Work problem

[practiceisthekey]

Hello,

I'm currently new here and i am racking my brains out with a problem my client has given me.

I don't know if this belongs here tho.

So, i work an advertising firm and had a project to collect and register mobile numbers to our app. It works as a data gathering app of of some sorts and will be used for the dissemination of their advertising materials. Anyhow we had a big blunder as according to them, we had gathered almost 200,000 entries but have 127,730 duplicates. Of the 127,730 duplicates, 23,232 unique mobile numbers were used.

# of times the mobile number was registered	total duplicates	%
2 to 10	57177	~45
10 to 20	3769	~3
21 to 50	5184	~4
51 to 100	5043	~4
101 to 500	30279	~24
500 and up	26278	~21

TOTAL

127730

100

What i want to know is how do i get to know the the actual or approximate number of mobile numbers used for each of the first column figures. (i.e out of 23,232 mobile numbers how many was used 2 to 10 times, 10 to 20 times and so on)

I can't provide other data as client is furious at us. Thank you for your help.

 

[Steven G]

I would think that elementary school division would be appropriate here.

If each number was registered 2 times to produce 57,177 duplicates then there would be 57,177/2 numbers that were registered two times.
If each number was registered 10 times to produce 57,177 duplicates then there would be 57,177/10 numbers that were registered ten times.

If each number was registered between 2 and 10 ten times to produce 57,177 duplicates then there would be between 57,177/10 and 57,177/2 numbers registered between 2 and 10 times.

Alternatively you can use the midpoint value in each range of the numbers in the left column and divide the right hand column numbers by those numbers. Ex: Between 2 and 10 is 6, so compute 57,177/6 for a BAD approximation.