Research Methods Flashcards
What is empiricism?
Information gained through direct observation or experiment.
What is objectivity?
Observations and experiments should be unaffected by bias (such as researcher expectations).
What is replicability?
It is important that research can be repeated and similar results obtained, this adds to the reliability of the study.
What does rational mean?
logical basis for a course of action or belief.
What is hypothesis testing?
Using the scientific process to test a hypothesis under controlled conditions.
What is theory construction?
Validity of a theory is tested. Observations help to construct theories to understand the phenomena around us.
What is induction?
Involves reasoning from the particular to the general. FOr example, a scientist may observe instances of a natural phenomenon and come up with a general law or theory.
What is deduction?
Involves reasoning from the general to the particular. Starts with a theory and looking for instances to confirm this.
What is an example of induction?
Newton’s Laws are an example of this. He observed the behaviour of physical objects and produced laws that made sense of what he observed
What is an example of deduction?
Darwin’s theory of evolution is an example of this. He formulated a theory and set out to test its propositions by observing animals in nature. He specifically sought to collect data to prove his theory.
What is the scientific process of induction?
- Observations.
- Testable hypothesis
- Conduct a study to test the hypothesis
- Draw conclusions
(repeat either of these steps as necessary) - Propose theory.
What is the scientific process of deduction?
- Observations.
- Propose theory
- Testable hypothesis
- Conduct a study to test the hypothesis.
(repeat either of these steps as necessary) - Draw conclusions
What is the scientific model based on?
Upon a deduction system.
What is the scientific model?
- Observe something about the world
- Come up with a theory about the world
- From the theory, develop a testable hypothesis
- Test the hypothesis; observe results
- Use results to modify theory…. and so on
What is the falsification principle?
Instead of looking for examples to confirm a theory the only way to prove a theory is correct is to seek disproof. The only way to prove a theory correct was actually to seek disproof.
Who developed the falsification principle?
Karl Popper
What are the stages of Karl Poppers hypothetio-deductive method?
- Null hypothesis “Not all swans are white”
- Observation “Look for swans and record sightings”
- “No black swans were sighted”
- If there is no proof for the null, then you reject it.
- Create an alternative hypothesis
- Accept the alternative hypothesis with reasonable certainty.
Is the scientific method appropriate for psychology?
- The scientific method is reductionist and deterministic, by attempting to explain complex human behaviour in simplistic terms.
- Psychological treatments of mental health problems have had modest success; therefore the goals of science are not always appropriate in psychology.
- Science takes the nomothetic approach, whilst psychologists argue the idiographic approach is more suitable when treating patients.
Can psychology claim to be a science?
- Subjective; e.g. data collected using interviews, questionnaires, content analysis, or observation are less objective than experiments, but triangulation can make this method more objective and valid
- Experimenter bias and demand characteristics compromise validity.
What are the goals of science?
- Investigate and understand the natural world.
- Explain events in the natural world.
- Use those explanations to make predictions.
What is the nomothetic approach?
Looking to make generalisations about people and find similarities
What is the idiographic approach?
A focus on the individual .
What is peer review?
Peer review is the assessment of research by others who are experts in the same field (peers). This is usually done before research is published.
What are the advantages of peer review?
- Ensures research published is of high quality
- Checks the validity
- Judges the credibility of the research and assesses the quality and appropriateness of the design and methodology
- Peers assess how original the work is
- Can recommend whether the work needs to be rejected or revised
- Ensures well=respected journals have integrity. Prevents fault dates.
- Necessary where applying for funding
- Online journals can form the basis of peer review
What is the limitations of peer review?
- Slow
- Expensive
- Profligate of academic time
- Highly subjective
- Prone to bias
- Easily abused
- Poor at detecting defects
- Useless at detecting fraud
- Finding an expert
- Anonymity
- Publication bias
- Preserving the status quo
What is the limitation of finding an expert in peer review?
It isn’t always possible to find a suitable expert to review the report.
What is the limitation of anonymity in peer review?
Anonymous review is an issue as relationships between experts sometimes affect objectivity, and it can be highly competitive. Now journals prefer open reviewing.
What is the limitation of publication bias in terms of peer review?
Peer review tends to prefer positive results
What is the limitation of preserving the status quo in terms of peer review?
peer review tends to prefer results that support previous theory, rather than going against it. Science does not really like huge shifts in opinion or theory.
What is an experiment?
An experiment involves the manipulation (changing) of an independent variable to see what effect it has on the dependent variable, while at the same time trying to control other variables which might affect the results.
