research methods (yr12) Flashcards
what are the 3 types of hypothesis?
directional
non directional
null
what is a directional hypothesis?
makes a precise prediction of the exact direction results are expected to go in
what is a non directional hypothesis?
makes a cautious prediction and states a change but not the direction of that change
what is a null hypothesis?
predicts that there will be no change or relationship/it does the opposite of the experimental design
what are extraneous variables?
give an example
variables that affect ALL pps involved e.g time of day
what are confounding variables?
give an example
variables that affect SOME of the pps involved e.g hungry
what are the 3 types of experiment?
lab
field
natural
strengths of a lab experiment (3)
- high level of control of both the IV and EV
- easy to replicate
- can conclude cause and effect
weaknesses of a lab experiment (3)
- lack ecological validity
- high chance of investigator and participant effect
- lack mundane realism
strengths of a field experiment (3)
- can conclude cause and effect
- higher level of ecological validity
- reduction in participant effects e.g demand characteristics
weaknesses of a field experiment (3)
- less control due to more natural setting
- more time consuming
- random allocations to conditions is difficult
a strength of a natural experiment
- high levels of ecological validity - can generalise findings
weaknesses of a natural experiment (3)
- cannot conclude cause and effect - problems with internal validity
- no random allocations to conditions
- conditions vary naturally
what is a case study?
gathering of information about an individual or group of people that typically involves the production of a case history
strengths of a case study (4)
- produce rich data (qualitative)
- high levels of ecological validity - generalise findings
- can be used to investigate rare human behaviour
- lead to new psychological insights
weaknesses of a case study (5)
- difficult to replicate - hard to establish reliability of data
- possibility of researcher bias is high
- retrospective data collection is unreliable
- ethical issues e.g confidentiality
- low population validity
strengths of correlational studies (4)
- can establish a relationship between 2 variables
- procedures can be repeated to confirm findings
- can stimulate areas for additional research
- can be used when it would be unethical or impractical to manipulate variables
what are the 2 types of self report methods?
what is a common research method?
questionnaires and interviews
diary studies
strengths of self report methods (2)
- research pps don’t have to recollect exact details from past events so less likely to experience recall problems
- use diary entries as a starting point for understanding of behaviour
weaknesses of self report methods (2)
- data may be untruthful and subject to social desirability bias
- diaries are problematic - pps may not want to record their daily activities
strengths of questionnaires (3)
- researchers don’t have to be present - reduction in investigator effects
- collect the same information from large samples quickly and conveniently
- ask people directly how they think and feel
weaknesses of questionnaires (3)
- social desirability
- sample may be bias as only certain individuals fill in questionnaires
- may obtain different interpretations of questions
what are the 2 types of interviews?
structured and semi structured
what is a structured interview?
questions have exactly the same wording and order for each interviewee
what is a semi structured interview?
same questions for each interviewee but the order may vary
strengths of structured interviews (3)
- easily repeated as questions are standardised
- requires less interviewing skills
- easier to analyse because answers are more predictable
weaknesses of structured interviews (2)
- interviewer bias - interviewer’s expectations may influence answers
- reliability may be affected by the same interviewer behaving differently on different occasions
strengths of semi structured interviews (2)
- more detailed information
- can access information that may not be revealed by predetermined questions
weaknesses of semi structured interviews (2)
- less objective as the interviewer develops questions on the spot
- requires well trained interviewers - more expensive to produce reliable results
what are the 4 types of observations?
naturalistic
controlled
participant
non - participant
advantages of naturalistic (2)
- natural behaviour is observed
- high in ecological validity
disadvantages of naturalistic (3)
- little control over confounding variables
- less reliable
- less representative (smaller sample)
advantages of controlled (3)
- easily replicated
- quicker and easier to analyse - bigger sample
- control over confounding variables
disadvantages of controlled (2)
- behaviour may not be natural/normal
- low ecological validity
advantages of participant (2)
- easier to understand observee’s behaviour
- high in ecological validity
disadvantages of participant (2)
- hard to record observations - often done retrospectively so unreliable
- observer can become involved with pps and data can be subjected
advantages of non-participant (2)
- observations can be made as they happen and are more reliable
- lack of contact means the observer can remain objective
disadvantage of non-participant
behaviour may be recorded but the meaning behind it is unknown
what is an example of a controlled and non-participant observation?
Bandura’s Bobo doll research
what are the 3 locations of research?
lab
field
online
advantages of lab research (3)
- measure research variables more easily
- control confounding or extraneous variables
- easy to replicate research
disadvantages of lab research (2)
- pps may demonstrate artificial behaviour - low ecological validity
- some research can’t be conducted in a lab because of the nature of the behaviour being researched
advantages of field research (3)
- behaviour is more natural
- useful if you want to minimise the artificial nature of research
- examine behaviour in a huge range of contexts - difficult in a lab
disadvantages of field research (3)
- difficult to control confounding or extraneous variables
- can’t replicate research due to the difference in settings
- can’t utilise a full complement of equipment
advantages of online research (4)
- access a large group of pps
- more diverse sample so less culturally bias
- cost effective
- data analysis is quicker as pps have already transcribed their responses
disadvantages of online research (3)
- limited as most are surveys or questionnaires
- ethical issues such as consent and protection from harm
- difficult to appropriately debrief pps
what are the 3 types of experimental design?
repeated measures
independent groups
matched pairs
what is repeated measures?
the same pps in each condition
what are independent groups?
different pps in each condition
what are matched pairs?
different but similar pps in each condition
strengths of repeated measures (3)
- subject variables - extraneous variables are kept constant
- better statistical tests can be used because of less variation
- fewer subjects required
weaknesses of repeated measures (3)
- order effects become constant when one condition is done after another
- demand characteristics
- different tests may be needed
strengths of independent groups (3)
- order effects do not influence second condition
- demand characteristics are limited
- same test can be used
weaknesses of independent groups (3)
- subject variables differ which could become confounding variables
- worse statistical tests as less variation
- more subjects required - less economical
strengths of matched pairs (5)
- subject variables are more constant
- better statistical test as less variation
- order effects do not occur
- demand characteristics are limited
- same test can be used
weaknesses of matched pairs (3)
- subject variables can never perfectly be matched
- time consuming and difficult
- more subjects required - less economical
what is counterbalancing?
method we can use to minimise the impact of order effects with a repeated measures design
what are the 7 sampling techniques?
random
opportunity
systematic
stratified
quota
volunteer
snowball
what is random sampling?
every participant within the target population has an equal chance at selection. numbers or names are ‘draw out of a hat’ and ideally shuffled in between each selection
strength of random sampling
random sampling in large numbers is the best chance of an unbiased representative sample of a target population
weaknesses of random sampling (2)
- the larger the target population the more difficult it is to sample randomly
- true random sampling is very time consuming therefore very rare
what is opportunity sampling?
using those who are most convenient or most available to you
strength of opportunity sampling
the easiest most economical method of sampling - takes less time to locate sample
weakness of opportunity sampling
inevitably produces a biased sample - drawn from a small part of a target population
what is systematic sampling?
using a pre-determined system to select pps. the numerical interval is applied consistently (select every nth___)
strength of systematic sampling
reduces the level of bias in the sample as pps are selected using an objective system
weakness of systematic sampling
not truly unbiased/random unless you select a number using a random method
what is stratified sampling?
sub-groups within a target population are identified. pps are obtained from each sub-group in proportion to their occurrence in the target population
strength of stratified sampling
likely to produce a highly representative sample compared to other methods
weakness of stratified sampling
uneconomical method - very time consuming
what is quota sampling?
same as stratified sampling but for a quote sample this selection is made using non random techniques
strength of quota sampling
likely to produce a highly representative sample compared to other methods
weakness of quota sampling
uneconomical method - very time consuming
what is volunteer sampling?
using advertisements/leaflets, posters, radio etc to announce the research and request volunteers for the sample
strengths of volunteer sampling (2)
- relatively convenient, informed consent - ethical
- gives a variety of pps which makes it less bias and more representative
weakness of volunteer sampling
may systematically bias the sample in a particular direction
what is snowball sampling?
start off with a small number of pps. these recruit further pps from their social network and the sample grows gradually over time
strength of snowball sampling
enables a researcher to locate groups of people who may be difficult to access
weakness of snowball sampling
likely to be a bias sample and not be a good cross section from the population - made of friends and family
what are the 9 ethical issues?
deception
valid consent
protection from harm
confidentiality
privacy
right to withdraw
risk to the pp’s values, relationships, status or privacy
working with vulnerable individuals
working with animals
what is internal reliability?
give an example for Milgram’s study
a measure of the extent to which something is consistent within itself
standardised procedures - scripted prods recorded ‘learner’s’ reactions
what method do you use to assess internal reliability?
what is it?
split half method
splitting the test or questionnaire concerned into 2 parts after data has been obtained from the pps e.g comparing results obtained from odd and even numbered questions
how can we improve internal reliability?
using standardised procedures so all pps have the same experiences as one another
what is external reliability?
give an example for Milgram’s study
assess the consistency of a measure from one use to another
when the study was replicated similar results were found
how can we assess external reliability?
what is it?
test-retest method
presenting the pps with the same test on different occasions with no feedback given after the first presentation
how can we improve external reliability?
standardised procedures: essential that the test is administered in the exact same way in the test and re-test phases in order to have any chance of producing the same outcome
what is observer reliability?
the extent to which 2 or more observers are consistent in their recordings
how do we assess observer reliability?
what is it?
inter-rater reliability method
measuring the extent to which researchers, scoring the same pps, achieve consistency of measurement with each other
how can we improve observer reliability?
variables/behaviours will need to be carefully operationalised so that each observer has a shared and accurate understanding of what behaviours to study and record
what is internal validity?
give an example for Milgram’s study
a measure of the extent to which the researcher has measured what they set out to measure
low internal validity due to demand characteristics
how can we improve internal validity?
give examples (3)
control/eliminate confounding and extraneous variables:
- demand characteristics - single blind techniques
- order effects - independent groups design
- participant variables - repeated measures/matched pairs design
what is external validity?
give an example for Milgram’s study
a measure of the extent to which we can generalise the findings outside the context of the investigation
poor external validity - all male and american pps, academic setting, conformist
how can we improve external validity? (3)
- adopting field or natural methods as opposed to lab based studies
- look at sampling techniques - random and stratified methods are more likely to produce representative samples
- repeat the research across different times, cultures, groups of pps
5 ways to asses validity
face validity
content validity
concurrent validity
construct validity
predictive validity
what is operationlisation?
when a variable is defined by the researcher and a way of
measuring that variable is developed for the research
what are the 5 steps of content analysis?
- familiarise yourself with the data
- identify key themes/categories
- code the data
- count the number of instances of evidence within each category
- draw conclusions
what are the 2 ways that the research can carry out the second step of content analysis?
top-down: researcher decides on appropriate categories before beginning the research
bottom-up: the categories or themes emerge when examining the data
what are the 5 types of graphical representation?
- bar chart
- line graph
- bar chart
- histogram
- scatter graph
what do correlational studies measure?
the relationship between 2 variables
what are the variables measured in correlational studies known as?
co-variables
define:
positive correlation
negative correlation
zero correlation
the 2 variables increase together
as 1 variable increases the other decreases
no relationship between the variables
what is correlation co-efficient?
a numerical representation of the strength and direction of the
relationship between two variables.
what can the correlation co-efficient range between?
-1.0 and +1.0
what does -1.0 and +1.0 represent?
-1.0 = perfect negative correlation
+1.0 = perfect positive correlation
what indicates a stronger correlation in correlation co-efficient?
the number being closer to 1
the strengths of correlations (2)
- can be used when it would be unethical or impractical to manipulate variables and can make use of existing data
- can establish a relationship between two variables if correlation is significant. If the correlation is not significant then you can probably rule out a causal relationship.
weakness of correlations
- correlational studies do not establish cause and effect; it only establishes a relationship between two variables. It may be that a third variable that has not been identified is creating the relationship
what are the measures of central tendancy?
mean
median
mode
strength of the mean
takes all the scores into account making it a sensitive measure of central tendency
weaknesses of the mean (2)
- can be very misleading if the distribution differs from normal and there are 1 or 2 extreme scores in one direction
- can only be used with interval or ratio data
strengths of the median (2)
- unaffected by a few extreme scores because it focuses only on scores from the middle of the distribution
- can be used with ordinal data
weakness of the median
ignores most of the scores so is less sensitive than the mean. also not always representative of the scores obtained
strengths of the mode (2)
- unaffected by 1 or 2 extreme scores and is the easiest to work out
- can be used with nominal data
what are the 4 levels of measurement from basic to complex?
nominal
ordinal
interval
ratio
what is nominal data?
give an example
the data is in separate categories
e.g. grouping people according to their favourite football team
what is ordinal data?
give an example
the data can be ordered in some way
e.g. asking people to put football teams in order of liking
what is interval data?
data is measured using units of equal intervals
what is ratio data?
give an example
when there is a true zero point
e.g. most measures of physical quantities
what are the 2 measures of dispersion?
range
standard deviation
strengths of the range (2)
- quick to calculate and provides direct information
-if 2 sets of data have the same mean, the range can offer another way of describing the data
weakness of the range
doesn’t provide any idea of the distribution of values around the centre, nor does it take individual values into account
what does standard deviation measure?
the spread of data around the mean
what are the 8 design options for questionnaires and interviews?
- open or closed questions
- question order
- wording
- avoid leading questions
- avoid double-barrelled questions
- avoid emotive questions
- avoid vagueness or ambiguity
- avoid inappropriate assumptions
strength of qualitative data
can successfully reduce complex forms of behaviour to a manageable number of categories of theoretical importance
weakness of qualitative data
reported findings tend to be unreliable and difficult to replicate due to the fact that this data is subjective and impressionistic
strength of quantitative data
relatively easy to analyse in comparison to qualitative data using descriptive and inferential statistics
weakness of quantitative data
may over simplify reality therefore any conclusions drawn may be effectively meaningless