What Is The Best Sample Size For A Population. A rule-of-thumb is that for small populations 500 you select at least 50 for the sample. Now if 60 of the participants reported a fear of heights there would be a 95 probability that between 50 and 70 of the total population have a fear of heights.
If you increase the sample size to 100 people your margin of error falls to 10. In a population of 200000 10 would be 20000. The smaller the population the larger the required sample ratio.
Different sample size formula are required depending on the research underlying statistical test for example a t-test for comparing two means a z-test for comparing two proportions or a log-rank test in time to event analyses.
Now if 60 of the participants reported a fear of heights there would be a 95 probability that between 50 and 70 of the total population have a fear of heights. Different sample size formula are required depending on the research underlying statistical test for example a t-test for comparing two means a z-test for comparing two proportions or a log-rank test in time to event analyses. The formula does not cover finite population. The smaller the population the larger the required sample ratio.
