Research methods Year 1 Flashcards
what is a laboratory experiment
conducted in a highly controlled environment
not necessarily a lab
What are the different types of experiments/experimental methods
laboratory
field
natural
quasi
Strengths of laboratory experiments
Control of confounding and extraneous variables
high internal validity
replication is easier
Limitations of laboratory experiments
Lack generalisability (artificial)
low external validity
demand characteristics
What is a field experiment
IV is manipulated in a natural more everyday setting
set in participants normal environment
Strengths of field experiments
high external validity
higher mundane realism
Limitations of field experiments
less control of confounding and extraneous variable
replication is harder
ethical issues if Ps are not aware they are being studied
What is a natural experiment
researcher has no control over the IV e.g. before and after a natural disaster or if a child was in hospital age 5-10
strengths of a natural experiment
provide opportunity for research that could not have been done for practical or ethical reasons e.g. orphan studies
high external validity
Limitations of natural experiments
Ps are not randomly allocated to conditions so may have confounding variables
may have limited generalisability if event happens rarely
as IV is not manipulated by researcher cause cannot be established
What is a quasi-experiment
IV is based off an existing difference between people e.g. age and gender
strength of quasi-experiments
soften carried out under controlled conditions so have same strengths as lab experiments
Limitations of quasi-experiments
cannot randomly allocate Ps to conditions so may have confounding variables
as IV is not manipulated on purpose cause cannot be established
what are the types of observations
naturalistic
controlled
covert
overt
participant
non-participant
what is a naturalistic observation
take place in the setting where the target behaviour would naturally occur
what is a controlled observation
some control over variables such as manipulating variables to observe effect and to control confounding/extraneous variables
what is a covert observation
participants are unaware they are the focus of a study and that they are being observed
what is an overt observation
participants know their behaviour is being observed and have given consent beforehand
what is a participant observation
the observer is part of the group they are studying
what is a non-participant experiment
researcher remains separate from the people they are studying
what are the self-report techniques
questionnaires
interviews
what are open questions
does not have a fixed range of answers
Ps are free to answer in any way they want
tend to produce qualitative data
what is a questionnaire
pre-set list of written questions for a participant to respond to
types of questions in questionnaires
open
closed
what are closed questions
have a fixed range of answers
tend to produce quantitative data
what is a structured interview
pre-determined set of questions that are asked in a fixed order
What are the types of interviews
structured
unstructured
what is an unstructured interview
no set questions
general aim of the topic to be discussed
free-flowing and more conversation like
strengths of questionnaires
cost effective as gathers a lot of data quickly when sent to lots of people
less effort as researcher does not have to be present
Limitations of questionnaires
social desirability bias means people le to present themselves in a positive light
response bias e.g. always ticking yes (acquiescence bias) of answering at one end of a scale
Strengths of structured interviews
easy to replicate
reduces differences between interviewers
limitations of structured interviews
interviewers cannot deviate from questions or explain the questions limiting richness of data
strengths of unstructured interviews
more flexibility to follow up points
gain more insight into interviewee
unexpected information
limitations of unstructured interviews
interviewer bias
data analysis is difficult as much of the info is irrelevant
What is a correlation
illustrates the strength and direction of an association between 2 or more co-variables
How are correlations plotted
scattergrams
what is the difference between correlations and experiments
experiments the researcher controls or manipulates the independent variable to measure the effect on the dependent variable - causation can be established
correlations the IV is not being manipulated and cause and effect cannot be established
What is an aim
statement of what the researchers intended to find out in a research study
what is a hypothesis
precise testable statement about the relationship between variables
must be operationalised
what is a directional hypothesis
only when there is previous data on the subject
states the direction of the predicted difference between to conditions or groups
What is a non-directional hypothesis
when there is no previous research on the topic
predicts that there is simply as difference between two conditions or groups without stating the direction of the difference
difference between population and sample
population is the large group of people that a researcher is interested in studying
sample is a small representative group from the target population to generalise from
What is random sampling
lottery technique used to select from list of every member of population e.g. draw names from hat
What is a systematic sample
selecting every nth person e.g. every 5th person in a register
what is stratified sampling
produced by identifying subgroups according to their frequency in the population
Ps in subgroups are selected randomly
what is volunteer sampling
study is advertised e.g. in newspaper or internet
people volunteer to be studied
what is opportunity sampling
people are selected who are most easily available at the time of the study
opportunity sample strengths
easy
less time consuming
opportunity sample limitations
biased as drawn from small part of population who may all have something in common that means they are available
random sampling strengths
unbiassed
all members of population have equal chance of being selected
random sampling limitations
need to have list of all members then contact those selected which is time consuming
people selected may not say yes
stratified sampling strengths
more representative
unbiassed
stratified sampling limitation
very time consuming to identify strata then randomly select people and contact them
those contacted may not want to participate
systematic sampling strengths
unbiassed as system is objective
systematic sampling limitations
