The groups or subsets will be "mirror images" of each other (except for chance differences).
For example, if you start with a convenience sample of 100 people and randomly assign them to two groups of 50 people, the two groups will be "equivalent" on all known and unknown variables.
Random assignment generates similar groups; it is used in experimental research to produce the strongest experimental research designs.
You can use this randomizer program for random assignment:
Determining the Sample Size When Random Sampling is Used
Would you like to know the answer to the question "How big should my sample be?"
I will start with my four "simple" answers to your important question:
Always try to get as big of a sample as you can for your study (up to say a 1000 people or so).
If your population is only100 people or fewer, then include the entire population in your study rather than taking a sample (i.e., don't take a sample; include everyone).
To get a feel for typical sample sizes, examine other studies in the research literature on your topic and see how many they are selecting.
For an exact number of people to sample, just look at Figure 7.5 which shows recommended sample sizes.
Use a sample size calculator. (Generally these require you to learn a little bit of statistics first.) Here is one available on the web:
Here are a few more points about sample size. In particular, you will need samples under these circumstances:
When the population is very .
When you want to break down the data into multiple categories.