Unit 1: Research Methods Flashcards
what are the 4 main research methods ?
experiment
observation
correlation
self report
what is an experimental research method ?
a research method that can establish the cause and effect relationships between variables
what is a hypothesis ?
a prediction of the effect of changing one variable (IV), on one other variable (DV).
why are there normally 2 conditions in an experiment ?
you have one control condition and the other non-control condition, to measure the effect of the IV.
what are laboratory experiments ?
experiments carried out under controlled conditions
what are field experiments ?
experiments carried out in a realistic setting
what are qausi experiments ?
experiments where the IV is naturally occurring e.g. autism (baren-cohen study)
what is one strength of a laboratory experiment ?
controlled so we can insure the variable is the only thing we are measuring
what is one weakness of a laboratory experiment ?
less ecological validity, artificial settings that do not reflect real-life, therefore the behavior we see may also be artificial
what is one strength of a field experiment ?
more ecological validity, as it can offer a more realistic setting for a study
what is one weakness of a field experiment ?
lack of control, difficult to control extraneous variables
what is one strength of a quasi experiment ?
it allows us to study the effects of variables psychologists cant manipulate
what is one weakness of a quasi experiment ?
no control over the participants, in terms of a social setting
what is a naturalistic observation ?
carried out in a natural setting, field experiment
what is a controlled observation ?
attempting to control all possible factors which may affect behaviour
what is a participant observation ?
where the observer is a part or pretending to be a part of the group they are observing
what is a non-participant observation ?
where the observer is not part or pretending to be a part of the group they are observing
what is an unstructured observation ?
observer records everything that happens in no particular structure
what is a structured observation ?
only noting down data they need
what is a covert observation ?
where the participant does not know they are being observed
what is an overt observation ?
where the participant is aware they are being observed and may of already given consent
what are the weaknesses of unstructured observations ?
might be too much going on
the data may be too dense to analyse
difficult to summarise and present data
what are the strengths and weaknesses of structured observations ?
strengths:
allows for comparisons to be made across each observation
trends in data can be seen more easily
weaknesses:
may miss other important behaviours
what are the weaknesses of naturalistic observations ?
lack of control
what are the weaknesses of controlled observations ?
artificial, demand characteristics
what are the strengths and weaknesses of participant observations ?
strengths:
insight into the experience and gain detail there
good vantage point
weakness:
may be observing for a long-time
what are the strengths and weaknesses of non-participant observations ?
strengths:
may stay more objective
weakness:
not enough insight
what are the strengths and weaknesses of covert observations ?
strengths:
natural behaviour
weaknesses:
no consent
what are the different techniques for collecting data via a self-report ?
questionnaires
structured interview
unstructured interview
semi-structured interview
what are questionnaires ?
are sets of questionnaires is that are usually completed as pen and paper tests, or can be done over the internet or telephone
what is an advantage of questionnaires ?
they gather a great deal of data from a large sample very quickly
what is a structured interview ?
an interview where the same set of questions is asked to each participant in the same order
what is an advantage and disadvantage of a structured interview ?
adv: easier to gather quantitative data than an unstructured interview, can easily analyse data for trends
dadv: artificial, participant may not feel free to give detailed answers
what is an unstructured interview ?
the researcher has topics to discuss but they are not in any order
what is an advantage and disadvantage of a unstructured interview ?
adv: lots of qualitative data
dadv: can be difficult to summarise data, look for trends etc.
what is a semi-structured interview ?
where the interview has a list of questions but can be sociable ?
what are ways of collecting data when doing a self-report ?
open questions
closed questions
rating scales
likert scales
semantic differential scale
what is an open question ?
where the participant has freedom to respond and with an explanation
what type of data do open questions provide ?
qualitative data
what are advantages and disadvantages of open questions ?
adv: high validity, as participants are not forced to respond in a certain way
dadv: harder to analyse the qualitative data
what is a closed question ?
where the respondent has limited ways of responding
what are advantages and disadvantages of closed questions ?
