Scientific studies often rely on surveys.If you want your sample to reflect the conditions of the overall population, you need to include a certain number of people.To calculate your sample size, you need to determine several set values and plug them into an appropriate formula.
Step 1: Know the population size.
Population size is the total number of people in your demographic.You can use an approximated value for larger studies.When working with a small group, precision has a bigger impact.If you want to conduct a survey among employees of a small business, the population size should be within a dozen or so people.Larger surveys allow for more deviation from the actual population.Even though the actual value may vary by hundreds of thousands, you can estimate the size of your demographic by including everyone in the United States.
Step 2: Determine the margin of error.
"confidence interval" refers to the amount of error you want to allow in your results.Your sample results will be close to the true value of the overall population discussed in your study if you use the margin of error.Choosing a smaller margin of error will result in more accurate answers, but it will also require a larger sample.The margin of error is usually a plus or minus percentage.If the entire population were asked the same question, the margin of error would be between 30% and 40%.
Step 3: Your confidence level should be set.
Confidence interval is related to confidence level.The degree of certainty is measured by how well a sample represents the overall population within your chosen margin of error.You can claim that you are certain that your results fall within your chosen margin of error if you choose a confidence level of 95.A larger sample is needed to get a larger degree of accuracy.99% confident is the most common confidence level.Setting a confidence level of 95% for the example stated in the margin of error step would mean that you are certain that 30% to 40% of the total concerned population would agree with option A of your survey.
Step 4: You should specify your standard of deviation.
The standard of deviation shows how much variation you expect.Moderate results are more likely to be accurate than extreme answers.If 99% of your survey responses answer "Yes" and only 1% reply "No", the sample probably represents the overall population very accurately.There is a greater chance of error if 45% answer "Yes" and 45% don't.The value is difficult to determine, so most researchers set it at 50%.If you stick with this value, your sample size will be large enough to represent the entire population within your confidence interval and confidence level.
Step 5: You can find your Z-score.
The Z-score is set based on your confidence level.The standard normal score is the number of standard deviations between any selected value and the average of the population.You can find a Z-score on a table or use an online calculator.Each of these methods can be very complex.Most researchers memorize the necessary Z-score for the most common confidence levels since they are fairly standardized.
Step 6: Look at the equation.
If you have a small to moderate population, you should use the standard formula.The standard formula for sample size is:
Step 7: Plug in your values.
The numerical values that actually apply to your survey should be replaced with the variable placeholders.Determine the ideal survey size for a group of people.A 50% standard of deviation and a 5% margin of error are used.You would have a Z-score of 2.58 for 99% confidence.This means that there is a difference between N and 2.58 and 0.05 and 0.5.
Step 8: Do the math.
The equation can be solved using numerical values.The sample size is represented by the solution.The sample size is 1 + [z * p(1-p)] / e * N.
Step 9: Look at the formula.
If you have an unknown population, you'll need to use a secondary formula.The top half of the formula can be used if you still have values for the rest.
Step 10: Put your values in the equation.
The numerical values for your survey should be replaced with the variable placeholders.Determine the necessary survey size for an unknown population with a 90% confidence level, 50% standard of deviation, and 3% margin of error.The Z-score is 1.65 for 90% confidence.This means that it's 1.65 e and 0.03 p.
Step 11: Do the math.
Plugging numbers into the formula will help solve the equation.Your sample size will be indicated by your answer.A sample size is defined as the amount of space between the letters p and e.
Step 12: The formula should be looked at.
When you can estimate the population but don't know how a certain population behaves, you use a very general equation called Slovin's formula.The least ideal formula is described as: N + population size e + margin of error.If circumstances prevent you from determining an appropriate standard of deviation and/or confidence level, you should only use this.
Step 13: Plug in the numbers.
The numerical values that apply to your survey should be replaced with the variable placeholders.To get a 4% margin of error, you have to calculate the necessary survey size.This means that there is a difference of 0.04 and N.
Step 14: Do the numbers.
Use your survey-specific numbers to solve the equation.The answer should be your survey size.The final answer is 173.41, which is the sample size of N + N*e.