What is a variable?
Things which can vary or change
What is the independent variable?
The variable that you manipulate
What is the dependent variable?
The variable that you measure.
What is a laboratory experiment?
The researcher has strict control over variables and uses standardised procedures in a controlled environment. The researcher manipulates the Independent Variable.
What is a field experiment?
The experiment takes place in the subjects own natural environment, but the researcher still manipulates the Independent Variable.
What is a Quasi/Natural Experiment?
The independent variable is already naturally occurring; the researcher just records the effect on the dependent variable. The experiment may take place in a lab or in the natural environment.
What are the strengths of a lab experiment?
- High control of extraneous variables
- Replicability
- high internal validity
What are the weaknesses of a lab experiment?
- Investigator effects.
- Demand characteristics
- Low external (ecological) validity
What are the strengths of a field experiment?
- Experimenter effects reduced if participants are unaware of being studied
- Natural environment (high ecological validity)
- Less demand characteristicics
What are the weaknesses of a field experiment?
- Can’t control all extraneous variables.
- Can’t always repeat
- Ethical issues.
What are the strengths of a natural experiment?
- Some situations would be unethical to set up
2. High ecological validity
What are the weaknesses of a natural experiment?
- Causal conclusions cannot be drawn as IV is not manipulated
- Participants are not randomly allocated to conditions
- Confounding variables.
What is the advantage of an experiment?
- Establishes cause and effect
2. Objective
What is the disadvantage of an experiment?
- low levels of ecological validity and construct validity
2. Risk of demand characteristics.
What is a hypothesis?
a statement or prediction of what results you expect to find after your experiment.
How do you write a hypothesis?
Much state what you expect will happen, state the independent and dependent variable, and how you will operationalize these. If it is correlational, this must be stated in the hypothesis.
What is a directional/one tailed hypothesis?
are predictions that state the direction the results will go in.
What is a non-directional hypothesis?
are predictions that do not state the direction the results will go in.
What is a null hypothesis?
A null-hypothesis is a statement of no difference between the variables.
What is a repeated measures design?
This design uses the same participants in both conditions
What are the advantages of a repeated measures design?
No individual differences
What are the disadvantages of a repeated measures design?
- Demand characteristics; likely to figure out what the experimenters are expecting
- Order effects- either boredom or practice.
What can reduce order effects?
Counterbalancing
What is an independent measures design?
Each participant only takes part in one condition
What are the advantages of independent measures design?
- Fewer demand characters-only know their condition
2. No order effects
What are the disadvantages of independent measures design?
- Individual differences
What is a matched pairs design?
involves the use of independent measures, but each participant in Group A is paired with one in Group B.
This is done by finding participants who can be matched on key characteristics, e.g. IQ, memory ability, gender and so on. …
What is the advantage of matched pairs design?
Controls for individual differences
What is the disadvantage of matched pairs design?
Can be difficult to make perfect matches and is costly on money and time
What are the two types of self-report?
- Questionnaires; written form
2. Interviews; oral type
What are open questions?
Require options and explanations from participants – qualitative data
What are closed questions?
forced choice e.g. yes/no – Quantitative data
What is likert scaling?
Measures strength of opinion e.g. strongly agree, agree, neutral, disagree, strongly disagree,
Why is a pilot study needed for self-report?
Self-report is only ever as good as the questions – Need a pilot study to increase reliability and validity.
What are the strengths of self-report?
- Allows access to private thoughts and feelings
2. Can discover potential actions without having to set up a situation to test it.
What are the weaknesses of self-report?
- Can be unreliable due to participant variables
2. Potential researcher bias due to questioning and language.
What are naturalistic observations?
Observations that take place in a natural situation.
What are controlled observations?
Observations that take place where some variables are controlled and manipulated by the experimenter
What is participant observation?
The observer acts as part of the group being watched
What is non-participant observations?
The experimenter does not become part of the group being observed.
What are disclosed observations?
the participants in the study will be aware that they are being watched and this may therefore alter their behaviour
What are undisclosed observations?
this is covert observation – the subjects are not aware that they are being watched
What is direct observation?
Direct observation is when we are observing behaviour as it happens.
What is indirect observation?
Indirect observations may be when data has already been collected, for example, observing adverts on tv.
What are structured observations?
Observations where the behaviours to be observed and the sampling to be used and determined beforehand.
What is unstructured observations?
The observer records everything that happens.
What is the problem with unstructured observations?
