All flashcards topics

Outliers and cleaning dataEdexcel A-Level Maths: Flashcards

What these 13 flashcards ask

  • Give the IQR rule for outliers.
  • Give the standard deviation rule for outliers.
  • Q1=14, Q3=22. Find the outlier limits using 1.5\timesIQR.
  • Mean 805, SD 6. Outlier limits at 3 SD?
  • How are outliers shown on a box plot?
  • Which measures are least affected by an outlier?
  • Which measures are most affected by an outlier?
  • An outlier is a recording error and the true value is known. What do you do?
  • An outlier is a genuine value. What do you do?
  • Two ways to deal with missing data?
  • Disadvantage of omitting missing cases?
  • Mean of 200 values is 805; one value of 842 is removed. New mean?
  • Why can an outlier make the mean \pm3SD rule less reliable?

Exam questions on Outliers and cleaning data

  1. The numbers of text messages sent in one day by 40 students have minimum 3, lower quartile 14, upper quartile 22 and maximum 50. A value is an outlier if it is more than 1.5×1.5\timesIQR above the upper quartile or below the lower quartile.
    The maximum value of 50 was recorded in error and should have been 15. State what should be done with this value and find the effect on the mean.2 marks
  2. The masses of 200 loaves from a bakery have mean 805 g and standard deviation 6 g. A loaf is classed as an outlier if its mass is more than 3 standard deviations from the mean.
    A loaf of mass 842 g is an outlier because the scale was faulty. Find the mean mass of the other 199 loaves.2 marks
  3. A student measures the heights, in cm, of 8 plants. The values entered in a spreadsheet are 12.5, 13.1, 12.8, 128, 13.4, 12.9 and 13.0, and the cell for the eighth plant was left blank.
    Identify the likely error in the data, explain how you would deal with it, and calculate the mean height of the plants measured, after dealing with it.3 marks
See the full worksheet

Written by the Exaim team, led by Shaun Daswani (Head of Upper Secondary, Improve ME Institute; MSc Financial Mathematics, Imperial College London; BSc, UCL) and Jason Daswani (operational lead, Improve ME Institute; LSE).