Issues in research methods 2 Flashcards
(21 cards)
What is a spurious correlation?
When two items appear to be related but the relationship is not causal or meaningful
If variable A causes variable B, what does this imply?
Change in A is associated with change in B
Change in A reliably precedes change in B
Without change in A, change in B does not occur (if A is the sole cause of B)
What is an extraneous variable?
Anything other than the IV that could affect the DV
What is a confounding variable?
A type of variable that not only affects the DV but also varies with IV systematically - uncontrolled and obscures causal effect
What is an effect size?
Statistical measure of the magnitude of an observed effect in a population
What is internal validity?
The extent to which we can be sure that the changes we observe have actually been caused by our manipulation, rather than other factors.
What is the notation for pre-test?
O1 (observation 1)
What is the notation for experimental treatment?
X
What is the notation for post-test?
O2 (obervation 2)
What are maturation effects?
Maturation effects: participants behaviour changes over time naturally (i.e. nothing to do with the treatment/intervention)
What are history effects?
something changes about the participants circumstances that influences the variables (e.g. good/bad life events, cultural events etc.)
What are testing effects?
merely having been tested before may have changed how they do on the post-test
What is regression towards the mean?
an extreme score is likely to become more average
What are selection effects?
participants are selected because of their extremity (or peculiarity) on the variable of interest - any change can only be an improvement
What is a passive control group?
participants are selected because of their extremity (or peculiarity) on the variable of interest
What is an active control group?
participants are selected because of their extremity (or peculiarity) on the variable of interest
What is a wait list control group?
participants are selected because of their extremity (or peculiarity) on the variable of interest
What are 3 ways to eliminate confounds due to ppt characteristics?
Within-ppt design
Random assignment
Matched pairs design
What are 3 ways of eliminate confounds due to experimenters or procedures?
- ensure conditions are as similar as possible except for manipulations
- standardise procedures
- randomisation of order of conditions
What is differential attrition?
when people leave one condition or treatment more than any other (also known as drop-out rates) - the data becomes biased to those who complete it.
What type of design is differential attrition most important in?
Longitudinal
