Median Calculation in Economics
You already know the median from everyday life. If five friends have pocket money of ₹50, ₹100, ₹150, ₹200, and ₹5000, the "middle" value — ₹150 — tells you more about the group than the average (which gets pulled up to ₹1100 by that one high value). That's the median: the value that splits a sorted list into two equal halves.
The Precise Meaning
The median is the positional average — it depends only on the order of values, not on their magnitude. For any set of data arranged in ascending order:
- If the number of observations (n) is odd, the median is the 2n+1th observation.
- If n is even, the median is the average of the 2nth and 2n+1th observations.
Median=Value of the 2n+1th item (for odd n)
Median=2Value of 2nth item+Value of 2n+1th item (for even n)
Why It Matters in Economics
Economics deals with skewed distributions — most people earn less than the average, most households own less than the average wealth. The median gives you the typical experience. When the government reports "median household income," it's telling you what the person exactly in the middle earns. Half the households earn less, half earn more. That's far more meaningful than the mean, which a handful of billionaires can distort.
Calculating the Median from Raw Data
Example 1 (odd n): Incomes of 5 workers: ₹8000, ₹12000, ₹15000, ₹25000, ₹60000.
Arrange in ascending order (already done). n=5, so median is the 25+1=3rd value = ₹15000.
Example 2 (even n): Incomes of 6 workers: ₹8000, ₹12000, ₹15000, ₹25000, ₹60000, ₹200000.
n=6. The 26=3rd value is ₹15000, the 4th value is ₹25000. Median = 215000+25000= ₹20000.
The Median for Grouped (Continuous) Data
In economics, you rarely get raw numbers — you get frequency distributions like "income between ₹10000-₹20000: 50 people." Here, the median lies inside a class interval. The formula is:
Median=L+f2N−cf×h
Where:
- L = lower limit of the median class (the class where the cumulative frequency first reaches or exceeds 2N)
- N = total frequency
- cf = cumulative frequency of the class before the median class
- f = frequency of the median class
- h = class width
Step-by-step logic:
- Find 2N.
- Build a cumulative frequency column.
- Identify the median class — the first class where cumulative frequency ≥2N.
- Plug into the formula.
The formula is just linear interpolation. You're saying: "I need to go 2N−cf items into this class of f items, which covers a width of h." So you add that fraction of the width to the lower limit.
A Worked Example
| Income (₹) | Frequency | Cumulative Frequency |
|---|
| 0-10000 | 10 | 10 |
| 10000-20000 | 20 | 30 |
| 20000-30000 | 30 | 60 |
| 30000-40000 | 25 | 85 |
| 40000-50000 | 15 | 100 |
N=100, so 2N=50. The cumulative frequency first reaches 50 in the 20000-30000 class (cumulative freq = 60). That's the median class.
L=20000, cf=30 (cumulative frequency before this class), f=30, h=10000.
Median=20000+3050−30×10000=20000+3020×10000=20000+6666.67=₹26666.67 …