adv: quantitative data, easy to analyse
dadv: lacks ecological validity, due to forced choices of answers available
what is a rating scale, and give an example ?
way of providing quantitative measure
e.g. (1-10)
what is a likert scale, and give an example ?
where people are given a range of answers from which they select one that represents the extent to which they like/ dislike or agree/ disagree something.
stronglyagree/agree/dontknow/disagree/strongly diasgree
what are the advantages of using likert scales ?
can increase ecological validity of a rating scale, because people have verbal options to chose from so its less artificial
if you assign numbers to the responses its possible to create quantitative data also from the responses
what is a semantic differential scale ?
it is used to put something on a scale between two descriptive words such as, ‘strong’ or ‘weak’.
what is a drawback of a semantic differential scale ?
participants have to have a reasonable vocabulary, and there may be cultural implications
what are the advantages and disadvantages of self-report ?
ADV: psychologists are able to measure cognitive variables, such as memory, knowledge and attitudes which cannot be observed or biologically tested
DADV: the validity of self-report data can be questioned where participants are able to deliberately falsify their answers out of fear of being judged
what is a correlation study ?
where statistics are used to tell us the relationship between two co-variables
what are the two types of correlation ?
positive correlation
negative correlation
what is a positive correlation ?
where one variable increases so the other one does too.
e.g. as height increases
IQ increases
what is a negative correlation ?
where one variable increases as the other one decreases
e.g. number of hours on xbox increases
exam results decrease
where is there no correlation ?
when there is no link between the two co-variables
what are the advantages ad disadvantages of correlational research ?
ADV: can be used to support the scientific credibility of research
DADV: just because the two co-variables are correlated doesn’t mean one caused the other to change
what are 5 other research methods ?
case studies
longitudinal and snapshot studies
psychometric tests
physiological measures
cross-cultural research
what are case studies ?
research that focuses on one participant or small group of participants with a specific characteristic.
e.g. a school class
what methods do case studies use to collect data ?
unstructured interviews
observation
psychometric test results
medical notes
all these are used to make a subjective analysis or the person or group
what is a disadvantage of case studies ?
lacks generalisability, not many people are going to relate to the case studies done as its usually researching a particularly unusual behaviour
what is a longitudinal study ?
where one participant or one group of individuals is studied over a long period of time
why are longitudinal studies done ?
to track development and enables us to monitor changes overtime
what is an advantage of longitudinal studies ?
reduction in participant variables as the same person or people are being studied
what is a snapshot study ?
different groups of people are tested at the same point in time and their performances compared
what is the advantage of snapshot studies ?
relatively quick to carry out
inexpensive
what are psychometric tests ?
tests to measure mental characteristics
i.e. intelligence, brain function, creativity, personality
what are advantages and disadvantages to psychometric tests ?
ADV: provide quantitative data
DADV: data may be falsified (low internal validity)
what is cross-cultural research ?
research studying or comparing multiple cultures at once
what is an issue with cross-cultural research ?
bias:
use of materials, the way research is carried out, or the interpretation of data
e.g. using a questionnaire for people who are not used to writing may lead to a lack of validity
what is a one-tailed hypothesis ?
an effect is predicted and is specific
directional
e.g. “students who listen to music while studying will score higher in the end of year test than those who study without music.”
what is a two-tailed hypothesis ?
an effect is predicted but not specific
non-directional
e.g. “listening to music while studying will affect a student’s performance in their end of year test.”
for a correlation study how do one-tailed hypothesis differ ?
it states whether there will be a positive or negative correlation
what is an alternative hypothesis ?
the hypothesis says the IV will have an effect on the DV
what is an null hypothesis ?
the hypothesis says the IV will not have an effect on the DV
for a correlation study how does a null hypothesis differ ?
says there will be no correlation between the variables
what is an IV variable ?
the one that changes
“cause”
what is a DV variable ?
the one that is measured
“effect”
what does operationalising a variable mean ?