not truly unbiassed unless start person is selected randomly
volunteer sample strengths
access to variety of people e.g. everyone who reads the newspaper which may make a representative and less biassed sample
volunteer sample limitations
biased as people are likely to be motivated or those with time on their hands, may be in need or money this results in volunteer bias
what is a pilot study
a small-scale trial run of a study to test any aspects of the design with a view to make improvements
what are the types of experimental design
repeated measures
independent groups
matched pairs
what is repeated measures design
each participant takes part in every level of the independent variable
limitation of repeated measures
order effects e.g. may do better in second condition because of practice or worse because of fatigue
more likely to guess the purpose of the experiment which may affect behaviour
how to deal with limitations of repeated measures
counterbalancing overcomes order effects
1 groups will do conditions A then B
1 group will do conditions B then A
What is an independent groups design
participants are allocated to groups
each group does a different level of the IV
limitations of independent groups
participant variables cannot be controlled and they may act as confounding variables
more participants are needed
how to overcome limitations of independent groups
random allocation to groups distributes participant variables evenly theoretically
what is a matched pairs design
pairs of participants are matched in terms of key variables that will effect results
the member of each pair are allocated to different IV conditions
limitations of matched pairs
time consuming and difficult to match Ps
not all participant variables can be controlled
how to overcome limitations of matched pairs
match on less variables to make it easier
conduct pilot study to find variables to consider matching
what is needed to design an observation
behavioural categories
type of sampling
types of sampling in observations
event sampling
time sampling
what is event sampling
counting the number of times a certain behaviour occurs
what is time sampling
recording behaviours in a given time frame e.g. what is the participant doing every 15 seconds
how to determine behavioural categories in observations
must be objective
must cover all possible component behaviours
must be mutually exclusive
how to write good questionnaire questions
make sure questions have clarity
don’t use biassed questions (leading questions)
use questions that can be easily analysed (mainly closed questions)
how to write a good questionnaire
use filler questions to reduce demand characteristics
questions sequence - start with easy questions so by the hard questions the P has relaxed
pilot study to test and refine questions
sampling technique for respondent
how to design an interview
record the interview
think about the effect of the interviewer
think about questioning skills in an unstructured interview
why record an interview
so interviewer can pay attention to listening instead of taking notes
what is the effect of an interviewer
interested interviewer may increase the amount of information provided by P
to display interest think of non-verbal communication and knowing when to speak/not interupting
what questioning skills are needed in an unstructured interview
what kind of follow up questions to ask
avoid repeating questions
avoid probing
ask focused questions
open questions strengths
Ps can expand on their answer - more detail and information collected
provide unexpected answers which can provide insight
open questions limitations
most Ps avoid giving long complex answers so may not provide extra information
produce qualitative data which is hard to summarise and draw conclusions from
closed questions strengths
limited range of answers which produces quantitative data
answers are easier to analyse and draw conclusions from
closed questions limitations
P may be forced to select from answers that don’t represent their real thoughts - data lacks validity
Ps may say don’t know or have a preference to say yes (acquiescence bias) - data is not informative
what is the dependent variable
what is being measured
what is the independent variable
the variable that is directly manipulated by the researcher to tests its effect on the dependent variable
what is operationalising
ensuring that variables are in a form that can be easily tested e.g. intelligence may be operationalised as IQ score
what is control of a variable
the extent to which any variable is held constant or regulated by a researcher
what is an extraneous variable
don not vary systematically with the IV so do not act as an alternate IV but may have an effect on the DV
make it more difficult to detect a significant effect
what is a confounding variable
a variable that is not the IV but varies systematically with the IV
changes in the DV may be due to the confounding variable rather than the IV so the outcome is meaningless
what is standardisations
ensuring that all participants receives the same set of procedures so the study can be repeated
what are demand characteristics
when participants become aware of the aims of the study which may make them behave in a different way
what are investigator effects
anything an investigator does that has an effect of the Ps performance other than what was intended
may act as a confounding or extraneous variable
how to reduce demand characteristics
single blind design
what is a single blind design
the participant is not aware of the research aims and/or which conditions of the experiment they are receiving
how to reduce investigator effects
double blind design
what is a double blind design
the participator and the person conducting the experiment do not know the aims and/or hypothesis
What is the role of the British Psychological society code of ethics
includes a set of ethical guidelines
researchers have a professional duty to observe these guidelines when conducting research
guidelines are implemented by ethics committees in research institutions
what are the 6 ethical issues
informed consent
deception
right to withdraw
protection from harm
confidentiality
privacy
what is confidentiality
concerns the communication of personal information from one person to another and the trust that the information will be protected
what is deception
when a participant is not told the true aims of a study and thus cannot truly give informed consent
what is informed consent
participants must be
given a comprehensive information concerning the nature and purpose of the research and their role in it to make an informed decisions as to whether or not to participate
