Sample-Size Calculator
1. Enter the number of people in the total population you want to sample.2. Enter the desired confidence interval — the "margin of error." For example, if you enter "3," you'll calculate a sample that will provide results accurate to plus or minus three percentage points.
3. Enter the desired confidence level. Most research is done at a 95% level — meaning you can be sure 95% of the time the results are the "true" results.
4. Select the "Calculate" button, and read your sample size.
Population
Population is the number of potential
respondents in the "universe" being sampled, such the
number of adults in a community, the number of customers in a market
segment, the number of households in a city, the number of members
in an association, or the number of supervisors in a manufacturing
plant. In practice, only some of these people actually will be surveyed,
and out of those only some actually will respond to a particular
question.
Confidence Interval
Confidence interval is the plus or minus
figure reported with survey results which specifies the range where
the real percentage falls. For example, if you use a confidence
interval of +/-3 and 43% of the sample answers a certain way, you
can be sure that the true results fall between 40% (-3) and 46%
(+3). Choosing a very small confidence interval (to get more accurate
Confidence Level
Confidence level is a percentage –
usually 95% or 99% – that represents how certain you are
that data are the true results. A 95% confidence level means you
can be certain 95% of the time that the data are the true results,
while a 99% confidence level means that you can be certain 99%
of the time.
Sample Size
Sample size is the number of people
who will need to respond to a particular question in order to provide
data of the desired precision. For more accurate survey results,
the sample size should be as close to the population size as possible.
In practice, however, issues such as time, logistics and cost often
cause researchers to reduce this number.