describing the variables in detail
and explaining how they will be measured
e.g. the prediction that “eating chocolate improves exam performance”
what does the researcher mean by “eating chocolate” and “exam performance”
“participants who eat 200g of 70% cocoa chocolate 20 mins before taking their mock GCSE maths exam will perform higher.”
what are extraneous variables ?
all other variables which might influence behaviour
what are participant variables ?
factors within a person that can change overtime
what are situational factors ?
these are factors which can vary in the environment
what are the 3 strategies of controlling extraneous variables ?
standardisation
randomisation
counterbalancing
what is standardisation ?
keeping the test conditions the same for every participant
what is randomisation ?
random allocation of experimental conditions
what is counterbalancing ?
varying the order of presentation of tasks for participants
what is random sampling ?
every member of the target population has an equal chance of being selected
e.g. drawing out of a hat or a random number generator
what is snowball sampling ?
where one participant is told to recruit family and friends for the study
what is opportunity sampling ?
the researcher selects the most convenient people for the study
what is self-selected sampling ?
where people volunteer to take part in the study
e.g. advert, newspaper
a sample should be … ?
representative of the target population
where does gender bias occur in a sample ?
where the sample is all males or all females
where does age bias occur in a sample ?
where there are certain age groups, not representative of all people
where does culture bias occur ?
only one country/ area.
what do measures designs tell us ?
how participants are allocated in each condition
what is a repeated measures design ?
same participants are used for each condition
what is a independent measures design ?
different participants are used for each condition
what is a matched participants design ?
participants are paired up with someone else in the sample, due to a similar trait or traits
what are the strengths and weakness of a repeated measures design ?
S: comparing participants with themselves will likely result in less individual differences confounding our results
fewer participants, more cost (time) effective
W: order effects (boredom, fatigue, practice)
demand characteristics (participants may work out the IV, therefore changing their behaviour
what are the strengths and weaknesses of matched participants design ?
S: less likely to be effected by demand characteristics as each participant is only tested once
controls participant variables better
W: very time consuming to match participants
what are the strengths and weaknesses of independent measures design ?
S: less likely to have demand characteristics as participants are only tested once
W: individual differences between participants may confound findings/ results
what is raw data ?
data that psychologists collect for each participant
what is nominal level data ?
when data is categorised
what is ordinal level data ?
when data is ranked
what is interval level data ?
when data is ranked, and it shows how much difference there is between data
what is an example of interval level data ?
machinery bought to measure dependent variables, accurate
what is primary data ?
data gathered by the individual/ experimenter
what is secondary data ?
data gathered already by a 3rd party
what is an advantage of primary data ?
data is specific to the study
what is an advantage of secondary data ?
easy to access
usually cheaper than first hand gathering this data
what are the 4 ways of analysing data ?
measure of central tendency (combination of median and mode)
mean
median
mode
what are the 3 measures of dispersion ?
range
variance
standard deviation
how do calculate variance ?
1) work out the mean
2) for each participant, subtract the mean from their score to find the difference
3) square the result (difference for each participant)
4) work out the mean of those squared differences
what does a small variance indicate ?
that all the scores are very close to the mean
what does a large variance indicate ?
that all the scores are very far away from the mean, very spread-out
how do you work out the standard deviation ?
square root of the variance
why is probability important to psychologists ?
they want to know what the probability is that the independent variable did affect the dependent variable
why may a sample lack representativeness & generalisability ?
it may not be representative of the target population and therefore cannot be generalisable to the whole population
what is population validity ?
how generalisable a sample is
what is reliability ?
the consistency of research or findings
what is internal reliability ?
the consistency of results within a test
e.g. does the 1st half of the test give the same results as the 2nd half of the test
how do you test internal reliability ?
split half method
(test one half of the questions and then test the other half of the questions)
what is external reliability ?
refers to the extent at which test score vary from one time to another
how can you test external reliability ?
a test retest again
what is inter-rater reliability ?
when 2 observers consistently rate or observe the same behavior and the two sets of ratings are correlated
what is validity ?
how accurate a piece of research (or test) is measuring what it aims to measure.
what is a suitable correlation score for the inter-rater reliability ?
