research methods - 2 Flashcards
order effects
variables such as fatigue or practice effects, which affect the study if things are done in the same order
participants may become bored/tired of the study or may have done the same activity multiple times and may improve or discover the aim which will affect the findings
randomisation
making as many things within the research design and procedure as random as possible to reduce investigator effects/biases.
demand characteristics
participants not behaving naturally
instead they behave according to or against the aim
standardised procedure
a procedure that is carried out in a set way that is the same for everybody
e.g. every participant looks at the list of words for a minute.
participant variables
they are related to individual characteristics of each participant that may have an impact
e.g. mood, anxiety, awareness
what is meant by operationalising?
the process of making something measurable.
dependent variable
the variable you are measuring
double blind experiment
when the experimenter does not know the aims of the experiment and therefore can’t have any influence
situational variables
something to do with what is happening
e.g. time of day experiment is done
independent variable
the variable you change/manipulate.
extraneous variables
variables in the environment that have the potential to affect the findings of your study
e.g. noise in room
experimenter effects
when the experimenter being present affects the findings of the study
e.g. the tone of voice when giving instructions may indicate the answers needed
subjectivity
when analysing data that involves words there can be interpretation bias as you have to interpret what is being said in the data, which will be different for everyone.
what is meant by experimental design and what are the three types?
the allocation of participants for your study, whether you have one or more groups
1) repeated measures
2) independent groups
3) matched pairs design
repeated measures design
there is one group doing all conditions
independent groups design?
there are two separate groups in different experimental conditions.
matched pairs design?
there are two groups, but the groups are matched for something similar
e.g. age, personality
standard deviation
how close the scores are around the mean.
what does a small standard deviation show?
scores are clustered closely around the mean.
what does a large standard deviation show?
scores are spread out.
what is a sample?
who the participants are for the study.
e.g. age, race, background
what is meant by a research method?
the main way the data is collected in a study, such as using an experiment, a case study or a questionnaire.
predictive validity
to which the measure being used will allow you to predict future behaviours that this measure should be able to predict
e.g. when a student has good GCSE grades, we can predict that they will achieve good A-level grades.
what is meant by good predictive validity?
the data collected can be used to predict future behaviours.
objectivity
when analysing data there is no interpretation bias
this is the case when analysing quantitative data as they are factual findings.
what are the measures of central tendency?
the mean, median and mode of a set of scores.
measures of dispersion
range and standard deviation
how widely spread a set of scores are from the measures of central tendency
what is a hypothesis?
a prediction of what you think is going to happen in the results.
what are confounding variables?
variables that do affect the findings of your study
e.g. noise affecting your memory experiment
generalisibility
whether or not the sample is representative to the whole or target population.
does it represent a variety of people?
how big is the sample?
is the sampling technique creating a bias sample?
ethics
a set of guidelines psychologists have to follow to make sure participants are not harmed mentally or physically in the study
internal validity?
whether or not you are measuring what you claim to measure
involves isolating the variables to make sure the IV is affecting the DV so cause and effect can be established
ensuring results aren’t affected by extraneous variables.
ecological validity
whether or not the data represents a natural setting, if yes then it has high ecological validity
can the results be used to predict things about the participants future behaviour?
what is meant by application to real life?
whether or not the data/findings can be usefully applied to support a theory or to explain a real like phenomena or to improve quality of life or outcomes for society
reliability
whether or not the theory/study can be tested again and get the same results
if yes, it can be tested for reliability.
inter-rater reliability
whether or not there are multiple observers/researchers agreeing on behaviour
what is a lab experiment?
a study taking place in an artificial setting, using artificial tasks
very tight control over variables
collect quantitative data
aim to establish cause and effect
allows for future predictions
what is an aim?
the purpose of the study
It can be considered unethical to not tell participants your full aim
advantage of a lab experiment
high reliability as extraneous variables can be controlled tightly and procedures are standardised
high internal validity as there are no extraneous variables and there is lots of control.
limitation of a lab experiment
low ecological validity as it can be too controlled
(not real life setting)
what is a field experiment?
similar to lab experiments, but conducted in a more real life setting
e.g. public transport
aim is to establish a cause and effect relationship between IV and DV in a real life setting
participants are usually not aware they’re in the experiment.
what is an advantage of a field experiment?
high ecological validity as setting is more realistic and applicable and participants are in their normal environment, therefore behaviour is more realistic.
what is a limitation of a field experiment?
low internal validity as there is less control than lab experiments
extraneous variables are more likely to distort findings
harder to establish cause and effect relationship.
what is a natural experiment?
