1. Question about sample size and margin of error

I am trying to determine if my dataset sample size is large enough to be statistically significant. I'm using a 95% confidence interval. However, every formula I've found uses margin of error---and to calculate margin of error, I need a sample size. This seems circular, and I am lost.

2. Re: Question about sample size and margin of error

You can't talk about statistical significance without actually having data.

It sounds more like what you're interested in is doing a sample size calculation. Typically for these you specify a specific alternative hypothesis and a power you would like to achieve. Once you have that information you can solve for the sample size required.

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

zizekkeynes (12-05-2013)

4. Re: Question about sample size and margin of error

I do have a dataset, actually. I'm trying to determine if the samples it used were large enough.

I'm really new to all this, so let me back up a bit. I'm looking at a bunch of operating expenses for various properties, and I want to know if I can say "in x state, operating expenses were z on average" and have that be statistically significant. Not sure how hypothesis would work with that? (Also unfamiliar with power.)

5. Re: Question about sample size and margin of error

try 1-sample equality test, use alpha=0.05
http://powerandsamplesize.com/Calcul...ample-Equality

 Tweet