Goodnight!
I have questions regarding the definition of sample size.
The aim of the study is to evaluate if the mother's diet will contribute to the offspring's obesity rates.
The experiment in question has the following design:
Six types of diet and a control diet will be used in the treatments of female mice. After the experiment and the mating of the females, we only need to use the male individuals of the offspring. Therefore, I need to define the number of female mice that will be used in each of the treatments, and define the number of male individuals that will be selected from each offspring, to carry out the index tests.
For ethical reasons, I need to use as few individuals as possible and I need statistical bases to define this number. A big problem is that we cannot predict how many males will come from each problem.
Can anybody help me?
I would recommend that you try and make a power calculation, in order to find out how many subjects you need in each group. See if you can find high-quality trials in mice, which have investigated something similar, and base your calculation on means and standard deviations from this study.
I would not base any sample size calculation on published data. There are two reasons for this. The first is that published estimates are subject to sampling error (yes, the standard deviation has a confidence interval too). But far more important is that sample size should be set so that you have an acceptable power to find the smallest effect size that is of real life importance. (And 80% is not acceptable – a guaranteed chance of 20% of failing to find the effect if is exists!)
You need to define the minimum effect of maternal diet on offspring obsesity that would be clinically/practically significant as a basis for sample size calculations.
Hello Carolina Mendes Muniz. If I understand, your eventual analysis will (or could) use data at 3 levels: The male offspring mice are at Level 1; they are clustered within mothers, who are at Level 2; and the mothers are clustered within the 7 dietary conditions, which are at Level 3. Is that right? Thanks for clarifying.
If you will be using a multilevel model for the eventual analysis, I think that simulation may be the best (and maybe only) way to carry out a power analysis. What software do you use, by the way?
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size