research methods Flashcards
what is a lab experiment?
highly controlled in an artificial environment
what is a field experiment?
highly controlled in a natural environment
what is a quasi experiment?
no control over the independent variable; it is naturally occuring
what is an independent variable?
what you change // the cause
what is a dependent variable?
what you measure // the effect
what is a confounding variable?
a variable that affects the DV and validity
what is an extraneous variable?
a variable that could affect the DV, but has been controlled for so it doesn’t
what is an independent measures design?
participants are only in one group of the experiment
what is a repeated measures design?
participants are in both conditions of the experiment
what is a matched pairs design?
participants are matched in each condition for characteristics that may have an effect on their performance
what are individual differences?
demand characteristics; fatigue effects; order effects
benefits of an independent measures design
only experiences one condition so unable to guess the aim of the study; reduces situational variables which increases validity; easy to replace participants
limitations of an independent measures design
twice as many participants needed; increases participant variables; some people may be naturally ‘better’ which affects the validity as a confounding variable
benefits of a repeated measures design
controls participant variables; only need half the number of participants
limitations of a repeated measures design
situational variables such as fatigue and order effects (use counterbalancing to avoid this); more prone to demand characteristics; two versions of the task must be created of equal difficulty; if someone drops out two sets of data are lost
benefits of a matched pairs design
controls for participant variables; reduces situational variables
limitations of a matched pairs design
if someone drops out, you must find a new ‘match’ or risk losing two sets of data; requires hard work to match participants; some participants may get bored and drop out early
what is an alternate hypotheses?
“there will be a significant difference between…”
what is a null hypotheses?
“there will be no significant difference between…”
what are participant variables?
age, sex, mood, gender, ethnicity, culture, intelligence, personality.
these can be limited by: taking a larger sample; random allocation; repeated measures design
what are situational variables?
environment (heat, noise, distractions), time of day, order effects.
these can be controlled by: standardisation; counterbalancing
what is standardisation?
a standardised procedure that uses the same order and surroundings to increase validity and reliability with simple instructions
what is counterbalancing?
ABBA to deal with situational variables
what are investigator variables?
body language, tone of voice, confirmation bias, demand characteristics.
these can be dealt with by: single blind; double blind
what is a single blind?
participants don’t know what the study is about
what is a double blind?
both the participant and investigator don’t know what the study is about
what is a correlation?
a mathematical technique that requires two variables to be measured quantitatively to establish a correlation // a relationship between two variables where changes in one go along with the other
how can data be gathered for correlations?
self report, observation, or physiological measures
what is a positive correlation?
both variables increase
what is a negative correlation?
variables change in opposite directions
what is a coefficient?
a number that tells you how strong the correlation is
benefits of a correlation
indicates a connection between two issues in situations where experimental proof is impossible; does not require manipulation of variable- therefore safer and more ethical than experimenting on humans; high ecological validity as the numbers come from real life
limitations of a correlation
does not prove a causal relationship; does not prove a curvilinear relationship; subject to the problems associated with the method used to collect the data
what are descriptive statistics?
summary of data to illustrate patterns and relationships but can’t infer conclusions (e.g., mean, mode)
what are inferential statistics?
statistical tests that allow us to make conclusions in relation to our hypothesis (e.g., mann-whitney, spearman’s rho)
what is nominal data?
measure of central tendency: mode
category data
simplest type of data
what is ordinal data?
measure of central tendency: median
data ranked in order
what is interval data?
measure of central tendency: mean
interval data
measured on a fixed scale
what is a self-report?
questionnaires and interviews are two types of self-report where the participant tells you how they are feeling or what they are thinking. usually used in observational studies and experiments.
what are closed questions?
limited choice which gives quantitative data; easy to compare and analyse; doesn’t give much depth or explanation
what are open questions?
gives qualitative data; writes depth and detail; difficult to compare
what is a likert scale?
a data collection method on a scale which uses an odd number to have a midpoint. gives strength of feeling, qualitative with no explanation.
what is social desirability bias?
a situational variable where people choose the middle option in a self report if they don’t know or don’t want to seem extreme.
what is a response bias?