This may lead to only recording visible or eye catching behaviour but not necessarily the most important behaviours.
What is time sampling?
WHen observations are made at regular time intervals and coded
What is event sampling?
When you keep a tally chart of each time a type of behaviour occurs.
What is observation?
Watching a participant and recording their behaviour.
What are the strengths of observations?
+ Possible to directly study behaviour rather than relying on self-report methods
+ High ecological validity as natural settings are observed
What are the weaknesses of observation?
Can only measure overt behaviour
- Potential observer bias
- Observer effect may lead to unreal behaviour
What is a correlation?
Determining the extent of the relationship between two variables. Association does not mean causation.
What is a positive correlation?
A relationship between two co-variables, that as the value of one variable increases so does the other.
What is meant by the term negative correlation?
A relationship between two co-variables, that as the value of one variable increases, the value of the other variable decreases
What are co-variables?
When one conducts correlational analysis there is no IV or DV, instead the two variables (which are measured) are referred to as co-variables.
How are correlations shown?
On a scatter graph.
What is a correlation co-efficient?
A co-efficient tells us how closely the co-variables are related. +1 is a perfect positive correlation, whilst -1 is a perfect negative correlation. 0 shows no correlation.
What are the strengths of correlations?
- Can statistically analyse naturally occurring phenomena
- Reliable measurements on strength and direction of the relationship of the co-variables can be made
- Easily Replicated
What are the weaknesses of correlations?
- Cannot establish cause and effect
- Intervening (unknown) variables can affect the construct validity of the findings
- Sample may lack generalisability
What is a case study?
Studying one person, group, organisation or event in detail.
What are the strengths of a case study?
+ Efficient method as it only takes one case study to disprove a theory
+ High validity as research offers detailed insight into naturally occurring but rare phenomena
What are the weaknesses of a case study?
- Cannot generalise due to small samples
2. Subjective
What is a content analysis?
Analysing secondary material to gain an insight into human behaviour.
What are the strengths of content analysis?
- Few ethical issues as material is being studied, rather than people
- Allows researchers to study people who may be difficult to access directly
What are the weaknesses of content analysis?
- Misinterpretation may occur due to the people not actually being studied directly
- Qualitative content findings may be subjective
- Quantitative content findings may lack construct validity
What is internal validity?
Whether the researcher measured what they intended to measure
What is internal validity affected by?
Extraneous/confounding variables.
What is external validity?
The extent the results of the study can be generalised to others (ecological validity)
What is internal reliability?
The measure of something that is consistent within itself (e.g. the questions on an IQ test measure IQ)
What is external reliability?
The measure is consistent over several occasions (e.g. the same individual gets the same IQ score)
How can be assess/ensure reliability?
- Inter-rater reliability
- Split-half method
- Test-retest method.
- Face validity
- Concurrent validity
- Predictive validity
What is inter-rater reliability?
Two or more interviewers/observers must get the same outcome on 80% or more of the behaviours.
What is split-half method?
Compare an individual’s performance on two halves of a test.
What is the test-retest method?
A person repeats a test a month or so after doing the test the first time
What is face validity?
Does the test look as though it measures what it intends to measure.
What is concurrent validity?
Results from a new test can be compared to a previously well-established test.
What is opportunity sampling?
Use the people available at the time. Who are most easily available. The easiest method but inevitably biased.
What is volunteer sampling?
Participants are selected by asking for volunteers, for example placing an advertisement on a college noticeboard. This method can access a variety of PP which would make the sample more represenatative but is inevitable biased due to volunteer bias.
What is random sampling?
Participants are identified and then selected by a lottery method or a random name generator. Normally unbiased. May be bias because some people refuse to take part.
What is stratified sampling?
Sub-groups are identified (e.g. boys or girls), then a predetermined number from each group is selected randomly in proportion to the target population. More representative.
What is quota sampling?
Same as stratified but using opportunity sampling.
What is snowball sampling?
Participants recommend friends to join the study. Prone to bias because you only get access to a small proportion of the population. USeful when conducting research with participants who are not easy to identify.
Why are ethical guidelines important?
Any professional group has a duty to behave in an ethical manner i.e. to behave with proper regard for the rights and feelings of others.
What are the ethical issues with human participants?
- Informed consent
- Right to withdraw
- Debrief
- Deception
- Protection for harm.
What does the BPS code of conduct say?
- Respect
- Competence
- Responsibility
- Integrity
What is meant by respect in the BPS code of conduct?
