Stratifying can enhance the precision of a sample estimate without increasing the sample size. In other words, you can get the same level of precision by either drawing a larger random sample, or by using a well-thought-through stratified random sample of a smaller size.

Simple random and systematic sampling techniques are very important to successful survey research. They make sure your sample is representative and defines what degree of error you will see in you results. Stratified sampling is not an alternative to these methods but is a modification of their use. Stratifying a sample enables you to easily breakout survey results by different segments of your population.  A stratified is likely to be more representative on a number of variables than a random sample. When a sample is stratified, various segments of interest are identified prior to sample selection and a sufficient quantity of names is selected from each. An example might help illustrate how a stratified sample can provide cost-efficient way of examining characteristics of desired segments while obtaining data that more accurately reflects the overall characteristics of your survey population.

Let’s look at the breakdown of Company X’s education customer base: 10% - small schools, 30% - large schools, 60% - medium schools. (Estimated total market, 10,000 schools)

Without stratifying the sample, you would expect to receive the same proportion of responses as the population.

Using random sampling, these are the anticipated results you would see with an overall population of 10,000 schools.

Note: there is a fairly large sampling error in the small school segment. As such, the data has questionable value. You could increase the size of the total sample by a factor of three (the number of small school responses should increase threefold), but the cost of your survey research effort would increase significantly.

Solution
A smart solution is to stratify the sample. This is done by first, grouping the names of schools by segment type before undertaking sampling. Then selecting a specific number of names from each segment (rather than in proportion to actual population totals). Using the above scenario, here is an example of stratifying a sample and its impact:

Collecting an equal number of responses from each segment provides the same sampling error for each. The small sacrifice in precision for large schools (±8.3 vs. ±6.3%) is more than offset by increased precision for the small school segment. (±8.3 vs. ±15.5%)

Stratifying your sample is an affordable way to examine the characteristics of specific segments while still getting data that accurately reflects the overall characteristics of your population.