I am planing a cross sectional survey on maternal health literacy. What is the best way to calculate the sample size?
1. Use the real number of population (2400) calculated on https://www.calculator.net. the sample size is 332.
2. Use the effect size of a prior study to calculate using G*Power.
I personally would recommend using G*Power, but you certainly could compare the two results from the two different ways of estimating sample size.
If you want to scientifically calculate the appropriate sample size for your study, then I would suggest you adopt the time tested Krejcie and Morgan formula- Article Determining Sample Size for Research Activities
.https://www.kenpro.org/sample-size-determination-using-krejcie-and-morgan-table/
s. Rama Gokula Krishnan That approach was needed 50 years ago before computers. Now online sample size calculators allow you to vary your assumptions about effect size etc,
You can think about it;
With 95% conference sample size is 384 × 1.5 design effect + 5% error
You can change design effect and error according to the requirement of your research.
Before confirm your sample size, the issues you needs to clear:
1. Is it manageable by you?
2. Do you get........... number of sample (like patient of rare disease will not found huge) you take?
3. Do you have enough budget for data collection for the sample you are going to taka? (Here budget for survey)
Thank you for all answers! Rafia Rahman I am not sure what 384 came from? and how can I calculate the design effect and 5% error? Thank you
As my study is a simple survey, I can not find any effect size from prior study to put on G*Power. David L Morgan
To be 95% confident that the true value of the estimate will be within 5 percentage points of 0.5, (that is, between the values of 0.45 and 0.55), the required sample size is 385. This is the number of actual responses needed to achieve the stated level of accuracy.
The design effect (denoted as deff) is defined as the ratio of the variance of an estimate under a sampling plan to the variance of the same estimate from a simple random sample with same number of observation units. The sampling plan could be a stratified sampling or other complex sample designs.
Error is marginal error.;The margin of error in statistics is the degree of error in results received from random sampling surveys. A higher margin of error in statistics indicates less likelihood of relying on the results of a survey or poll, i.e. the confidence on the results will be lower to represent a population.
Thitaporn Siriwan I am not sure what you mean by a "simple survey." For G*Power, you would need to have an estimate of an effect for a t-Test or correlations etc.
If you are only going to collect descriptive statistics, then the result you originally showed from the sample size calculator would be sufficient.
- Badges
- Science topic
- Similar topics
- Phytochemistry
- Extracts