Exam 2 3/3/25 Flashcards
design confound
an experimenters mistake in designing the independent variable such that a second variable happens to vary systematically with the intended independent variable
systematic vs unsystematic variability
There will always be some variation across participants in a study. A variable is only a confound when its levels vary systematically across levels of your independent variable
Does watching an adult exert effort increase a baby’s persistence? How do we operationalize “exert effort”?
the number of attempts made to get a toy out of the box
kinds of experiments (3 kids)
independent group designs vs within groups
Different participants at different levels of the IV
The same participants experience all levels of the IV
posttest only vs pretest/posttest
The dependent variable is measured once after the manipulation of IV
The dependent variable measured before and after manipulation of IV
concurrent vs repeated
All levels of the IV experienced at once
Levels of IV experienced sequentially
potential problems with independent group design
why is pretest/posttest useful?
you have a baseline score for each person and see if the IV had an improvement on scores, which ensures there were no selection effects
which is better, posttest only or pretest/postest?
In some situations, it is problematic to use a pretest/posttest design.
* e.g., if DV will cause fatigue
* e.g., if exposure to the DV causes familiarity effects
In other situations, it makes sense.
* e.g., measuring GRE scores before and after intervention
posttest-only designs can still be very powerful
* random assignment and manipulation of IV
within groups design benefits
eliminating confounds/no selection effects
unsystematic variability is less of a problem since each participant is being compared to itself
statistical power increased the ability to detect difference between conditions
need fewer participants: the same amount of data with half the number of participants
2 types of within-group designs
repeated measures design: participants are exposed to one level of the IV and tested on the DV consecutively (one after the other)
concurrent measures design: participants are exposed to the different levels simultaneously and then tested on the DV
order effects
Exposure to one level of the IV can influence responses to subsequent levels of the IV. A confound because differences in DV may be explained by the sequence in which the levels were experienced.
practice effects/fatigue effects
A type of order effect. Participants may get better as the task continues or get tired or bored toward the end
carryover effects
A type of order effect. some form of contamination carries over from one condition to the next
counterbalancing
used to avoid order effects
full counterbalancing
all orders/combinations used
partial counterbalancing
not all orders are tested
problems with within groups design
havent ruled out confounds like order effects, might not be practical or possible, demand characteristics (participants act in different ways based on the knowledge of the IV
