How many people do you need to talk to to get a margin of
error you are comfortable with? Consult our handy calculator and
find out!
Listed below are few terms you will need to understand before using
the sample size calculator:
Confidence Level: The percentage value that tells how confident a researcher can be
about being correct. A 95% confidence level is a generally acceptable
level of confidence and is most typically used and accepted within
the research industry. Which means that if a study were conducted
100 times, answers would be within the margin of error 95 out of
100 times.
Margin of Error / Confidence Interval: Assumes that you have
a random sample. The margin of error for a typical survey is +/
5%. This means that results may vary as much as five percent in
either direction. The margin of error for subsamples (i.e. men
versus women), is based on the number in that subsample.
Population Size: The population size is the universe from
which you are taking your sample. If the population size is very
large or unknown, leave this field blank.
DIRECTIONS:
 Choose a confidence level
 Enter an acceptable margin of error (between .1 and 50  leave
off % sign)
 Enter population (if known)
Click on "calculate"
 This calculator requires Internet Explorer 3.0 or later or Netscape
3.0 or later or a compatible browser. Leave the population box
blank, if the population is very large or unknown.
CAUTION: Sampling error is only one source of bias. Contact us
to discuss other possible sources of bias (i.e. question bias).
(This sample size calculator was created by Creative
Research Systems.)
Sample Size: n= 
50

100

200

300

400

600

800

1,000

Margin of Error*:(+/) 
14.2%

10.0%

7.1%

5.8%

5.0%

4.1%

3.5%

3.2%

The
margin of error for a poorly designed survey: +/ 100%
* Based on a 95% level
of confidence; assumes a random sample and worstcase (50/50) response. If this does not make sense, it's time to call Riley Research. 