# CDF of average

#### lina2401

##### New Member
Hi all,
I hope that someone can help me with this! I have a list of values as below:
82.1134
84.5516
91.1851
65.6035
69.971
92.4706
79.1505
93.0844
92.9598

and I need to find the CDF of their average! how can calculate and present that in a chart?

I do appreciate any help with this. Thanks in advance.
-Lina

#### Dason

You question doesn't really make sense. What do you mean by the CDF of their average? Their average is a single number...

#### lina2401

##### New Member
Maybe I should rewrite the question in a different way!
What would be the CDF of the above numbers?

#### Dason

Well do you know what a CDF is? What is the definition?

#### lina2401

##### New Member
All what I know is from the Wikipedia!! I tried to find some practical examples but I couldn't!

#### Mean Joe

##### TS Contributor
An important thing to know about the CDF (cumulative distribution function) is its definition...

Some basics:
the input to the CDF is a number. The output from the CDF is a number between 0 and 1.

If you see/say CDF(4.8)=0.25, then that means 25% of values from the distribution fall at/below 4.8.

#### lina2401

##### New Member
I need to do it by hand.

#### lina2401

##### New Member
No I need this as part of a research!

#### seanw

##### New Member
Maybe I should rewrite the question in a different way!
What would be the CDF of the above numbers?
Hi lina2401,

It depends on what you mean by "the CDF." A CDF, as has been pointed out, is a function. You supply the value of x (a single observation from a distribution X), and the CDF gives you p(X<=x), i.e., the proportion of scores that are less than or equal to x, i.e., the probability of a single random observation from X being less than or equal to x. In that sense, "find the CDF" could simply mean "calculate p(X<=x) for each x".

If, on the other hand, by "find the CDF" you mean you want to identify what distribution these values come from, that's a much more complicated issue. For that, you'd need to consider the nature of the data, consider running some goodness-of-fit tests for different distributions, examine quantile reference plots, etc.

#### hlsmith

##### Less is more. Stay pure. Stay poor.
If it is for research why do you have to do this by hand? I would assume you could easily do it with Microsoft Excel or any other commonly available software.

#### rogojel

##### TS Contributor
hi,
this seems to be an application of the central limit theorem, no?