Comparing Data Sets
When Emma's class compared test scores between two periods, they discovered Period 3 averaged 82 points while Period 5 averaged 79 points. However, Period 3's scores ranged from 65 to 95, while Period 5's ranged from 75 to 83, revealing that higher averages don't always tell the complete story about data consistency.
Why it matters
Comparing data sets helps students analyze real-world scenarios where simple averages can be misleading. In quality control, Factory A might average 50 defects per batch with a range of 30, while Factory B averages 52 defects with a range of 8—making Factory B more reliable despite the higher average. Sports analysts compare player performance using both scoring averages and consistency measures. Weather forecasters examine temperature ranges alongside means to predict variability. Students learn that two basketball players might both average 15 points per game, but Player A's scores range from 5 to 25 points while Player B consistently scores 13 to 17 points, making Player B more dependable. These comparison skills transfer directly to interpreting medical studies, business analytics, and scientific research where understanding both central tendency and variability drives informed decision-making.
How to solve comparing data sets
Comparing Data Sets
- Compare averages (mean, median) to see which set is 'higher'.
- Compare spread (range, IQR) to see which set is more consistent.
- Use the same type of average for a fair comparison.
- Back up comparisons with specific values.
Example: Set A: median 12, range 8. Set B: median 15, range 3 → B is higher and more consistent.
Worked examples
Two factories produce widgets. Factory A averages 8 per day, Factory B averages 16 per day. Which produces more?
Answer: Factory B
- Compare the means → 16 > 8 — Factory B's average (16) is greater than Factory A's average (8).
Delivery times (days): Company A = 9, 9, 4, 8, 10, Company B = 8, 8, 8, 8, 8. Both average 8 days. Which is more predictable?
Answer: Company B
- Compare the spread → The second set has no variation (all values equal) — All values in the second set are the same, meaning zero spread.
- Conclusion → Company B is more predictable — Company B delivers in the same number of days every time.
Temperatures in two cities last week: City A = {7, 9, 11, 19} degrees, City B = {4, 5, 9, 11} degrees. Which city had more temperature variation?
Answer: Set A
- Compare the ranges → Range A = 12, Range B = 7 — Range A (12) > Range B (7).
- Conclusion → Set A is more spread out — A larger range means more spread.
Common mistakes
- Students compare only means and ignore spread, concluding that Team A (mean 12, range 15) performs better than Team B (mean 11, range 3) without considering consistency.
- When comparing ranges, students subtract incorrectly, calculating range as 18 - 12 = 5 instead of 6, leading to wrong conclusions about data spread.
- Students mix different measures of center, comparing Set A's mean (15) to Set B's median (14) and declaring A superior without using consistent measures.
- Students confuse larger range with better performance, claiming data set with range 20 is 'better' than range 5 without considering the context of the problem.