 5
Compare in context, with numbers
A full comparison of two distributions mentions a measure of location and a measure of spread, quotes the values, and explains what they mean in the question's context, for example "Group B reacted faster on average".
Common mistakes
Common Mistake 1
Using frequency as the bar height
With unequal class widths, plotting frequency instead of frequency density makes wide classes look far too important. The height must be \(\dfrac{\text{frequency}}{\text{class width}}\).
Common Mistake 2
Plotting cumulative frequency at class midpoints
Cumulative frequency counts every value up to the end of a class, so it must be plotted at the upper class boundary. Plotting at midpoints shifts the whole graph and every reading from it.
Common Mistake 3
Drawing a whisker out to an outlier
The whisker stops at the most extreme value that is not an outlier, and each outlier is marked with its own cross. A whisker that reaches the outlier hides the information the box plot is meant to show.
Common Mistake 4
Rounding the position when interpolating grouped data
The "average two values or round up" rule is for individual, discrete data values. For grouped data, use the position \(\dfrac{n}{4}\), \(\dfrac{n}{2}\) or \(\dfrac{3n}{4}\) exactly as it is in the interpolation formula.
Common Mistake 5
Removing every outlier automatically
Cleaning data means correcting or removing values that are errors. A genuine extreme value is real data and should normally stay in, even if it is an outlier.
Practice questions
Work through each question before checking the worked solution. Unless a question says otherwise, an outlier is a value more than \(1.5 \times \text{IQR}\) below \(Q_1\) or above \(Q_3\).
Core Skills
Q1A data set has \(Q_1 = 18\) and \(Q_3 = 30\). Which of the values 2, 47 and 50 are outliers?Core Skills
Q2(a) The class \(15 \le x < 20\) has frequency 30. Find its frequency density.(b) A histogram bar of width 10 has frequency density 2.5. Find the frequency it represents.Core Skills
Q3The masses, \(m\) kg, of 50 parcels are grouped in the classes \(0 \le m < 10\), \(10 \le m < 20\), \(20 \le m < 30\), \(30 \le m < 40\) and \(40 \le m < 50\), with frequencies 5, 11, 20, 9 and 5. Find the cumulative frequencies and list the points you would plot for a cumulative frequency diagram.Core Skills
Q4A data set has lowest value 12, \(Q_1 = 20\), median 26, \(Q_3 = 31\) and highest value 40. Find the range and the IQR, and show that there are no outliers.Core Skills
Q5Using the parcel data in Q3, estimate the median mass by linear interpolation.Core Skills
Exam-Style
Q6A data set has mean 42 and standard deviation 6. An outlier is defined as a value more than 2 standard deviations from the mean.(a) Which of the values 28, 31 and 55 are outliers?(b) The value 55 is checked and found to be a genuine measurement. Should it be removed from the data? Explain.Exam-Style
Histogram for Q7 and Q15: the times, in seconds, taken to complete a task.
Q7The histogram above shows the times taken by a group of people to complete a task. The classes are \(0 \le t < 20\), \(20 \le t < 30\), \(30 \le t < 35\), \(35 \le t < 40\) and \(40 \le t < 60\).(a) Find the number of people in the group.(b) Estimate the number of people who took between 26 and 38 seconds.Exam-Style
Q8On a histogram, the bar for the class \(10 \le x < 20\) is 2 cm wide and 5 cm tall, and represents a frequency of 40. The bar for the class \(20 \le x < 25\) is 8 cm tall. Find its width and the frequency it represents.Exam-Style
Q9The heights, \(h\) cm, of 60 students are grouped as \(140 \le h < 150\): 6, \(150 \le h < 155\): 14, \(155 \le h < 160\): 22, \(160 \le h < 170\): 12, \(170 \le h < 180\): 6. Use linear interpolation to estimate \(Q_1\), \(Q_3\) and the interquartile range.Exam-Style
Box plots for Q10: battery life, in hours, for samples from two factories.
