Methodological Control in Experimental Research Flashcards
Any independent variable must have a minimum of two levels. This means at the very least…
an experiment will compare level A with level B
If participants receive either A or B but not both, the design is a…
between-subjects design
If participants receive both levels A and B, the design is a….
within-subjects design OR sometimes called a repeated-measures design
If the independent variable is a subject variable there is no choice but to use what type of design?
Between-subjects design
What is the goal of random assignment?
To take individual difference factors that could influence the study and spread them evenly throughout the different groups
When there is only a small number of participants, random assignment can fail to create equivalent groups. When this is the case researchers use a technique called _________
matching
What is an advantage of a within-subjects design?
Fewer participants need to be recruited
Sequence or order effect in a within-subjects design
Once a participant has completed the first part of a study the experience or altered circumstances could influence performance in later parts of the study
How do researchers control order effects in a within-subjects design?
Counterbalancing
Cross-sectional and longitudinal research use _____ as the primary independent variable
age
Cross sectional studies take a ________ -subjects approach
between
Longitudinal studies take a ______ - subjects approach
within
What is a problem associated with cross-sectional studies?
Cohort effect - when a commonly aged group of people in research indirectly affect results due to their common age-related influences
What is a problem associated with longitudinal studies?
Attrition
In trying to balance cohort and attrition problems, researchers use a strategy that combines cross sectional with longitudinal studies. One such design is called a….
cohort sequential design
How to control for experimenter bias?
Research protocols, double blind procedure
How to control for participant bias?
Reduce demand characteristics (i.e., deception), placebo control group, single-blind, conduct field research
What is a disadvantage of a between-subjects design?
Large number of people may need to be recruited
Blocked random assignment
Researcher randomly divides participants into blocks so that variability within the blocks is less than variability between blocks. Participants within each block are randomly assigned to treatment conditions.
Progressive effect
A sequence/ order effect in which performance changes steadily from trial to trial
Carry-over effect
A sequence/ order effect in which some sequences may produce effects different from other sequences
Why does counterbalancing work better for progressive effects than for carry-over effects?
Because it is a strategy to control order effects. Even if you control for order effects, carry-over effects will still most likely occur
Two types of counterbalancing for when participants are tested once per condition
- Complete counterbalancing
2. Partial counterbalancing
Complete counterbalancing
Every possible sequence will be used at least once.
Ex; If a study has three conditions, then there are six possible sequences. Participants would be assigned to one of the six sequences.
