chapter 10 Flashcards
(32 cards)
one-way design
one in which only one independent variable is manipulated
The simplest one-way is the two-group experimental design
- Ex: does coffee increase short term memory? You can test the dosage effects on memory with four categories of IV (0 mg, 100mg, 200mg, 400mg)
Three types of one-way designs:
randomized groups design
matched subjects design
repeated measures (within-subjects) design
randomized groups design
participants are assigned randomly to one of two or more conditions
matched subjects design
participants are matched into blocks on the basis of a relevant third variable that may impact the DV
Matched participants are then randomly assigned from blocks to one of two or more conditions
repeated measures (within subjects) design
each participant serves in all experimental conditions
posttest only design
DV is measured only once after the experimental manipulation of the IV
Randomly assign individuals into two types of depression treatment (new drugs vs placebo) and test the participants at the end of the treatment using a depression scale to see if there are significant group differences
pretest-posttest design
DV is measured twice, both before and after the experimental manipulation
Randomly assign individuals into two groups then test them before (pre-test) and after (post-test) using the measures of DP (e.g, depression scale)
Advantages of Pretest-Posttest Designs
Can establish in the various experimental conditions did not differ on the DV at the beginning of the experiment (don’t leave it to the random assignment)
Can see how much (i.e., effect size) the IV changed participants’ behavior from pretest to posttest empirically with data gathered at the beginning and end of the study (more conclusive)
More powerful than post-only designs in detecting the effects of the independent variable
Disadvantages of Pretest-Posttest Designs
- pretest sensitization
- In experiments that are based on priming, pretest-posttest designs may not be necessary. In such circumstances, posttest-only designs provide enough information to determine whether the independent variable has an effect on the dependent variable.
- Demand characteristics
pretest sensitization
administering the pretest may lead participants to respond differently to the IV athan they would had they not been pretested
factors
Independent variables are referred to as factors
Factorial Designs
an experimental design in which two or more independent variables are manipulated
Two way design → 2 IVs
Three way design → 3 IVs
Factorial Nomenclature
We use special terms to describe the size and structure of factorial designs
A “2x2 factorial” (read “2-by-2”) – a design with two independent variables, each with two levels
A “3x3 factorial” – two independent variables and each V has three levels
A “2x2x4 factorial” – three independent variables and the first two variables have 2 levels, and the third variable has four levels
- Levels = conditions = groups = categories of IV
We can tell how many experimental conditions a factorial design has simply by multiplying the numbers in a design specification
Assigning Participants to Conditions in a Factorial Design
randomized groups factorial design
matched groups factorial design
repeated measures factorial design
randomized groups factorial design
participants are assigned randomly to one of the possible combinations of the independent variable
matched groups factorial design
participants are first matched into blocks on the basis of some variable that correlates with the dependent variable
- Participants in each block are then randomly assigned to one of the experimental conditions
repeated measures factorial design
each participant participates in every experimental condition
Factorial Design Example
Coffee effects on attention experiment
- First IV is dosage with four levels
- Second IV is brand (Starbucks vs Dunkin Donuts)
Factorial design with a 4x2 structure
Two sources of true variance in factorial designs
main effect
interaction effect
main effect
variance due to IVs; the effect of that independent variable while ignoring the effects of all other independent variables in the design
A factorial design will have as many main effects as there are independent variables
- In coffee experiment – two main effects
- Dosage effect – does the amount of coffee intake affect memory?
- Brand effect – does the brand of coffee affect memory?
interaction effect
variance due to interactions between the IVs
interaction
occurs when the effect of one independent variable differs across the levels of another independent variable (e.g., if the effect of A is different under one level of B than another level of B)
Ex: there is an interaction effect if the effect of variable A (coffee dosage) is different under one level of variable B (starbucks) than it is under another level of variable B (dunkin donuts)
Easier to examine on a graph
higher-order designs
Three-way designs examine:
The main effects of three independent variables
Three two-way interactions – the AxB interaction (ignoring C), the AxC interaction (ignoring B), the BxC interaction (ignoring A)
One three-way interaction of AxBxC
Mixed (Expericorr) Design
Factorial design can combine features of both randomized and repeated measures in an experiment
like a combination of experimental and quasi
participants are randomly assigned to only one level of some independent variable(s); also called a between-within design
- Involve both independent variables (that are manipulated) and subject variable (that are measured)
- E.g., randomly assign individuals into one of four dosage categories in our coffee experiment but then have each person taste both starbucks and dunkin donut coffee brands in a repeated design