Q10The box plots above summarise battery life for two factories. Factory X: lowest 18, \(Q_1 = 24\), median 28, \(Q_3 = 31\), highest 36. Factory Y: lowest 15, \(Q_1 = 20\), median 25, \(Q_3 = 33\), highest 42. Compare the battery life of the two factories, and say which factory's batteries you would choose if you needed a predictable battery life.Exam-Style
A* Challenge
Q11On a histogram, the class \(0 \le x < 5\) has frequency 12 and is drawn as a bar 1.5 cm wide and 3 cm tall. Find the width and the height of the bar for the class \(5 \le x < 15\), which has frequency 18.A* Challenge
Q12Grouped data has the classes \(0 \le x < 10\), \(10 \le x < 20\), \(20 \le x < 40\) and \(40 \le x < 60\), with frequencies 8, 12, \(k\) and 10. The median, estimated by linear interpolation, is 28. Find \(k\).A* Challenge
Q13A data set has \(Q_1 = 40\), but \(Q_3\) is unknown. Its three largest values are 68, 71 and 90. Using the \(1.5 \times \text{IQR}\) rule, 71 is an outlier but 68 is not.(a) Find the range of possible values of \(Q_3\).(b) The smallest value in the data set is 21. Show that 21 must be an outlier.A* Challenge
Q14Use the fun-run data from Worked Example 4 and the quartiles found in Worked Example 5.(a) Using these estimated quartiles, show that, although the individual times are not known, no runner in the table can be an outlier under the \(1.5 \times \text{IQR}\) rule.(b) One more runner, who took longer than 60 minutes, is added to the data. Use linear interpolation to find the new \(Q_1\) and \(Q_3\), and hence find the time this runner must exceed to be an outlier.A* Challenge
Q15For the task times in the Q7 histogram:(a) estimate the median by linear interpolation(b) estimate the mean using class midpoints(c) explain why both answers are estimatesA* Challenge
The lowest value, 12, is above 3.5 and the highest value, 40, is below 47.5, so there are no outliers
Range \(=28\), IQR \(=11\), no outliers
Q5 — Median \(\approx 24.5\) kg
1
Median position \(=\dfrac{50}{2} = 25\), which is in the class \(20 \le m < 30\) (cumulative frequency before it \(F = 16\), \(f = 20\))
2
Median \(= 20 + \dfrac{25 - 16}{20} \times 10 = 20 + 4.5 = 24.5\) kg
Median \(\approx 24.5\) kg
Exam-Style (Q6–Q10)
Q6 — (a) 28 and 55; (b) No, keep it
1
(a) Limits: \(42 - 2(6) = 30\) and \(42 + 2(6) = 54\). \(28 < 30\) and \(55 > 54\), so 28 and 55 are outliers; 31 is not
2
(b) No. Only values that are errors should be removed or corrected when cleaning data. 55 is a genuine value, so removing it would misrepresent the data
(a) 28 and 55 are outliers; 31 is not(b) No, 55 is a genuine value, so it should be kept
Q7 — (a) 82 people; (b) About 39
1
(a) Frequency \(=\) frequency density \(\times\) class width: \(20 \times 0.5 = 10\), \(10 \times 2.5 = 25\), \(5 \times 4 = 20\), \(5 \times 3 = 15\), \(20 \times 0.6 = 12\). Total \(= 82\)
2
(b) 26 to 30: \(4 \times 2.5 = 10\); 30 to 35: \(20\); 35 to 38: \(3 \times 3 = 9\)
3
\(10 + 20 + 9 = 39\) people (an estimate, assuming the values in each class are spread evenly)
(a) 82 people(b) About 39 people
Q8 — Width 1 cm, frequency 32
1
A class width of 10 is drawn 2 cm wide, so a class width of 5 is drawn 1 cm wide
2
The first bar has area \(2 \times 5 = 10\) cm² for a frequency of 40, so 1 cm² represents \(\dfrac{40}{10} = 4\)
3
The second bar has area \(1 \times 8 = 8\) cm², so its frequency is \(8 \times 4 = 32\)
\(Q_1\) position \(=\dfrac{60}{4} = 15\), in \(150 \le h < 155\): \(Q_1 = 150 + \dfrac{15 - 6}{14} \times 5 = 153.21\) (2 d.p.)
3
\(Q_3\) position \(=\dfrac{3(60)}{4} = 45\), in \(160 \le h < 170\): \(Q_3 = 160 + \dfrac{45 - 42}{12} \times 10 = 162.5\)
4
\(\text{IQR} = 162.5 - 153.214\ldots = 9.29\) cm (2 d.p.)
\(Q_1 \approx 153.21\), \(Q_3 = 162.5\), IQR \(\approx 9.29\) cm
Q10 — X longer on average and more consistent; choose X
1
Location: Factory X's median (28 hours) is higher than Factory Y's (25 hours), so X's batteries generally last longer
2
Spread: X's IQR is \(31 - 24 = 7\) hours and Y's is \(33 - 20 = 13\) hours (ranges 18 and 27 hours), so X's battery life is much more consistent
3
Choose Factory X: its smaller IQR means its battery life is more predictable, and it also lasts longer on average
Factory X: its batteries last longer on average and are more consistent
A* Challenge (Q11–Q15)
Q11 — Width 3 cm, height 2.25 cm
1
A class width of 5 is drawn 1.5 cm wide, so a class width of 10 is drawn 3 cm wide
2
