research methods Flashcards
Empirical Approach
The source of knowledge comes through our senses - knowledge is gained through experience.
If a theory hasn’t been tested empirically, then it cannot be classed as scientific.
PARADIGM
A general theory or law that is accepted by the majority of scientists in a specific field of study
Pre-science
No paradigm exists, and there is much debate about what the subject is and its theoretical approach
Normal science
A generally accepted paradigm that can account for all the phenomena related to the subject, and can explain and interpret all findings
Scientific revolution
Evidence against the old paradigm reaches a certain point, and there is a paradigm shift. The old paradigm is replaced by a new one
Null hypothesis
A statement which predicts no difference/relationship in results, and predicts all possible outcomes
Experimental/alternative/research hypothesis
A statement that predicts a difference/relationship in results - predicts a difference between the conditions of an independent and dependent variable
Aim
The intended purpose of an investigation
Hypothesis
A clear, precise and testable statement about the expected outcome of the research
Independent variable
Variable that is manipulated or changed by the researcher
Dependent variable
Variable that is measured
Operationalisation
The process of clearly defining observable behaviours that represent a more general construct in order for them to be measured
Independent groups
Two separate groups of participants experience two different conditions of the experiment
Repeated measures
All participants experience both conditions of the independent variable
Matched pairs
Participants are paired together on a variable/variables relevant to the experiment
Random allocation
In an experiment were participants are involved in a number of different conditions, the order of those conditions should be random
Counterbalancing
An attempt to control order effects in a repeated measures design - half the participants take part in condition A and B, the other half visa versa
Hawthorn effect
People change their behaviour due to the fact that they are being observed
Demand Characteristics
Participants are influenced by their environment/what’s going on in the study, so their is a change in their behaviour
Social desirability bias
Participants answer in ways which make them look good to others
Standardisation
Using exactly the same procedures and instructions for all participants in the research study, each time the experiment is conducted
Investigator effects
Any effect of the investigators behaviour on the research outcome. They reveal to the participants how they should behave or what the experiment is about.
Demand characteristics
Participants are influenced by their environment to the point they change the way they are acting
Single - blind techniques
Participants don’t know about the test being conducted, but the researchers do
Double - blind techniques
Both participants and the doctors don’t know about the study, therefore this reduces investigator effects
Ethics
Governs what psychologists can and cannot do, based on morals
Informed consent
Participants above the age of 18 have the ability to give consent if they are willing to take part in a study
Right to withdraw
Participants should have the right to leave any study, at any point.
Confidentiality
Data given to researchers, by participants of the study, must be kept anonymous unless said otherwise.
Deception
This is when participants are not told the entire truth about the study
Protection
Protecting participants from mental and physical harm whilst conducting the study
Debriefing
Researchers and participants talk over the experiment/study in order to remove any anxieties or misconceptions
Sample
A small representative group gained from the target population
Sampling
Method used to identify and obtain the sample of participants in a study
Generalisation
Applying the findings of a particular study to the population
Sample bias
When a sampling method results in unrepresentative sample
Volunteer bias
people who volunteer to participate in research are likely to be different and this can distort data/research
Random sampling
Selecting a sample using a random technique, meaning that everyone has an equal chance of being picked:
- picking numbers from a hat (lottery method)
- random number table
Evaluation of random sampling
Strengths: Reduces the effect of researcher bias, Increases the chance of having a representative sample
Limitations: Sample could still be biased depending on the population, Time consuming, An impossible method to do without specific data
Stratified sampling
A sample produced by identifying sub groups according to their frequency in the population - then participants are selected randomly from their subgroups
Evaluation of stratified sampling
Strengths: Representative sample, Accurate, Reduces researcher bias
Limitations: Time consuming, Human error could occur if maths is done wrong
Volunteer sampling
A sample relying on volunteers by advertising the study - via newspaper, internet, noticeboard.
