Of course most of the experiments you have read about in these revision notes take place in a controlled environment. This means that the conditions have been set up and controlled by the researchers in an artificial environment i.e. a laboratory, a classroom or an observation unit. The problem with this is people may not behave in the same way in the real world, whereas it is the real world we are trying to understand.
Some experiments can take place in the real world. Scientists may observe the behaviour of children in a playground, for example, or parking patterns in supermarket car parks. It may be argued that the results of such experiments have more ecological validity i.e. they relate more directly to the way people actually behave in real situations. The disadvantage of this is that conditions aren’t controlled and the data is far harder to collect. At least in a controlled environment later researchers can repeat the experiment to test its accuracy and cause and effect can be more accurately identified.
——————————————————-
Sampling methods
If you know which section of the population you are trying to understand then this is your target population. Of course you can only use the tiniest fraction of this population and your participants are collectively known as the sample. You want your sample to be as representative of the target population as possible so that you can make a generalised conclusion. This means that the behaviour exhibited by the participants in your sample is similar to how other members of the target population would behave. There are a number of sampling methods:
Opportunity sampling: This is when you select members from the target population simply because they are willing to be participants in the study. This is perhaps the quickest way of going about selecting participants but is likely to be unrepresentative.
Random sampling: When the target population has been identified you select at random which ones will become part of your study. This can be done by allocating numbers and drawing from a hat or by using a random selection computer programme. Each member has an equal chance of being selected. This results in a representative sample and there is no human bias in the selection process. It can however take a lot of time to set up.
Systematic sampling: Every nth member of the population is selected as a participant e.g. every 20th. This is a simple procedure but may not necessarily end up as a representative sample.
Stratified sampling: The researcher selects an equal percentage of participants from each subgroup of the target population. This is the most representative of the sampling techniques but can take a long time to set up.