A Level Math Revision

IAL S1 data and summary statistics: exam questions with mark schemes

Types of data (qualitative/quantitative, discrete/continuous); mean, median, mode, quartiles and percentiles; variance and standard deviation; coding; outliers. (Sampling methods are not in IAL S1.)

Each question carries its marks, and its mark scheme sits under it: M marks for method, A marks for accuracy, B marks for a correct result on its own. Try the question on paper first, then open the solution and mark yourself the way an examiner would.

Edexcel IAL S1 Statistics 1 · 10 questions · 53 marks · Measures of Central Tendency, Descriptive statistics, Descriptive Statistics, Presentation of Data

Question 1

4 marks · warm-up

Class A consists of 15 students who scored a mean of 70 on a test. Class B consists of 25 students who scored a mean of 78 on the same test. Calculate the exact overall mean score for all 40 students combined.

Show solution

M1 for finding the total sum of scores for Class A: 15×70=1050.
M1 for finding the total sum of scores for Class B: 25×78=1950.
M1 for setting up the combined mean calculation: 1050+195015+25.
A1 for evaluating to the final exact answer: 300040=75.

Answer: 75

Question 2

5 marks · warm-up

A dataset contains 5 numbers: x,y,4,6,8. The mean of the dataset is 5 and the variance is 4. Given that x<y, find the exact values of x and y.

Show solution

M1 for using the mean to form an equation: x+y+185=5⟹x+y=7.
M1 for using the variance formula ∑x2n−μ2=Var: x2+y2+16+36+645−25=4.
M1 for simplifying the variance equation: x2+y2+1165=29⟹x2+y2=145−116=29.
M1 for solving the simultaneous equations by substitution (e.g. y=7−x⟹x2+(7−x)2=29) or using (x+y)2=x2+y2+2xy⟹49=29+2xy⟹xy=10.
A1 for finding the two numbers whose sum is 7 and product is 10: 2 and 5. Since x<y, x=2 and y=5.

Answer: x=2,y=5

Question 3

5 marks · standard

A dataset consists of n completely identical values, x.

  1. Write down the interquartile range (IQR) of this dataset.
  2. A new, single data value y is added to the dataset, where y≠x. Assuming n is very large, prove algebraically why the value y will always be classified as an outlier, regardless of how close y is to x.
Show solution
  1. A1 for stating the IQR is 0 (since Q3=x and Q1=x, x−x=0).
  2. M1 for determining the standard outlier boundaries: Q1−1.5×IQR and Q3+1.5×IQR.
    M1 for substituting Q1=x,Q3=x, and IQR=0 to get the interval [x,x].
    B1 for stating that any value must strictly fall within the interval [x,x] to not be an outlier, meaning it must be exactly x.
    B1 for concluding that since y≠x, y falls outside the boundaries and is therefore mathematically classified as an outlier, regardless of its proximity to x. *

Answer: IQR =0; both outlier limits equal x, so any y≠x is an outlier

Question 4

5 marks · standard


The annual salaries, in thousands of pounds, for six employees at a small startup are: 20, 22, 25, 28, 30, 120

  1. Calculate the mean salary.

  2. Find the median salary.

  3. State which average (mean or median) is the best measure of central tendency for this data set, and give a reason for your choice.

Show solution
  1. Mean =20+22+25+28+30+1206=2456 M1 =40.8 (3 s.f.) A1

  2. Median =25+282=26.5 M1 A1

  3. Median: it is not affected by the extreme value 120, whereas the mean is pulled upwards by it B1

Answer: Mean =40.8 (thousand pounds); median =26.5; the median, since the value 120 is an outlier that distorts the mean

Question 5

5 marks · standard

A dataset representing the time taken for 40 students to complete a puzzle has a lower quartile of 12 minutes and an upper quartile of 28 minutes.

  1. Calculate the Interquartile Range (IQR).
  2. Calculate the lower and upper boundaries for outliers.
  3. One student completed the puzzle in 50 minutes. State, with a reason, whether this time is considered an outlier.
Show solution
  1. IQR=28−12=16 A1
  2. Lower boundary =Q1−1.5×IQR=12−1.5(16)=12−24=−12 M1
    Upper boundary =Q3+1.5×IQR=28+24=52 A1
  3. Since 50<52, it does not exceed the upper boundary. M1
    It is not an outlier. A1

Answer: 50 < 52

Question 6

5 marks · standard

The weights of packages shipped by a postal service are summarised in a box and whisker plot. The lower quartile is Q1=15 kg and the upper quartile is Q3=45 kg.