Evaluation of volunteer sampling
Strengths: Reduces any ethical issues, Reduces researcher bias, Quicker and easier than other sampling methods
Limitations: Biased results could arise based on participants characteristics, Participants are more likely to display demand characteristics
Systematic sampling
A sample obtained by selecting every nth person
Example: every 5th person, or every 12th person
Evaluation of systematic sampling
Strengths: Reduction of researcher bias, Easier and quicker than other sampling methods,Can be used with large samples
Limitations: Biased by coincidence, More time consuming than other samples, Sometimes impossible to do
Opportunity sampling
Recruiting people who are the most convenient, or available and willing to take part
Evaluation of opportunity sample
Strengths: Quick, easy, inexpensive and convenient, Participants gathered in one place
Limitations: Not representative because people who aren’t available may differ from those who are available, Researcher has no direct control over the participants or the study
Laboratory experiment
An experiment which takes place in a highly controlled environment, and the IV is manipulated by the researcher
Evaluation of laboratory experiment
Strengths: Standardisation is possible which increases reliability, The cause and effect can be identified
Limitations: Low ecological validity, Possibility of participant bias due to demand characteristics, Tasks lack mundane realism
Field experiment
The independent variable is manipulated in a natural environment of the participants - sometimes they are unaware that they are being studied
Evaluation of Field experiment
Strengths: High ecological validity, Demand characteristics are not an issue as participants don’t know that they’re being studied
Limitations: No control of extraneous variables which reduces reliability
Natural experiment
The independent variable changes naturally - this means that the researcher doesn’t have much control. The DV is recorded
Evaluation of Natural experiment
Strengths: Provide opportunities for research which might not have happened due to ethical or practical reasons, High in ecological validity
Limitations: Reliability is reduced because these events have no specific time as to when they will take place, Research may still be conducted in a lab
Quasi experiment
The independent variable just exists, and it isn’t changed or manipulated - it is based on the differences between people (age, gender). The DV can be naturally occurring, or be decided by the researcher
Evaluation of quasi experiment
Strengths: Often carried out in controlled conditions (laboratory strengths)
Limitations: This type of experiment cannot use random sampling therefore there may be confounding variables, Change of the IV isn’t controlled by the researcher
Quantitative data
Data that is expressed numerically
- Percentages….
Evaluation of quantitative data
Strengths: Easy to analyse as it can be presented in a visual format
Limitations: Provides little insight and understanding into the participants thoughts and information
Qualitative data
Data that is expressed in words
- Written observation notes
- Diary entry….
Evaluation of qualitative data
Strengths: Provides a detailed understanding and insight into the participants views and information
Limitations: Difficult and time consuming to analyse
Primary data
Original data that has been collected specifically for the purpose of the research - also called field research
- Observations
- Interviews
-Questionnaires….
Evaluation of primary data
Strengths: The researcher has control over what data is collected, Data fits the purpose of the research
Limitations: Requires the time and effort of the researcher
Secondary data
Data collected by someone other than the person who is conducting the research
- Government statistics…
Evaluation of secondary data
Strengths: Easy to access, cheap and requires little effort from the researcher
Limitations: The content of the data may not match the purpose of the investigation, Reduction of validity
Meta analysis
A form of secondary data which refers to a process in which a number of studies are identified which have investigated the same aims/hypothesis. The results of these studies can be pooled together and a joint conclusion is produced
Evaluation of meta anlysis
Strengths: A larger, varied sample which allows it to be generalised over a larger population
Limitations: Increase of publication bias
Evaluation of mean
Strengths: Takes all the data into account
Limitations: Extreme values will change results
Evaluation of median
Strength: Not effected by extreme values
Limitations: Easy to calculate
Evaluation of mode
Strengths: Easy to calculate, Categorical data
Limitations: Not representative of the whole data set
Distributions
By plotting frequency data, we can see an overall pattern of the data
Normal distribution
- Forms a bell shaped curve
- Shows symmetry
- Mean, median and mode are all located at the highest peak
- On average, most people are scoring in the middle
Positively-skewed distribution
- A spread of frequency that is not symmetrical
- Data clusters to one end
- The long tail is at the right hand side
Negatively-skewed distribution
- The long tail is on the left side of the peak
Correlation
A technique used to investigate the strength of the relationship between two variables (co-variables)
- Presented using scatter graphs
Positive correlation
As one co-variable increases, the other co-variable also increases
Negative correlation
As one co-variable increases, the other co-variable decreases
Zero correlation
There is no relationship between the co-variables
Evaluation of correlations
Strengths: Able to analyse situations that could not be manipulated experimentally for ethical or practical reasons, Correlations are useful tools in research - they suggest possible future research if there is a relationship between variables
Limitations: Can only identify linear relationships, Correlation does not establish cause and effect
Evaluation of questionnaires
Strengths: Doesn’t take much time, money, or effort, Answers collected can be changed into graphs or charts because of how direct they can be
