¶ … desirable for the researcher to randomly assign subjects to the treatment and control groups than for the groups to evolve naturally? The whole purpose behind random assignment is to try to single out a single factor that is changing the experimental results. Narrowing down results to a single variable means otherwise equalizing the experimental groups. Therefore, having two experimental groups that are as similar as possible is an important component in the experimental design. If subject can self-select, there is a possibility that there is something different about the members that self-select to be in different groups that makes their outcomes different.

Instead, an experimental design tries to achieve as much similarity between two groups as is possible. "One group (the program or treatment group) gets the program and the other group (the comparison or control group) does not. In all other respects, the groups are treated the same. They have similar people, live in similar contexts, have similar backgrounds, and so on. Now, if we observe differences in outcomes between these two groups, then the differences must be due to the only thing that differs between them -- that one got the program and the other didn't" (Troohim, 2006).

Furthermore, Troohim believes that random assignment is the key to a successful experimental design. In fact, even with random assignment, he acknowledges that the two groups will not be exactly the same, but instead will be probabilistically equivalent, which means that they are equivalent...

Therefore, assuming that the samples are sufficiently large, then the random assignment should be sufficient to help establish causation between the independent and dependent variables, if that causation does, in fact, exist.
2.What is the weakness of posttest only designs?

Posttest only designs frequently use two groups, one group, the experimental group, has the independent variable and the other group, frequently called the control group, does not have the independent variable. Both groups undergo the same type of testing, with the goal of understanding the impact of the independent variable on the dependent variable. Then, researchers use statistical analysis to determine the impact of the independent variable on the dependent variable. Posttest only designs are frequently used in medical research, particularly drug research.

One of the weaknesses of the posttest only design is its limitation in scope; because it only looks at the groups after their assignment and after the application of the independent variable, this research method can offer little real insight into the makeup of the groups. Theoretically, the two groups are supposed to be virtually identical when testing begins in order to be able to assign outcomes to the independent variable. However, this is not necessarily the case. In fact, the posttest only design "is very poor at guarding against assignment bias, because the researcher knows nothing about the individual differences within the control…