experimental designs Flashcards
independent groups
two separate groups of particpants experience two different conditions of the experiment
if there are two levels of the independent variable this means that all particpants experience one level of the IV only
performance of the two groups would then be compared
limitation of independent group design
issue
particpants who occupy the different groups are not the same in terms of participant variables
if a researcher finds the mean difference between the groups on the dependent variable this may be more to do with partipcnat variables than the effects of the IV
these differences may act as a confounding variable which reduces validity of the findings
to deal with his problem you could use random allocation
limiatation of independent group design
less economical than repeated measures
each particpants contributes a single result only
twice as many particpants would be needed to produce equivalent data to that collected in a repeated measures design
increases the time and money spent on recruiting particpants
strenght of independent group design
order effects are not a problem whereas they are a problem in repeated measures designs
particpants are also less likely to guess the aims
repeated measures
all particpants experience other conditions of the experiment
two would then be compared to see if there was a difference
limitation of using repeated measure
biggest issue
each partipcnat has to do two tasks
order of these tasks may be significant - order effects
to deal with this you can use counterbalancing
repeated two tasks could create boredom or fatigue and may abuse deterioration in the performance in the second task
performance may also improve in the second task due to the effects of practice
order acts as a confounding variable
limitation of repeated measures
particpants may work it the aim of the study when they exernce all conditions of the experiment
demand characteristics seem to feature in repeated measures
strenght of repeated measures
partipcnat variables are controlled so have higher validity
fewer particpants are needed so less time spent recruiting them
matched pairs
particpants are paired together on a variable or variables
one particpants from each pair would be allocated to a different condition of the experiment
this is an attempt to control for the confounding variable of particpants variable
strenght of using matched pairs
particpants only take part in a single condition so order effects and demand characteristics are less of a problem
limiataion
matching may be time consuming and expensive particularly if a pre test is required so it is less economical