what is privacy
a persons right to control the flow of information about themselves
what is protection from harm
during research participants should not experience negative physical or psychological effects
what is the right to withdraw
participants can stop participating in a study at any time if they are uncomfortable in any way
participants have the right to refuse permissions for the researcher to use any of the data they produced
how to deal with informed consent
participants should be given a consent letter detailing all relevant information that might affect their decision to participate
parental consent is required for Ps under 16
how to deal with deception and prevention from harm
at the end of a study Ps should be given a full debrief to be made aware of the true aims of the study and any details not supplied with during the study e.g. other groups
Ps should be tole what their data will be used for and that they have the right to withdraw their data
in extreme cases counselling may be given
how to deal with confidentiality
maintain anonymity using participant numbers or initials
reminded in debriefing that their data will be protected and not shared
alternative ways of getting consent
presumptive consent
prior general consent
retrospective consent
what is presumptive consent
similar group of people to the Ps are asked if they would give consent
what is prior general consent
Ps give permission to take part in a number of studies including one that will involve deception - consenting to be deceived
what is retrospective consent
Ps are asked for consent in the debriefing after already taking part in the study
what is the role of peer review
establishing validity and accuracy of research
ensure any research published is of high quality
main aims of peer review
allocate research funding
validate the quality, accuracy and relevance of the research
suggest amendments or improvements
preventing inaccurate or false data from entering the public domain
how is peer review carried out
a panel of independent experts scrutinise all aspects of the written investigation
problems with peer review
publication bias
preserving the status quo
anonymity of reviewers
what is publication bias
journals tend to prefer to publish positive results which can result in misperception of the true facts
journals also avoid publishing replications which are important for validity
what is preserving the status quo
there is a preference for research that goes with existing theories rather than dissenting
what is the problem with anonymity of reviewers
reviewers may use the anonymity to bury opposing research to their own or settle rivalries
3 implications of psychological research for the economy
role of the father - mother can go back to work
treatment of mental disorders - less absence from work for mental disorders
improving eyewitness testimony - less money spent on wrongful conviction
what is randomisation
use of chance methods to reduce researchers unconscious bias in designing an experiment e.g. random order of words in a memory test or using a randomiser to determine which order Ps do IV conditions in
what is qualitative data
information in words that cannot be counted or quantified
what is quantitative data
information that can be represented in numbers and can be measured
how is qualitative data collected
data is observed not measured
observes people through the messages they produce and the way they act
concerned with beliefs attitudes and emotions
how is quantitative data collected
data is measured
psychologists develop measures of psychological variables
quantitative data strengths
easy to analyse using descriptive and inferential statistics
conclusions easily drawn
quantitative data limitations
may oversimplify reality so conclusions may be meaningless
qualitative data strengths
rich detailed information
unexpected insight
qualitative data limitations
much more difficult to analyse and draw conclusions from
what is primary data
information observed or collected directly from first hand experience
what is secondary data
information used in a research study that was collected by someone else or for a purpose other than the current one
primary data strengths
researcher has control over the data
data collection designed to fit the aims of the study
primary data limitations
very lengthy and expensive process
secondary data strengths
simpler and cheaper to use someone else’s data and takes less time
data may have been subject to statistical tests so it is already known whether it is significant
secondary data limitations
the data may not exactly fit the needs of the study
what is a meta-analysis
a number of studies are identified that have investigated the same aims/hypotheses
results of these studies are poled to produce a joint conclusion or statistic to represent the overall effect
meta-analysis strengths
reviewing from more than one study can increase the validity of the conclusions as it is a wider sample of Ps
often studies produce different results meta-analysis allows an overall conclusion
meta-analysis limitations
research design in the studies may vary so studies are not comparable
what are descriptive statistics
mean
median
mode
range
standard deviation
what are measures of central tendency
provide information about a typical value for a data set
mean
median
mode
what are measures of dispersion
provide information about how spread out a set of data is
range
standard deviation
when to use the mean
interval level data
when to use the median
interval and ordinal level data
when to use the mode
nominal, ordinal and interval level data
what is a positive correlation
the two variables increase together
what is a negative correlation
as one variable increase the other decreases
what is a zero correlation
there is not relationship between the variables
when to use a table
raw data before descriptive statistics have been carried out
when to use a bar chart
non-continuous data
nominal data
when to use a histogram
continuous data in categories
when to use a line graph
continuous data
when to use a scattergram
correlations
what is normal distribution
a symmetrical bell shaped frequency distribution
most of the scores are clustered close to the mean median and mode
the mean median and mode are at the mid-point
what is positive skewed distribution
most of the scores are to the left
the mode is to the left of the mean as the mean is effected by extreme scores to the right
what is negative skewed distribution
most of the scores are bunched towards the right
the mode is to the right of the mean as the mean is effected by extreme scores to the left