when people continue to tick the same box, and this can be stopped by reversing half of the questions to be phrased positively and the others negatively (split-half method)
what are semantic differentials?
similar to a likert scale, but it asks people to place themselves on a line between two extremes. used to measure attitudes.
what are interviews?
similar to questionnaires, but are face-to-face or over the telephone.
what are structured interviews?
all planned questions
what are unstructured interviews?
a conversation
what are semi-structured interviews?
uses some set questions. the best method as it provides qualitative and quantitative data.
benefits of self-report
allows participant to give views rather than just inferring from conversation; can study large samples easily and quickly; examine large number of variables; asks people to reveal behaviour and feelings from real life situations (ecologically valid)
limitations of self report
social desirability bias; validity issues from unclear questions; low response rates; leading questions; quantitative data does not include reasoning; qualitative data is hard to analyse; reliability and validity in context of the situation
what is reliability?
is it consistent with different people?
ways to improve reliability
ensure questions are not ambiguous; interviews must be standardised
what is validity?
does it measure what it set out to?
ways to improve validity
qualitative is more valid than quantitative by being able to see with greater ease; compare self report with another on the same topic to establish concurrent validity; avoid leading questions; add open ended questions; reinforce confidentiality to reduce social desirability bias
what is split-half method?
subtly repeats questions to ensure the opinion remains consistent, which increases the reliability
what is a participant observation?
the observer acts as part of the group being watched
what is a non-participant observation?
the observer does not become part of the group being observed
when can observations take place?
in a natural environment (naturalistic observation) or where variables are controlled and manipulated by the experimenter (controlled observation)
what is a structured observation?
determines the behaviours to be observed and the sampling to be used
what is an unstructured observation?
where the observer records everything that happens
what is an overt observation?
the participant knows they are being studied
what is a covert observation?
the participants do not know they are being studied
what is time sampling?
observations may be made at regular time intervals and coded
what is time-point sampling?
where the observer records what the participant is doing at fixed intervals, e.g., every five seconds over twenty minutes
what is time-event sampling?
where a fixed period is set for the observation, e.g., the first ten minutes of every hour being allocated to observe something
what is event sampling?
keeping a tally chart of each time a behaviour occurs
what are behavioural categories?
they are needed in structured observations to decide what is going to be observed and how it is going to be observed before the research begins. categories are defined.
what are coding frames?
these are used to make recording behavioural categories easier by listing different behaviours as different categories or ‘codes’. allows other information to be recorded quickly.
reliability in observations
difficult to replicate observations due to confounding variables; check consistency through inter-rater reliability; using good coding schemes
validity in observations
demand characteristics and observer bias can reduce validity. can be improved by using wider categories, a single-blind technique, or self-reports.
what is inter-rater reliability?
agree beforehand what will be observed and carry out a pilot study to ensure it works. each observer then observes the same thing independently. results are compared at the end of the observation. the greater the level of similarity, the greater the inter-rater reliability. means your coding scheme is consistent by producing the same results with different people.
ethics
informed consent, withdrawal, debriefing, deception, confidentiality, protection
what does a one-tailed hypothesis do?
predicts the direction of the relationship
what does a two-tailed hypothesis do?
does not know the direction of the relationship
when are hypotheses used?
for experiments and self-reports
why is sampling used?
because it takes too long to study everyone. it uses a sample to represent everyone and be generalisable to the wider population.
what is the population?
the group from which the sample is drawn
what is opportunity sampling?
the most used sampling technique by psychology students, which consists of taking sample from people who are available at the time and fit the necessary criteria.
benefits of opportunity sampling
quick, cheap and easy
limitations of opportunity sampling
not representative because it misses out people
what is random sampling?
every member of the population has an equal chance of being chosen. involves identifying everyone in the target population and selecting the number of participants needed.
benefits of random sampling
should be representative
limitations of random sampling
expensive; time consuming; not completely representative; if people decline it is no longer representative
what is self-selected sampling?
participants become part of the study because they volunteer when asked or in response to an advert.
benefits of self-selected sampling
quick, cheap and easy, and have consented
limitations of self-selected sampling
not representative as it is the same people who volunteer; higher demand characteristics through interest in psychology
what is stratified sampling?