Limitations: Social desirability bias may be an issue as participants might want to present themselves in a good light, Some participants might just agree with the statements given, regardless of the content of the question
Structured interview
An interview made up of pre-determined questions that are asked in a fixed order
Evaluation of structured interviews
Strengths: Straight forward to replicate, Reduces differences between interviews - standardisation
Limitations: If the questions are confusing to the participants , their answers will be limited
Unstructured interviews
An interview where there are no set questions, and it instead resembles a conversation to allow participants to elaborate and explore their answers
Evaluation of unstructured interviews
Strengths: Participants may feel more comfortable as they can answer however they want to, More detail into answers
Limitations: Due to the vague questions interviewers may have to go through lots of information to gather the information needed, Increased risk of interviews bias as an interview can adapt it as each interview is different
Semi-structured interview
A list of pre-determined questions which can be used, but interviewers are allowed to ask follow up questions based on previous answers
Naturalistic observation
Carried out in everyday settings, where the investigator does not interfere
Evaluation of naturalistic observation
Strengths: High ecological validity because they are conducted in a normal environment
Limitations: Researchers have very little control over extraneous/confounding variables
Controlled oberservations
Behaviour is observed under conditions where variables have been organised by the researcher
Evaluation of controlled observations
Strengths: Extraneous and confounding variables are less of a problem
Limitations: Low external/ecological validity, Findings cannot be applied to everyday life
Participant observation
The researcher participates in the activity being observed
Evaluation of participant observation
Strengths: Provides the researcher with increased insight into the people being studied
Limitations: Researchers may ‘go native’ and lose objectivity
Non-participant observations
The observer stays separate from people being observed
Evaluation of non-participant
Strengths: Researcher can remain objective so there is less danger of ‘going native’
Limitations: Lose valuable insight of the group
Overt observation
Participants are observed with their knowledge
Evaluation of overt observation
Strengths: Ethically acceptable, Researcher’s can gain consent from participants
Limitations: Demand characteristics may occur because participants know they are being studied
Covert observation
Participants are observed without their knowledge
Evaluation of covert observation
Strengths: Reduces demand characteristics because participants are unaware that they’re being studied
Limitations: Ethical issues (consent, withdrawal)
Unstructured observation
The researcher records all relevant behaviour but has no system
Evaluation of unstructured observation
Strengths: Researchers collect qualitative data which allows a detailed understanding of behaviour
Limitations: Qualitative data is time consuming and difficult to analyse
Structured observation
The researcher uses systems to record the behaviour, such as behavioural categories and event or time sampling
Evaluation of structured observations
Strengths: Behavioural categories make it easier to record data and produces quantitative data
Limitations: Using quantitative data means that meanings behind behaviour cannot be gained
Behavioural categories
When a target behaviour is broken up into components that are observable and measurable
Event sampling
Counting the number of times a particular behaviour occurs within a group
Time sampling
Recording behaviour within a pre-established time frame
Pilot study
A trial run of a research study, involving only a few participants who are representative of the target population
Pilotting
Testing a part of the eventual study
Peer review
Other people in the same field as you check the quality of your research and give improvements
Reliability
The extent to which a test or a study produces consistent results
Internal reliability
Measure of the extent to which something is consistent within itself
External reliability
Measure of consistency over a number of different occasions
Assessing reliability methods:
- Split-half method
- Test-retest method
Split-half method
When one half of the test compared with the other in order to check whether the scores are consistent
Test-retest method
The same test or interview is given to the same participant on two occasions to see if the same results are gained
Inter-rater reliability
The degree of agreement between different researchers - a result of 0.80 or more suggests good inter-rater reliability
Validity
The extent to which an observed effect is genuine
Internal validity
Whether the study has tested what it set out to test
External validity
The degree to which a research finding can be generalised to…
- other settings (ecological validity)
- to other groups of people (population validity)
- over time (temporal validity)
Face validity
Does the tests look correct?
Concurrent validity
Do results of this test match with results of a prior similar test?
Predictive validity
Based on prior knowledge, are the results ones that were expected
Improving validity
- Lie scale
- Covert Observation
- Behavioural categories
- Standardise
- Double blind
Level of significance
0.05 or 5%
Type 1 error
The null hypothesis is rejected and the alternative hypothesis was accepted, when it should’ve been the other way round.
- Often referred to as a false positive
Type 2 error
When the null hypothesis is accepted, and the alternative hypothesis was rejected when it should’ve been accepted.
Interval data
Data that can be ranked or put in order, but has a fixed scale
Ordinal data
Data that can be ranked or put in order but doesn’t have a fixed scale
Nominal data
Data that can be put into categories or frequencies or tally
