In a research study it is not always possible to measure an entire representing a specific demographic. (Some examples of demographics are students who attend a specific college, people who live in a specific city , state or neighborhood, people of a certain age range etc.). As a result measurements are taken from a sample of that population. The subjects from a sample population surveyed need to be randomly selected from a specific population of a specific demographic in order to be represented in an accurate manner.
Random Sampling- in the simplest terms means that each subject eligible to be in the study has an equal chance of being selected to be in the population under study. In this way the researcher can be more confident that the people in their sample are representative of the entire population of interest.
why would a researcher use another version of random sampling---stratified random sampling as opposed to simple random sampling?
A random sample would be ideal in order to protect the researcher against biases that will skew the data. For example, if you have a large population, and take a random sample of people, then you would hope that within your sample you would get a nice mix of people with different characteristics that would balance each other out.
Now, if you are just randomly selecting people, chances are you will get a nice mix of individuals. However, if you ...
Examples given to illustrate the points.