  1. Calculate the interquartile range (IQR).
  2. Determine the upper boundary for outliers in this dataset.
  3. A heavy package weighs 95 kg. Determine mathematically whether this package is considered an outlier.
Show solution
  1. IQR=45−15=30. A1
  2. Upper boundary =Q3+1.5×IQR=45+1.5(30) M1
    =45+45=90 kg. A1
  3. Since 95>90, the package weight exceeds the upper boundary. M1
    Yes, it is considered an outlier. A1

Answer: IQR =30 kg; upper boundary 90 kg; 95>90, so it is an outlier

Question 7

4 marks · harder


The distances travelled by 60 commuters to work are summarised in the frequency table below.

Distance (d km) Frequency Cumulative Frequency
0≤d<10 4
10≤d<20 11
20≤d<30 25
30≤d<40 16
40≤d<50 4
  1. Copy and complete the cumulative frequency column in the table.

  2. State the class interval that contains the median distance.

  3. Find an estimate for the mean distance travelled by the commuters.

Show solution
  1. Cumulative frequencies: 4,15,40,56,60 B1

  2. Median is the 30th value, which lies in 20≤d<30 B1

  3. ∑fx=4(5)+11(15)+25(25)+16(35)+4(45)=1550 M1

  4. Mean =155060=25.8 km (3 s.f.) A1

Answer: Cumulative frequencies 4,15,40,56,60; median class 20≤d<30; mean ≈25.8 km

Question 8

5 marks · harder


A dataset has a mean of 15 and a standard deviation of 3. A new dataset is formed by taking every value in the original dataset, multiplying it by 2, and then adding 4.

  1. Find the mean of the new dataset.

  2. Find the standard deviation of the new dataset.

  3. Find the variance of the new dataset.

  4. A single new data value, which is exactly equal to the original mean (15), is added to the original dataset. State whether the standard deviation of the dataset will increase, decrease, or remain the same. Give a reason for your answer.

Show solution
  1. New mean =2(15)+4=34 B1

  2. New s.d. =2×3=6 (adding 4 does not change spread) B1

  3. New variance =62=36 B1

  4. Adding a value equal to the mean leaves ∑(x−x¯)2 unchanged but increases n M1, so the standard deviation decreases A1

Answer: Mean =34; s.d. =6; variance =36; the standard deviation decreases

Question 9

6 marks · harder

A dataset consists of five discrete integers: −2, 1, a, b, and 7. The mode of the dataset is 1 and the mean is 3.

  1. Deduce the exact values of a and b, assuming a≤b.
  2. Calculate the exact variance of the dataset.
Show solution
  1. M1 for deducing that since the mode is 1, at least one of the unknown variables must be 1. Let a=1.
    M1 for using the mean formula: −2+1+1+b+75=3.
    A1 for solving for b: 7+b5=3⟹7+b=15⟹b=8. Thus a=1,b=8.
  2. M1 for applying the variance formula σ2=∑(x−μ)2n.
    M1 for calculating the squared deviations: (−2−3)2+(1−3)2+(1−3)2+(8−3)2+(7−3)2=25+4+4+25+16=74.
    A1 for calculating the exact variance: 745=14.8.

Answer: 745=14.8

Question 10

9 marks · harder


A dataset of 15 values has a mean of 45 and a standard deviation of 12. During a review of the data, it is discovered that one of the values, 80, was recorded in error and must be removed from the dataset.

  1. Find the new mean of the remaining 14 values.

  2. Calculate ∑x2 for the original dataset of 15 values.

  3. Hence, find the standard deviation of the new dataset with the anomaly removed.

Show solution
  1. Original n=15, μ=45. Original sum ∑x=15×45=675. M1
    Remove anomaly (80): New sum =675−80=595. M1
    New mean =59514=42.5. A1

  2. Using the variance formula: Var(X)=σ2=122=144. M1
    144=∑x215−452⟹144=∑x215−2025. M1
    ∑x215=2169⟹∑x2=32535. A1

  3. Remove anomaly from sum of squares: New ∑x2=32535−802=32535−6400=26135. A1
    New Variance =2613514−(42.5)2=1866.785...−1806.25=60.535... M1
    New SD =60.535...=7.7804...⟹7.78 (3sf). A1

Answer: New mean 42.5; ∑x2=32535; new s.d. 7.78

Notes and worked examples: IAL S1 Data and Summary Statistics. More S1 exam questions: Representation of Data · Probability · Correlation and Regression · Discrete Random Variables · Normal Distribution · Measures of Location and Spread.

Next topic: Representation of Data. Every IAL unit. Real papers to finish on: IAL S1 past papers.