Experimental Design Flashcards
Independent (predictor or explanatory) variable
The cause
Variable that is controlled or changed in the experiment
Dependent (outcome or response) variable
The effect
Variable being tested and measured
Hypothesis
tentative answer to a well-framed question
Experimental Group
The group that receives the treatment in an experiment
Control Group
Identical to experimental treatments except for one independent variable
Provides a baseline that lets us see if the treatment has an effect
Experimental unit
Physical entity to which a treatment is randomly applied and on which an observation is made
Internal Validity
Extent to which you can be confident that a cause and effect relationship established in a study cannot be explained by other factors
Control groups help ensure the internal validity of the experiment
Confounding variable
Unmeasured variable that effects both the cause and effect
Sample size
The number of experimental units per group
Negative Control Group
Experiment group treated the same as all the other but not expected to change from any variable
5 keys steps in designing an experiment
Consider your variables and how they are related
Write a specific, testable hypothesis
Design experimental treatments to manipulate your independent variable
Plan how you will measure your dependent variable
Randomly assign subjects to groups (control and experimental)
Explain the difference between Independent and Dependent Variable
Independent can be changed
Dependent is the effect/response
Explain the difference between Control and Experimental Group
Experimental group - gets the treatment
Control group - provides a baseline for the experiment, and expected result
Explain the purpose of including a suitable control group in an experiment
Creates a baseline for the experiment, lets us know is our independent variable has an effect on the dependent variable
Explain the purpose of standardizing variables in an experiment
Determines if the response was caused by just the independent variables and not other factors (confounding variables)