Suppose you want to take an average of your ratings by voters. You segregate them by age and ask them to rate you out of 5, 5 being the best. This is what you get:
| Age Range | Total Voters | Average Rating | |
| 10-20 | 10 | 5 | |
| 20-30 | 100 | 4 | |
| 30-40 | 150 | 2 | |
| 40-50 | 80 | 3.5 | |
| 50-60 | 60 | 2.5 |
What is a good way to understand the overall average?
Well, you could just take an average of averages = (5+4+2+3.5+2.5)/5 = 3.4
BUT, there is a problem with that. The number of young voters is the highest, but their voice is not represented. In fact, out of a total of 400 voters, as many as 150 have given an average rating of just 2!
How do we make sense of this data?
Well, we use something called weighted average. That is, we give a weightage (importance) to each number according to something that matters. in this case, it is the number of voters.
Weighted average can be based on anything that is important. In this case, it is the number of voters in an age group. In another case, it could be cities, it could be share of trade (as in the UN FAO Monthly Food Index), etc.
One Reply to “What is weighted average?”
Comments are closed.