1. ## sample size

Hi everyone,

I do my research to see the association of 2 qualitative variables which make 2x3 contingency table. I calculate the required sample size by using G*Power. I got 964 of the total sample size from G*Power. The problem is my population size have just 330. What should I do?

For more information, the parameter that I input in G*Power is as followed:

- effect size = 0.1
- alpha=0.05
- power=0.8
- df=2.

Thank you.

2. ## Re: sample size

Given that effect size, what power will you have? Now is that risk of a type II error (accepting the null when it should be rejected) acceptable to you?

You could also see what effect size given your constraints that you can reliably discern giving the constraints.

3. ## Re: sample size

Originally Posted by hlsmith
Given that effect size, what power will you have? Now is that risk of a type II error (accepting the null when it should be rejected) acceptable to you?

You could also see what effect size given your constraints that you can reliably discern giving the constraints.

The effect size of 0.1 that I set was from the previous research. Sometimes I set it from my pilot research. Can it from other way? Can I set it by myself?

4. ## Re: sample size

If previous research indicates an only small effect size (0.1), then using a larger effect size for the calculations would look dubious, IMHO.
What you could possiby do is to calculate the power you'd achieve with n=330, effect size 0.1 and alpha = 0.05; so that you can get an
impression whether power is still acceptable.

With kind regards

PonderStibbons

5. ## The Following User Says Thank You to Karabiner For This Useful Post:

saitharndham (11-06-2017)

 Tweet