Factors Affecting Causal Claims Flashcards
Who was the experiment conducted on?
It is important to note who the experiment was conducted on. Because results from the experiment can only be applied to that group. For example a test on males cannot necessarily be applied to females.
What is the Explanatory Variable?
The explanatory variable is the variable that attempts to explain or cause the changes observed in the response variable. All other variables must remain unchanged (controlled).
What is the Treatment?
The treatment is one of, or a combination of, explanatory variables assigned by the researcher.
What is the Response Variable?
This is what we are measuring or what we are wanting to see a change in, in response to the explanatory variable.
How were participants put into groups?
When making the groups, the goal is to make them as similar as possible so that the treatment applied to each group is the only difference. Making these groups through a random selection process eliminates bias in group making, meaning the groups will be more similar. However, if groups were selected non-randomly, Bias and favoritism will affect the groups meaning they may be more different.
Was there a control group?
This group creates a baseline of what would happen if there was no treatment applied. Allowing researchers to determine the effect of the treatment more accurately.
Was a Placebo Used?
A control group is sometimes given a placebo. For example, a sugar pill with no drug inside it. This can sometimes cause the placebo effect, where people experience positive/negative changes without having the treatment.
Was Blinding Used?
Oftentimes researchers who are creating a new drug really want it to work, so are biased towards seeing positive results. To avoid this researchers will use a blinding procedure. There are two types of blinding, single blinding and double-blinding. In single blinding, either the researcher or the participant knows who has received the treatment. And in Double-blinding neither the researcher nor the participant knows who has received the treatment. In this case, a third party knows which participant has received the treatment and informs them after the measurements have been taken. Double-blinded is the better method.
Are there any ethical considerations to be made?
In many situations it is not ethical to conduct an experiment. For example, you cant get some pregnant mothers to drink alcohol and some not to, to see how it affects the development of their unborn child. So sometimes you must only do an observational study instead of an experiment.