The first bar has area \(1.5 \times 3 = 4.5\) cm² for a frequency of 12, so each unit of frequency takes \(\dfrac{4.5}{12} = 0.375\) cm²
3
The second bar needs area \(18 \times 0.375 = 6.75\) cm²
4
Height \(=\dfrac{6.75}{3} = 2.25\) cm
Width 3 cm, height 2.25 cm
Q12 — \(k = 50\)
1
\(n = 30 + k\). The median, 28, is in the class \(20 \le x < 40\), with \(F = 20\) and width 20, at position \(\dfrac{30 + k}{2}\)
2
Write the position as \(p = \dfrac{30 + k}{2}\), so \(p - 20 = \dfrac{k - 10}{2}\). Then \(20 + \dfrac{p - 20}{k} \times 20 = 28\) gives \(\dfrac{p - 20}{k} = \dfrac{8}{20} = 0.4\)
3
\(\dfrac{k - 10}{2} = 0.4k\), so \(k - 10 = 0.8k\), giving \(0.2k = 10\) and \(k = 50\)
4
Check: \(n = 80\), median position 40, \(20 + \dfrac{40 - 20}{50} \times 20 = 28\). So \(k = 50\)
\(k = 50\)
Q13 — (a) \(51.2 \le Q_3 < 52.4\); (b) 21 is an outlier
1
(a) The upper limit is \(Q_3 + 1.5(Q_3 - 40) = 2.5Q_3 - 60\)
2
An outlier lies more than \(1.5 \times \text{IQR}\) above \(Q_3\). 68 is not an outlier, so \(68 \le 2.5Q_3 - 60\). 71 is an outlier, so \(71 > 2.5Q_3 - 60\)
3
\(128 \le 2.5Q_3 < 131\), so \(51.2 \le Q_3 < 52.4\). (90 is then also an outlier, since the upper limit is less than 71)
4
(b) The lower limit is \(40 - 1.5(Q_3 - 40) = 100 - 1.5Q_3\). Because \(Q_3 < 52.4\), the lower limit \(> 100 - 1.5(52.4) = 21.4\)
5
Whatever the value of \(Q_3\), the lower limit is greater than 21.4, and \(21 < 21.4\), so 21 must be an outlier
(a) \(51.2 \le Q_3 < 52.4\)(b) 21 is an outlier, whatever the value of \(Q_3\)
Q14 — (a) No outliers, using the estimated quartiles; (b) \(t > 65.3125\) minutes
1
(a) From Worked Example 5, \(Q_1 = 18.571\ldots\), \(Q_3 = 37\) and \(\text{IQR} = 18.428\ldots\), so \(1.5 \times \text{IQR} = 27.642\ldots\)
Every time in the table lies in \(0 \le t < 60\). No time can be below \(-9.07\), and every time is below \(60 < 64.64\), so, using these estimated quartiles, no recorded time can be an outlier
4
(b) Now \(n = 81\). The new time is above 60, so the cumulative frequencies of the existing classes do not change. \(Q_1\) position \(=\dfrac{81}{4} = 20.25\), in \(10 \le t < 20\): \(Q_1 = 10 + \dfrac{20.25 - 8}{14} \times 10 = 18.75\)
5
\(Q_3\) position \(=\dfrac{3(81)}{4} = 60.75\), in \(30 \le t < 40\): \(Q_3 = 30 + \dfrac{60.75 - 46}{20} \times 10 = 37.375\)
6
\(\text{IQR} = 37.375 - 18.75 = 18.625\), so the upper limit is \(37.375 + 1.5(18.625) = 37.375 + 27.9375 = 65.3125\)
(a) No recorded time can be an outlier (limits \(-9.07\) and \(64.64\), using the estimated quartiles)(b) The new runner is an outlier if their time is more than \(65.3125\) minutes (about 65.3 minutes)
Q15 — (a) Median \(=31.5\) s; (b) Mean \(\approx 30.95\) s; (c) Individual values unknown
1
(a) From Q7, the frequencies are 10, 25, 20, 15, 12 (\(n = 82\)), with cumulative frequencies 10, 35, 55, 70, 82. Median position \(=\dfrac{82}{2} = 41\), in \(30 \le t < 35\): \(30 + \dfrac{41 - 35}{20} \times 5 = 31.5\)
(c) The individual times are not known. The median assumes the values are spread evenly within their class, and the mean assumes every value equals its class midpoint
(a) Median \(=31.5\) s(b) Mean \(\approx 30.95\) s(c) The individual times are not known, so both values are estimates
Summary
An outlier is usually a value below \(Q_1 - 1.5 \times \text{IQR}\) or above \(Q_3 + 1.5 \times \text{IQR}\), but always use the rule the question gives. Remove or correct errors; keep genuine extreme values.
Box plot whiskers end at the most extreme values that are not outliers; each outlier is marked with a cross. Compare box plots using the median (location) and IQR (spread), in context.
Cumulative frequency is plotted at upper class boundaries, starting from 0 at the lower boundary of the first class, and joined with a smooth curve (straight lines also accepted); readings are estimates.
For grouped data, estimate the median, quartiles and percentiles with \(L + \dfrac{\text{position} - F}{f} \times w\), using the positions \(\dfrac{n}{2}\), \(\dfrac{n}{4}\), \(\dfrac{3n}{4}\) and \(\dfrac{kn}{100}\) without rounding.
In a histogram, frequency density \(=\dfrac{\text{frequency}}{\text{class width}}\), and the area of each bar is proportional to its frequency.
If histograms, cumulative frequency or interpolation are still causing problems, Alamin's diagnostic approach identifies exactly which skills are missing and builds a targeted plan to address them — with AI-powered practice between sessions.