Survey Sampling
Error
In most research projects, the sample size is determined by
the level of acceptable error. Errors in survey research arise
from three distinct sources:
1. Missing data from noninterviews and from item nonresponse.
2. Inaccurate information given by respondents or recorded by
interviewers.
3. Sampling error.
While the first two sources of error are independent of the
sample size, the third source of error is directly correlated
with it.
Though interviewing all the individuals in a target population
would eliminate sampling error, practical considerations such
as cost prohibit such precision. Therefore all surveys that draw
a sample of people from the total population are subject to sampling
error. But how much sampling error is acceptable?
Here's how it works: If we conduct a survey 100 times, we can
be confident that 95 times out of the 100, characteristics of
the sample would reflect the characteristics of the targeted
population plus or minus the number of percentage points shown
in the table below.
For example, if we survey 2500 people from the targeted population,
and 55% of those people answer "yes" to a given question,
we can be confident that between 53% and 57% of the total population
would have answered "yes" had they been asked the same
question.
Sample
Size 
Sample Error 
Sample
Size 
Sample
Error 
25 
20.0% 
800 
3.5% 
50 
14.2% 
1000 
3.2% 
100 
10.0% 
1200 
2.9% 
150 
8.2% 
1500 
2.6% 
200 
7.1% 
2000 
2.2% 
250 
6.4% 
2500 
2.0% 
300 
5.8% 
3000 
1.8% 
400 
5.0% 
4000 
1.6% 
500 
4.5% 
5000 
1.4% 
600 
4.1% 

