# Thread: Central tendency in stattistic:

1. ## Central tendency in stattistic:

If anyone want to calculate or estimate average age of people of a country (say India) what will be the appropriate method- mean, median or mode and why?

2. ## Re: Central tendency in stattistic:

Some context of what you want to do would be helpful, but in general, you need to understand the distribution shape. If symmetrical, the mean would work. If asymmetrical, use the median. The mode is used for nominal or ordinal data, and is not very useful for continuous data. Even when you bin continuous data, the choice of bin sizes will influence and change the mode.

3. ## The Following User Says Thank You to Miner For This Useful Post:

Suvamoy (09-20-2016)

4. ## Re: Central tendency in stattistic:

So I think It should be median.

5. ## Re: Central tendency in stattistic:

Based on this , I would agree.

6. ## Re: Central tendency in stattistic:

Originally Posted by Suvamoy
If anyone want to calculate or estimate average age ....
So you want to estimate the AVERAGE age.

The sample mean or average is a good estimate of the population average (from a simple random sample).

So I don't agree about using the median.

The population median will be different unless the density is perfectly symmetrical. But if you look at the enclosed link for India then you will see (lean your head 90 degrees) that it is very skewed. It almost look like a half normal distribution. So the population mean and sample mean will be very different from the population or sample median.

7. ## Re: Central tendency in stattistic:

It ends up depending on your objective. Mean is the center of mass of a distribution. Median is the 50th percentile.

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts