Research Methods Flashcards
Reliability
Consistency in results
Validity
Testing what the hypothesis claims (true to your prediction)
Paradigm
The basic assumptions and methods of a study (accepted by members of a group)
Paradigm shifts
When an important change in basic concepts and experimental practices of a scientific discipline occur
Objectivity
Unbiased by the researcher
Replicability
To repeat research and get the same findings using a standardised, controlled approach
Falsifiability
A theory is only scientific if it is possible to establish as false - if they survive attempts to falsify they are strong theories
Empirical method
Using a procedure that means you are only measuring what can be directly observed
Nominal data
Data in named categories, eg. Tall, Short
Ordinal data
Data ordered in some form, eg. 1st, 2nd
Interval data
Data measured using units of equal intervals
Ratio data
Data measured using units of equal intervals, not passing 0
Lab experiments
Iv manipulated, high controlled setting preventing the influence of extraneous variables
Strengths: cause and effect can be established
Weaknesses: low ecological validity - can’t be generalised to real life
increased chance of demand characteristics
Field experiments
Iv manipulated, naturalistic setting
Strengths: less change of experiment effects on results
high ecological validity
Weaknesses: ethical issues with a lack of consent
less control over extraneous variables
Natural experiments
Iv cannot be manipulated, dv is simply measured and judged as the effect of the iv
Strengths: high ecological validity
demand characteristics are often not an issue
Weaknesses: sample bias as participants can’t be randomly allocated to a condition
ethical issues with a lack of informed consent
Quasi experiments
Iv is naturally occurring and pre-determined, the iv is a difference between participants that already exists
Strengths: high ecological validity - the iv is naturally occurring so generalisable to real life
Weaknesses: low internal validity - lack of control over extraneous variables so the researcher can’t always accurately assess the effects of the iv - issues with cause and effect
non-replicable because reliability can’t be checked
Hypotheses
A clear, concise, testable statement that suggests the relationship between independent and dependent variables to be investigated (written in future tense)
Null hypotheses
Predicts there will be no difference/ correlation found in the results
Experimental hypotheses
Predicts there will be a significant difference/ correlation in the results between the two conditions
One tailed/ directional
States the iv with affect the dv in a specific direction (prediction can be made with previous evidence)
Two tailed/ non-directional
States there will be a difference found between the conditions of the independent variable, however the direction is not stated (no previous evidence)
Independent measures
Each participant is selected randomly for one condition only
Repeated measures
The same participants take part in both conditions
Match pairs
Participants are matched in pairs based on a shared characteristic, one member of each pair is placed in a separate condition
Mean
All scores are added together and divided by the total number of scores
Median
The middle value found in an ordered set of data
Mode
The most frequent value in a set of data
Range
The difference between the highest and lowest score
Strengths: easy to calculate
Weaknesses: distorted by extreme values
Standard deviation
A measure of the spread of score around the mean
Strengths: more precise
Weaknesses: may hide the characteristics of the data
Histograms
Represents continuous data on interval and ratio scales, bars represent each score of a group of scores, height of each bar represents the frequency, bars should touch
Scattergraphs
Used with correlational analysis, for each individual two scores are obtained to plot one dot, co-variables determine the x and y position of the dot, the scatter of the dots indicates the degree of correlation between the co-variables
Bar charts
Used when data is nominal, or to represent the average score of different groups, each bar is separate on the x-axis
Line graphs
Represents continuous data, uses points connected by lines to show how something changes in value over time, typically iv on x-axis and dv on y-axis
Operationalising
Making variables measurable
Extraneous variables
Anything other than the iv that has the potential to affect the results: participant, situational, investigator effects, demand characteristics
Naturalistic vs controlled observations
Naturalistic- Observes naturally occurring behaviour
The situation is not manipulated
Produces data with high ecological validity
Controlled- Observes behaviour in a prepared situation created by the researcher
No manipulation of variables
The researcher does not interfere in anyway
Participation vs non-participant observation
Participant- being involved in the observation group activities
Non- participant- observing the group from an outsider perspective
Disclosed vs undisclosed observation
Disclosed- participants are aware of their observation
Undisclosed- participants are unaware
Structured vs unstructured observation
Structured- events are observed in their natural setting and by an independent researcher
Unstructured- researcher records all relevant behaviour without a system
Methods of recording behaviour
Tally chart
Time sampling
Event sampling
Double blind technique
Neither the researcher or participant is aware of which condition they are in
Pilot study
A small-scale preliminary study conducted to evaluate the performance of the study’s design
Operational definitions
A description that defines a measure to such a degree that everyone collects data the same way
Inter-observer reliability
The observers agree prior to the observation on the operationalised definition of the behaviour. The observers independently rate the behaviour and compare their results using correlations analysis
Overt vs covert observations
Overt- participants are aware they are being observed, their is no deception
Covert- the researcher is undercover and the participants are unaware they are being observed
Evaluation of observational studies:
Pros- high ecological validity
allows us to study variable usually too unethical to manipulate
Cons- difficult to replicate
unethical as participants are unaware they are being observed- no consent
observer bias
time consuming and requiring careful preparation
Counterbalancing
Half the participants take part in condition A followers by condition B and vise versa.
Pilot study
A small scale version of the full research prior to practice their observation technique and check inter-observer reliability.
Semi-structured interview
Interviewers prepare a set of questions which they can adapt and refine dependant on the responses of the interviewee.
Structured interview
Interviewer will ask a series of prepared closed questions in order to gain quantitative data
Correlations
Look for a relationship
Have two co variables (not an IV and DV)
Do not use an experimental design
Plotted on a scattergraph
Case study
In-depth analysis of one person/group/event
Information is obtained from a range of sources: interviews, questionnaires and observations
Content analysis
Process whereby qualitative information can be systematically converted into qualitative data
It involves analysing transcripts in order to observe patterns and trends within the material
Thematic analysis
An alternative method of analysing qualitative data
Rather than converting into quantitative form, in thematic analysis the data remains of a qualitative nature
Aim
Give the research study a clear focus
A general statement outlining what the research intends to investigate