# Thread: how to understand if difference between two freq is significant

1. ## how to understand if difference between two freq is significant

Hi,
I need a suggest, I am not a statistician.

I have an observed frequency distribution.

A - 47.7
B - 51.9
C - 0.4

The sample is N=1626.
The theoric statistical error is 2,43

----------------------------------

1) what is the probability (how I can compute) that "A" assumes the maximum value "A+2.43" and in the same time "B" assumes the minimum value "B-2.43"

2) in general, what is the probability that "A" becames greater than "B"?

However, my problem is to understand if the difference between "A" and "B" is, stable, significant, or something like this.

TIA
Arni

2. ## Re: how to understand if difference between two freq is significant

Your questions really don't make sense to me. Are A/B/C categories? Or are they numbers? If they're the probability distribution then those are the only three values they can take so your question (1) really just doesn't make sense to me. Can you explain a little more?

3. ## Re: how to understand if difference between two freq is significant

Ok.
A/B/C are categories (ie Black/Green/Yellow).
In a survey, I observed:
A = 47.7%
B = 51.9%
C = 0.4%
(A+B+C =100%)

The statistic error is +-2.43, so I can read (in theory):

A = 50.13 (47.0 + 2.43)
B = 49.47 (51.9 - 2.43)

In the observed case B>A in the theoric case B<A.
Is there a way to understand how many probability I have to get the second case (B<A)?

 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