Statistics: The Spread of Data

The Importance of Spread in Statistics

  • Center vs Spread: While finding the center (mean or median) indicates a typical value of a dataset, understanding the spread is crucial for a complete picture.

Understanding Median and Its Role in Spread

  • Median: The median is defined as the middle number in a dataset.
  • Dividing Data:
    • For an odd number of data points, the median divides the dataset into two halves without being part of either half.
    • For an even number of data points, the dataset is split into two equal halves around the median.
  • Example of Odd and Even Data Points:
    • Odd: {1, 1, 2, 3, 3, 4, 5} → Median = 3
    • Even: {1, 1, 2, 3, 4, 4, 7, 8} → Median = (3 + 4)/2 = 3.5 (not part of halves)

Percentiles and Quartiles

  • Percentile: A measure indicating the value below which a given percentage falls (e.g., 80th percentile means better than 80% of the data).
  • Quartiles:
    • First Quartile (Q1): 25th percentile.
    • Median (Q2): 50th percentile.
    • Third Quartile (Q3): 75th percentile.
  • These quartiles create the Five Number Summary:
    • Minimum, Q1, Median (Q2), Q3, and Maximum.
  • Proportions of the dataset are defined by the quartiles (each segment contains about 25% of the data).

Example Calculation for Five Number Summary

Data Set #1: {11, 11, 11, 11, 11, 12, 12, 12, 13, 14, 14, 14, 15, 16, 17, 17, 17, 19, 19, 20}
  • Minimum = 11, Maximum = 20
  • Median calculation:
    • There are 20 values → Median = (10th + 11th)/2 = (14 + 14)/2 = 14
  • Lower Half for Q1:
    • {11, 11, 11, 11, 11, 12, 12, 12, 13, 14} → Median of lower half = (11 + 12)/2 = 11.5
  • Upper Half for Q3:
    • {14, 14, 15, 16, 17, 17, 17, 19, 19, 20} → Median of upper half = 17
  • Five Number Summary: Min = 11, Q1 = 11.5, Median = 14, Q3 = 17, Max = 20
Data Set #2: {10, 10, 10, 10, 12, 14, 14, 15, 16, 16, 17, 17, 17, 18, 19, 19, 19, 19, 20, 20, 20}
  • Minimum = 10, Maximum = 20
  • Median calculation:
    • There are 21 values → Median = 17 (11th value)
  • Lower Half for Q1:
    • {10, 10, 10, 10, 12, 14, 14, 15, 16, 16} → Median = (12 + 14)/2 = 13
  • Upper Half for Q3:
    • {17, 17, 18, 19, 19, 19, 19, 20, 20, 20} → Median = 19
  • Five Number Summary: Min = 10, Q1 = 13, Median = 17, Q3 = 19, Max = 20

Visual Representation: Box Plot

  • Box Plot Structure:
    • Whiskers: extend from the minimum to Q1 and from Q3 to the maximum.
    • The box itself spans from Q1 to Q3 and contains the median inside it.
Example of a Box Plot from Data Set #2:
  • Draw a number line from 0 to 20.
  • Plot:
    • Min (10) to Q1 (13), box from Q1-17 with median at 17 and Q3 (19) to Max (20).

Benefits of Box Plots

  • Quick Visual Approximation: Easier to interpret than raw values.
    • 50% of data falls within the box (Q1 to Q3).
    • Useful for understanding data spread and comparing multiple datasets.
  • Inter-Quartile Range (IQR):
    • Calculated as: IQR = Q3 - Q1.
    • Denotes the spread of the middle 50% of data.
  • Higher IQR: indicates more spread out data.

Comparing Datasets

  • Use box plots to compare datasets visually.
  • Example Comparison:
    • Data Set #1 IQR: 5.5, Data Set #2 IQR: 6.
    • This implies Data Set #2 data points are more spread out than those in Data Set #1.