I am considering a particular vehicle model and going to assess the maintenance practices. There are two versions of it coming out from two different countries and I'm considering one version shipped out from one country. It is hard to get the total number of vehicles available in that particular model which in tern made the determining the population difficult. What would be the best method to determine the sample size for the survey.
When I consider 95% confidence level with a confidence interval of 5, the sample size can be found as 384. Is it the correct number? can I go for lesser number of sample?
Optimal sample size depends on your population size. It's 278 for a population of 1000 at those parameters or 370 for 10,000, etc. But survey sampling can still give you valuable answers without having a sample size that represents the general population, as long as it is at least 30. The central limit theorem (CLT) states that the distribution of sample means approximates a normal distribution as the sample size gets larger, regardless of the population's distribution. Sample sizes equal to or greater than 30 are often considered sufficient for the CLT to hold.
Please, have a look on our article:
Article Population versus sampling procedures: implications from epi...
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size