# Thread: Confidence intervals: normal vs t-distribution (central limit theorem)

1. ## Confidence intervals: normal vs t-distribution (central limit theorem)

Hi all!

We did a serological survey for a disease taking 300 samples in a population of 50 000.

If our sample mean gives a 2% prevalence. How do we work out the confidence intervals? I have all the formula's and there are great CI calculators on the web BUT seeing that is only one survey then does the central limit theorem apply allowing us to use the z-score from a normal distribution?

Or should we rathr use the z-score from a t-distribution?

Many thanks!

Johann

2. ## Re: Confidence intervals: normal vs t-distribution (central limit theorem)

I think I've answered my question. Even though this was only one survey. The number of samples taken within the survey permits application of the central limit theorem.

3. ## Re: Confidence intervals: normal vs t-distribution (central limit theorem)

Was your outcome, disease => Yes/No?

If so, you can use the standard 95% CI for a proportion.

 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