participants are in their natural everyday environment
experimenter has no control over variables.
what is an advantage of a natural experiment?
highest ecological validity due to lack of involvement of researcher
findings can be easily generalised to other real life settings
what is a limitation of a natural experiment?
experimenter has no control control over variables
low reliability as some events are rare and may only occur once
ethical issue that participants aren’t aware they are involved
low internal validity as little control over variables and can’t be sure of cause and effect
what is a quasi experiment?
when the researcher is interested in an independent variable that is naturally occurring and cannot be manipulated.
e.g. gender, age phobias
DV is measured in lab
what is an advantage of a quasi experiment?
high internal validity as can be in controlled conditions, control over extraneous variables
allows for cause and effect between IV and DV
reliability as there is high control and instructions and procedures are precise
what is a limitation of a quasi experiment?
no way to show casual relationship as there could be extraneous variables, therefore cannot show a casual relationship as there is no direct manipulation of IV.
the IV is naturally occurring.
what is a strength of independent group designs?
order effects aren’t a problem, participants are less likely to guess the aim
reduced chance of demand characteristics.
what are limitations of independent group designs?
individual differences
e.g. some people may all have good memory
economically lower as have to use 2x more participants than repeated measures design
how can we deal with individual differences during independent group designs?
make groups as random as possible
what are strengths of repeated measure design?
individual differences are not an issue
economically better as fewer participants are needed
what is a limitation of repeated measure design?
order effects
participants can find out aim through tasks
effect of first conditions can last through second e.g. eating chocolate to improve memory
how can we deal with the limitations of repeated measures design?
counterbalancing:
-Split participants
-Half complete A first and half complete B first
-Data will average itself out controlling for practice and fatigue
what are the strengths of matched pairs design?
no order effects as not repeating conditions
extraneous variables are more controlled because people are paired before joining one condition
what is a limitation of matched pairs design?
no two people will be the same, can’t match exactly
time consuming
expensive
how can we deal with the limitations of matched pairs design?
prioritise important variables to control
e.g. not having participants with brain damage for testing memory
what are the 5 ways we can present quantitative data?
bar chart
histogram
line graph
tables
scattergram
what do tables consist of?
raw data that hasn’t been statistically analysed
can have measures of central tendencies and dispersion.
what does a bar chart consist of?
represents discrete data, it has frequencies of each item.
it can show percentages, 2 values together
what does a histogram consist of?
continuous data
what does a line graph consist of?
continuous data
can compare 2 or more frequencies
when is a scatter graph used?
when conducting a correlation analysis
what is a correlation?
illustrates the strength and direction of an association between two or more co-variables
what does a positive correlation mean?
when one co-variable increases, so does the other
e.g. the number of people in a room and noise tend to be positively correlated
what does a negative correlation mean?
as one co-variable increases, the other decreases
what does a zero correlation mean?
there is no relationship between the two variables.
what is the difference between an experiment and a correlation?
in an experiment the researcher controls or manipulates the IV in order to measure the effect on the DV
as a result of this deliberate change in one variable it is possible to infer that the IV caused any observed changes in the DV.
for a correlation there is no manipulation of one variable and therefore it isn’t possible to establish a cause and effect relationship between one co-variable and another
what are the strengths of correlation?
useful preliminary tool for research
provides a precise, quantifiable measure of how two variables are related
relatively quick and economical to carry out
what are weaknesses of correlation?
can only tell us how variables are related, but not why.
can be occasionally misused
what is a correlational hypothesis?
there is no IV or DV
hypothesis has to state expected relationship between variables, but co-variables which must be operationalised
can be directional or non-directional
what is a null hypothesis?
no relationship between variables.
what is a directional hypotheses?
a one tailed hypotheses
what is a non-directional hypotheses?
a two tailed hypotheses
6 types of observation
natural
structured
overt
covert
participant
non participant
what is a natural observation?
watching behaviour in the participants natural setting
most observations are natural because natural behaviour is what is required.
no manipulation by researcher and nothing is set up
they can collect qualitative data or quantitative data
what are strengths of a natural observation?
have higher ecological validity as setting is natural
collect rich and in depth data, increases validity
what are weaknesses of a natural observation?
difficult to test for reliability because they have no controls
if data collected is qualitative then there may be interpretation bias of the findings
what is a structured observation?
watching behaviour in a controlled and artificial way e.g. using a one way mirror
situation can be repeated, no manipulation of IV
there is manipulation of setting and situation
can collect qualitative and quantitative data
what are strengths of a structured observation?
better reliability as it is controlled
situation can be recorded to refer back to, increases reliability