Studied by 0 people
Experimental Design, and Null Hypothesis
Independent Variable
The varianle that is being tested.
Dependent Variable
The measured outcome resulting from the Independent Variable.
A properly designed experiment is also known as…
A controlled experiment
What do controlled experiments do?
They allow us to test only one thing, which is the Independent Variable.
Difference between Control Group vs Experimental Group
Control Group = DOESN’T include the Independent variable
Experimental Group = INCLUDES the Independent Variable
What is the purpose of an experiment?
To determine if there’s a significant difference between the results in the Control and Experimental group.
When a difference between the Control and Experimental group is present…
There is a CORRELATION between the presence of the Independent Variable and an observed outcome.
Controlled Variables
Variables that remain the same in the experiment.
Why are controlled variables important?
They ensure that the only difference observed between the Control and Expeirmental group is the Independent Variable, rather than another variable.
Scientists want to measure whether exposure to second-hand smoke causes cancer in mice. They exposed one group of mice to a cage with filtered air, and the other group of mice to a cage with environmental tobacco smoke. What is an example of a Controlled Variable in this experiment?
The temperature of the cages that each group of mice were put into.
Hypothesis
A testable explanation for a set of observations and data.
Null hypothesis
A hypothesis stating that the Independent Variable has no impact on the Dependent Variable.
When should you accept the Null Hypothesis?
When X2 < critical value, or when the error bars overlap (no statistical difference).
Chisquare equation
X² = ∑ (((observed - expected)²) ÷ expected)
Alternative Hypothesis
A hypothesis stating that the Independent Variable does have ean impact on the Dependent Variable.
When should you accept the Alternative Hypothesis and reject the Null Hypothesis?
When X² > critical value OR when the error bars DON’T overlap (statistical difference is present).
