Research methods

Created by

Maddie Jones

Cards (131)

types of experimental design
-independent groups
-repeated measures
-matched pairs
what is a repeated measures design 
same Ps do both conditions
what is a matched pairs design
pairs of matched Ps split into 2 groups and do one condition each
what is an independent groups design 
separate groups of Ps do each condition
evaluation of matched pairs
-reduces participant variables and order effects
-more Ps = more time to find similar people and individual differences may still play a part as it's very difficult to find exact copies
evaluation of independent groups
-avoids order effects = reduces demand characteristics = higher validity
-more expensive and time consuming b/c more Ps are required
-P variables may affect results so researchers cant be sure that the IV caused the change
evaluation of repeated measures
-fewer Ps = less costly and time consuming
-same Ps = less possibility of participant variables like individual differences
-order effects may occur b/c they may know what is expected of them by the 2nd condition
-demand characteristics
what is a hypothesis 
clear and precise prediction about difference or relationship between IV and DV in the study
what is operationalisation 
variable is clearly defined by researcher. can be applied to IV, DV or co-variables
what are the two types of hypothesis
-directional
-non-directional
what is a directional hypothesis 
predicts the direction of the difference between the 2+ variables
what is a non-directional hypothesis 
predicts that there will be a difference but not the direction of the difference
what is counterbalancing 
sample for repeated measures design is split in 2 and one group does one condition while the other group does the other to combat order effects
what is validity 
how accurate/legitimate a test is at testing the aim
what are the two types of validity
-internal
-external
what is external validity
how well it can be generalised to outside situations e.g. temporal and ecological
what is internal validity 
are the changes solely due to the IV in cause + effect relationship
what is ecological validity 
can findings be applied to other settings like everyday life
what is temporal validity 
can findings be applied across time
how can validity be assessed
-face validity
-concurrent validity
what is face validity 
does it appear to measure what it says. Tested by specialists who say if they think it is valid or not
what is concurrent validity
does results match up with recognised and trusted tests
how can validity be improved in experiments
-control groups
-single blind/double blind
-standardised instructions
what is a single blind/double blind procedure
Ps don't know what condition they are in or Ps and researcher don't know what condition they're in. Conditions don't lead to demand characteristics or investigator effects
what are standardised instructions 
clear, simple instructions that are the same and in the same format - reduce investigator effects and Ps are less likely to interpret differently
how can validity be improved in questionnaires
-lie scale
-anonymity
what is a lie scale 
wording same questions differently to see if their responses match up
how can validity be improved in observations
-covert observation
-behavioural categories
-qualitative methodology
what is qualitative methodology 
more in depth data collected. can be more subjective which means that validity is decreased. variety of sources
what is qualitative data 
non-numerical, language based data expressed in words
what are evaluative points for qualitative data
-rich detail = enhanced external validity
-subjective, interpretations of data can rely on opinions and judgements of researcher
what is quantitative data
numerical data, can be statistically analysed and easily converted into graphical format
what are evaluative points for quantitative data
-easy to statistically analyse = more objective
-lack of representativeness = lacks validity
what are ways of displaying quantitative data
-tables
-scattergraph
-bar chart
-histograms
what are ways of measuring central tendency
-mean
-median
-mode
what are ways of measuring dispersion
-range
-standard deviation
evaluation of mean 
-most representative
-most sensitive
-only for ordinal/interval data
evaluation of median 
-extreme scores don't affect results
-doesn't reflect all scores
evaluation of mode 
-extreme scores dont effect
-not always useful for central tendency, can be more than 1
evaluation of range 
-easy to calculate
-doesn't indicate distribution pattern across whole data set