The researcher needs to maintain privacy, confidentiality, and have informed consent. You would not need informed consent in an observation where people would normally expect to be observed. Deception is only acceptable when revealing the reasons for the study affect the integrity of the results.
What is meant by competence in the BPS code of conduct?
Psychologists should maintain high standards.
What is meant by responsibility in the BPS code of conduct?
Psychologists have responsibilities to clients, the public, and the science of psychology. This incorporates a debrief and protection from harm.
What is meant by integrity in the BPS code of conduct?
Psychologists should be honest and accurate, including the reporting of findings. Any misconduct should be reported to the BPS.
Why are licenses granted for animal research?
- Results are important enough
- Research cannot be done without animals
- There is a minimum number of animals used
- Discomfort is kept to a minimum.
Why do we use non-human animals in studies?
- Animals are fascinating
- Animals allow for greater control and more objectivity
- You can use animals when you can’t use humans
- There is enough of a similarity between humans and animals to draw conclusions from one to the other.
What are the questions about whether we can justify animals in research?
- Sentient beings
- Speciesism
- Animal rights.
What does Singer say about animals in research?
View is Utilitarian, (the greatest good for the greatest number), so if an animal reduces human suffering it is justifiable.
What did Regan say about animal in research?
Says animals should never be used under any circumstances.
What did Singer say about speciesism?
That testing on different animals is no different to sexism or racism.
What did Gray say about animals in research?
That we have a duty to humans
What did Russel and Birch propose as requirements for animal research?
- Reduction (use fewer animals)
- Replacement (use alternative methods if possible)
- Refinement (use improved techniques to reduce stress).
The house of Lords endorses this principle.
What slide did I get to?
106 out of 180
What are the two types of statistics?
Descriptive and Inferential
What is an inferential statistic?
When you are trying to reach conclusions that extend beyond the immediate data alone. For example, using inferential statistics to try to infer from the sample data what the population may think
What are the two main ways of summarising data using descriptive statistics?
- Measures of Central tendency
2. Measure of dispersion
What are measures of central tendency?
- Mean-add all scores together then divide by total number of scores
- Mode- most common value within a set of values
- Median-finding the mid-point in an ordered set of values
What are measures of dispersion?
- Shows a spread of data, e.g. the range of the data
2. Standard deviation
What is nominal data?
Data in separate categories, such as grouping people based on eye colour etc.
What is ordinal data?
Data that are ordered such as asking people to put football teams in order of preference etc.
What is interval data?
Data that are measured using units of equal measurements or using any ‘public measurement- attendance at football games, Bandura’s observation every 5 seconds etc.
What is the evaluation of the mean?
- It makes use of all the values of all the data – represents all
- Precise
- Extreme values can make it misrepresentative
- Can only be used with interval data
What is the evaluation of the median?
- Not affected by extreme values – anomalies can be discounted
- Can be used with ordinal data
- Not as ‘sensitive’ as the mean, as not all values are used
What is the evaluation of the mode?
- Useful when the data are in categories i.e. nominal data
- Not useful if there are several modes
- Useful when there are only a small number of values
What is the evaluation of the range?
- Provides direct information
- Affected by extreme values
- Doesn’t take into account the number of observations/values in the data set.
What should you do when making a graph?
- Give the graph a title
- Label both of the axes
- Use a ruler
- Make the graph at least half a side in size
- Plan before rushing in
- Think carefully about your choice of graph
When are bar charts used?
When data can be divided into categories otherwise known as discrete data. Bars are separated on a bar chart to denote we are dealing with separate conditions.
When are scattergrams used?
To depict associations with co-variables. Either variable occupies the X-axis and the other the y-axis.
When is a histogram used?
When the data is continuous rather than discrete (as in a bar chart). The bars touch each other. The x-acis is made up of equal sized intervals of a single category, like 0-9, 10-19 etc.
When do we use line graphs?
Line graphs are used to represent continuous data and use points connected by lines to show how something changes in value, or instance, over time.
Why is probability important for statistical analysis?
Psychologists look at data to see if the pattern of results could have occurred by chance. If there results did not occur by chance then we say they are significant.
Why is significance important for statistical analysis?
You need to have a null hypothesis and an alternative hypothesis. What we are looking for is a significant difference in results, so we can see they are not due to chance; we want to accept the alternative hypothesis.
Why is chance important for statistical analysis?
Normally psychologists set the probability level at p≤0.05
which means there is a 5% possibility the results occur by chance in the sample]
What is the observed value?
The rho or u value calculated is called the observed value.