classifying the main population into categories, and then choose a sample of participants from each category in the same proportion as they are in the population
benefits of stratified sampling
representative
limitations of stratified sampling
time consuming; can only be stratified on one category; in order to have correct proportions, the same group must get bigger each time; if someone drops out a participants who fits the stratified sample must be found
what is snowball sampling?
using a small group of people to ask other people to take part that have the same category, who then ask other people…
benefits of snowball sampling
useful for hard to reach groups
limitations of snowball sampling
time consuming; participants may not cooperate
when should bar charts be used?
when data is in discrete categories, and for nominal data
when should piecharts be used?
when you are confident that your data represents the whole- so they are barely used
hard to compare
when should a histogram/line graph be used?
to show the pattern in a whole data set (ordinal or interval)
show the distribution of scores
when should a scatter graph be used?
to display the findings of correlational studies
what is primary data?
data gathered by yourself for the study
what is secondary data?
data from another source
what are measures of dispersion?
gives an indication of how spread out results within a data set are.
range, variance, and standard deviation are used.
what is range?
the simplest measure of spread (used with ordinal or interval data)
subtract the smallest value from the largest and add one
can be distorted by outliers
what is variance?
gives an idea of how dispersed scores are around the mean
the bigger the number, the greater the variation
takes every score into account so is not affected by outliers
what is standard deviation?
tells us the average distance of each score from the mean
more precise as all values are taken into account
much harder and more time consuming to calculate
what critical value does psychological research require?
p < 0.05
chi-square test
independent design and nominal data
binomial sign test
repeated design and nominal data
mann-whitney u test
independent design and ordinal data
wilcoxon signed-rank test
repeated design and ordinal data
spearman’s rho test
correlation and ordinal data
what is a type one error?
when the operationalised hypothesis is accepted and the null is rejected, a ‘false positive’
caused by: poor research design; too lenient level of significance
what is a type two error?
where the null hypothesis is accepted despite the possibility to the operationalised hypothesis being correct, a ‘false negative’
caused by: poor research design, too stringent significance levels
what is the order of report writing?
abstract, introduction, method, results, discussion, referencing, appendices
what is included in the abstract?
summary of investigation
what is included in the introduction?
background research/theories/setting the scene
what is included in the method?
design, apparatus, participants, procedure
what is included in the results?
descriptive and inferential statistics
what is included in the discussion?
explaining results, linking to other research, evaluating/suggesting improvements, conclude
what is included in the appendices?
consent form, instructions, ethics, raw data, calculations
referencing books
boring, e.g. (1929) ‘a history of experimental psychology’, new york: century. page 20
author, initials, date, title, publisher, pages
referencing journals
sperry, r.w. (1968) hemisphere deconnection and unity in conscious awareness. ‘american psychologist’, 23, 723-733
author, initials, date, title, book, volume, pages
deductive reasoning
hypothesis -> experiment
logical and tests theories to drill down
inductive reasoning
observation -> theory
based on experiences and only takes one exception to falsify
what is the difference between variance and standard deviation?
variance is the average of the squared differences from the mean (tells how spread out results are around the mean)
standard deviation is the square root of the variances and 68% of scores fall in one s.d of the mean (tells the average distance of each score from the mean).
what is a significant difference?
means out has been found to be significant after being tested with inferential statistics. the observed value is compared with the critical value to see if it significant and the common level for significance in psychology is p<0.05.
hypothetico-deductive model
combines inductive and deductive stages of reasoning.
inductive reasoning for theory and deductive to drill down whether the idea works.
internal validity
how properly the experiment was conducted to produce truthful/accurate results
external validity
ecological + population
can results be generalised/representative?
face validity
does it look like it measures what it it supposed to measure?
construct validity?
does it measure all aspects of what is being assessed?
concurrent validity
correlates well with a pre-validated test
criterion validity
concurrent + predictive
can a measure predict future performance?
internal reliability
standardised, consistent procedure?
external validity
can be replicated from one time to another
inter-rater reliability
consistency of measuring tools
correlation of 80% is high
split half method
increases internal reliability
retreats questions in a questionnaire- two halves are similar to look for consistency of opinion and avoid response bias
test-retest
increases external validity
resting participants more than once