+0.8 or higher
what is event sampling ?
the act of recording is triggered by the occurrence of a specific behaviuor itself
what is time sampling ?
the act of recording is triggered by the ending of a set time interval
what is the research question ?
is a question related to what you are interested in finding out
what is a research aim ?
a statement about the purpose of the study
what is operationalisation of a variable ?
refers to the process of making variables physically measurable or testable
in a normal distribution graph where are the mean, median, and mode ?
at the midpoint
in a distorted distribution graph where are the mean, median, and mode ?
scattered around, due to outliers
what is a negatively skewed distribution curve ?
outliers scores are much lower than most students
what is a postively skewed distribution curve ?
outliers scores are much higher than most students
at what probability rate do psychologists deem research to have had a statistically significant effect ?
P < 0.05(greater than)
how can a researcher work out whether they have got a statistically significant effect ?
by doing a statistical analysis of their data
How can researchers work out which inferential statistics test to use ?
The statistical test to use is, in essence, determined by two things:
- The design of the investigation
- The level of measurement of the data that has been collected
what stastical test should be used for an independent measures design experiment, with nominal data ?
Chi-square‡
what stastical test should be used for an repeated measures design experiment matched participants design experiment, with nominal data ?
Binomial Sign test
what stastical test should be used for an correlation study, with nominal data ?
No test
what stastical test should be used for an independent measures design experiment, with ordinal data ?
Mann-Whitney U-test
what stastical test should be used for an repeated measures design experiment matched participants design experiment, with ordinal data ?
wilcoxon signed ranks
what stastical test should be used for a correlation study, with ordinal data ?
spearman’s rho
what stastical test should be used for a correlation study, with interval or ratio data ?
pearsons product moment
what stastical test should be used for a repeated measures design experiment matched participants design experiment , with interval or ratio data ?
related t-test
what stastical test should be used for a independent measures design experiment , with interval or ratio data ?
unrelated t-test
what are parametric tests ?
statistical tests (e.g. t-tests) used specifically with interval or ratio level data
what are non-parametric tests ?
statistical tests (e.g. u-tests) used specifically with nominal or ordinal level data
what are parametric tests more powerful than non-parametric tests ?
This is largely because by analysing raw individual scores (rather than, say, rank positions) they take account of not just the relative positions of individual items but the size of difference between one score and another.
what are the 3 criteria that have to be satisfied for a researcher to use a parametric test ?
+Interval or ratio level data
+A normal distribution of data
+Similar variances between results from the different conditions (i.e. homogeneity of variance)
what is a type 1 error ?
a false, positive
When researchers think they have found a significant result when they haven’t.
what is a type 2 error ?
false, negative
When researchers think they have not found a significant result when they have.
what do all these signs mean (<, «,»_space;, >, ∝, ∼) ?
= is equals
< is less than
«_space;is much less than
> is greater than
» is much greater than
∝ is proportional to
~ is approximately
what is internal validity ?
when a peice of research has lots of extraneous variables, and therefore may not be actually testing the effect of the IV
what is external validity ?
when the results of research can be generalised to other settings, because they were done in realistic settings, or have a representative sample, or didn’t have any bias in the method or interpretation of the results
what is face validity ?
how good the test or research looks to be at testing what it is meant to be testing.
what is construct validity?
where a test or study measures the actual behaviour it sets out to measure
what is concurrent validity ?
where a test or piece of research gives the same results as another test or study,
what is criterion ?
refers to how much one measure predicts the value of another measure
what is population validity ?
how accurately the test or study measures behaviour in the general population.
what is ecological validity ?
how like real-life a peice of research is
what is social desirability ?
shown by participants who want to present an image of being a good member of society.
what is single blind research ?
when the participants do not know the aim of the study
what is double blind research ?
when neither the participants nor the people carrying out the research know the aim of it.
what are the 6 ethical guidelines ?
- consent
- right to withdraw
- confidentiality
- deception
- debrief
- protection from harm
what are the 4 ethical considerations ?
respect
responsibility
integrity
competence
