Chapter 4 (Unit 2) Flashcards
What is an experiment?
When a researcher imposes a treatment on experimental units and then measures their response.
What is an observational study?
When a researcher observes individuals and measures variables of interest but does not impose treatments.
What is a factor?
The explanatory variable in the experiment.
What are levels?
The different values of the factors.
What are treatments?
Specific conditions applied to the individuals.
What is a lurking variable?
It’s not part of the explanatory or response variables, but it may influence the response variables. It can affect the interpretation of the relationships between variables.
What is confounding?
When the variables’ effects on a response can’t be distinguished from each other.
- usually found in an observational study
- it affects the outcome (response variable)
*random assignment lessens the opportunity for confounding to occur*
What are experimental units?
The smallest collection of individuals to which a treatment is collected.
What are subjects?
Human experimental units.
What are the characteristics of a well designed experiment?
- randomization must occur
- replication must occur-the number of experimental units
- randomization- experimental units to treatments or treatments to experimental units
What is a completely randomized design?

What is the purpose of a control?
- keep extraneous variables as constant as possible
- have something to compare to
What is the purpose of random assignment?
- Using chances to assign experimental units to treatments
- Helps create roughly equivalent sized groups that may help to balance lurking variables that are not able to be controlled in the treatment group
What is the purpose of replication?
To have enough experimental units to distinguish a difference in the effects of the treatments from chance variation.
What is a placebo?
A fake treatment that keeps the subject from knowing if they are being treated.
What is the placebo effect?
When subjects get better because they expect the treatment to work even though the have recieved a placebo.
What does it mean to be single-blind?
When either the subject or the person assigning the treatment knows what’s going on (the other does not know).
What does it mean to be double-blind?
The person recieving the treatment or the person giving it does not know if the treatment is a placebo.
What does it mean to be statistically significant?
There was a substantial difference of outcome between the two groups (control vs treatment).
What is a block?
- A way to incorporate control into your experiment.
- The block must be of the same type-there must be a reason for the block.
- It is expected to affect the response of the treatment
- It is able to detect differences in the response variable to the treatments
- Some treatments are better for certain blocks
What does a randomized block design look like?

What is a matched pair design?
- A certain type of block
- Usually used with twins (matched pairs)
- only two treatment conditions
*closely matched right/left or pretest/posttest*
Scenarios
- Pain test for twins
- Lotion tests on hands
What are extraneous variables?
Extraneous variable are any variables that you are not intentionally studying in your experiment or test.