pilot studies and correlations Flashcards
pilot study
- small scale trial run of the actual investigation
- before the real investigation is conducted
what do researchers test for in a pilot study
- check participants understood the instructions
- whether the materials are clear
- whether the questions are clear
- behavioural categories, timing of observations, where the observers are
- ethical issues
- timings
why do we do pilot studies
- allows us to check the investigation runs smoothly and removes any ambiguous/confusing elements
- allows the researcher to identify any issues and to modify the design, saving time and money in the long run
correlation definition
a mathematical technique in which a researcher investigates a relationship between 2 co-variables
strengths of correlations
- less time-consuming and economical as there is no need for a controlled environment or manipulation of variables
- useful preliminary tool for research as they provide a quantifiable measure of how 2 variables are related which can suggest ideas for future research
- they can be used as starting points to assess possible patterns before researchers commit to a study
- correlations can be done when it is unethical/impractical to manipulate the variables
- if a correlation is not significant, a causal relationship is ruled out
- if a correlation is significant, further investigation can be justified
weaknesses of correlations
- lack of experimental manipulation and control so it doesn’t tell us why the variables are related
- it doesn’t demonstrate cause and effect between variables therefore we do not know which variable is causing the other to change
- may be another untested variable that is causing the relation between the two (intervening variable)
- people often misinterpret correlations as a cause and effect relationship
- may lack validity e.g. not generalisable
positive correlation
as 1 co-variable increases, so does the other
negative correlation
as 1 co-variable increases, the other decreases
zero correlation
when there is no relationship between the co-variables
co-variables
the variables investigated in a correlation. They are not referred to as the IV and DV because a correlation investigates the association between the variables rather than a cause and effect relationship
curvilinear relationships
some relationships are more complex than positive or negative. Performance may be at its best when there is a moderate level of arousal and will deteriorate if arousal level is too low or high
correlation coefficients
a number between -1 and +1 that tell us the strength and direction of the relationship between the 2 co-variables
coefficient rules
- 0.8 and above = strong correlation
- Around 0.5-0.79 = moderate correlation
- Around 0.3 = weak correlation
- Near 0 = zero correlation
any result above 0.8 is significant