For example, to obtain a stratified sample of university students, the researcher would first organize the population by college class and then select appropriate numbers of freshmen, sophomores, juniors, and seniors. This ensures that the researcher has adequate amounts of subjects from each class in the final sample.
It is important to note that the strata used in stratified sampling must not overlap. Having overlapping subgroups will give some individuals a higher chance of being selected as subjects in the sample. If this happened, it would not be a probability sample.
Some of the most common strata used in stratified random sampling are age, gender, religion, educational attainment, socioeconomic status, and nationality.
When To Use Stratified Sampling
There are many situations in which researchers would choose stratified random sampling over other types of sampling. First, it is used when the researcher wants to highlight a specific subgroup within the population. Stratified sampling is good for this because it ensures the presence of key subgroups within the sample.
Researchers also use stratified random sampling when they want to observe relationships between two or more subgroups. With this type of sampling, the researcher is guaranteed subjects from each subgroup are included in the final sample, whereas simple random sampling does not ensure that subgroups are represented equally or proportionately within the sample.
Researchers who are interested in rare extremes of a population often use stratified random sampling because he or she can representatively sample even the smallest and most inaccessible subgroups of the population. Simple random sampling does not allow this.
Stratified random samples generally require smaller sample sizes, which in turn can save a lot of time, money, and effort for the researchers. This is because this type of sampling technique has a high statistical precision compared to simple random sampling due to the fact that the variability within the subgroups is lower compare to the variations of dealing with an entire population.
Proportionate Stratified Random Sample
In proportional stratified random sampling, the size of each strata is proportionate to the population size of the strata when looked at across the entire population. This means that each stratum has the same sampling fraction.
For example, let’s say you have four strata with population sizes of 200, 400, 600, and 800. If you choose a sampling fraction of ½, this means you must randomly sample 100, 200, 300, and 400 subjects from each stratum respectively. The same sampling fraction is used for each stratum regardless of the differences in population size of the strata.
Disproportionate Stratified Random Sample
In disproportionate stratified random sampling, the different strata do not have the same sampling fractions as each other. For instance, if your four strata contain 200, 400, 600, and 800 people, you may choose to have different sampling fractions for each stratum. Perhaps the first strata with 200 people has a sampling fraction of ½, resulting in 100 people selected for the sample, while the last strata with 800 people has a sampling fraction of ¼, resulting in 200 people selected for the sample.
The precision of using disproportionate stratified random sampling is highly dependent on the sampling fractions chosen and used by the researcher. Here, the researcher must be very careful and know exactly what he or she is doing. Mistakes made in choosing and using sampling fractions could result in a stratum that is overrepresented or underrepresented, resulting in skewed results.
Advantages of Stratified Sampling
Using a stratified sample will always achieve greater precision than a simple random sample, provided that the strata have been chosen so that members of the same stratum are as similar as possible in terms of the characteristic of interest. The greater the differences between the strata, the greater the gain in precision.
Administratively, it is often more convenient to stratify a sample than to select a simple random sample. For instance, interviewers can be trained on how to best deal with a particular age or ethnic group while others are trained on the best way to deal with a different age or ethnic group. This way the interviewers can concentrate on and refine a small set of skills and it is less timely and costly for the researcher.
A final advantage that stratified random sampling has over simple random sampling is that is guarantees better coverage of the population. The researcher has control over the subgroups that are included in the sample, whereas simple random sampling does not guarantee than any one type of person will be included in the final sample.
Disadvantages of Stratified Sampling
One main disadvantage of stratified random sampling is that is can be difficult to identify appropriate strata for a study. A second disadvantage is that it is more complex to organize and analyze the results compared to simple random sampling.
Babbie, E. (2001). The Practice of Social Research: 9th Edition. Belmont, CA: Wadsworth Thomson.
Castillo, J.J. (2009). Stratified Sampling Method. Retrieved March 2012 from Experiment Resources: http://www.experiment-resources.com/stratified-sampling.html