Psychology: Non-Experimental Methods Flashcards
What is the difference between a correlation and an experiment?
- Experiments involve the manipulation of one variable (IV) to see the effect on another (DV). This allows cause to be established.
- Correlational variables (co-variables) cannot be manipulated. They can only be measured. This means cause cannot be established.
What are the variables called in a correlation study?
Co-variables
What is meant by a positive correlation?
As one co-variable increases, s does the other
What is meant by a negative correlation?
As one co-variable increases, the other decreases
What is meant by a zero correlation?
When there is no relationship between two co-variables
Why can’t we say one co-varibel cause the effect on the other co-variable?
Correlation does not equal causation
Two strengths of correlation research
- It allows the researcher to study the relationship between variable that cannot be manipulated e.g. smoking and lung cancer
- It is possible to correlate a large amount of data and secondary data (data that has already be collected for another purpose) can be used
One limitation of correlational research
Association does not mean causation –> Cause and Effect cannot be established
What is a Naturalistic observation?
Strength & Limitation
An observation where the researcher studies behaviour in its real-life or natural setting without any intervention or control from the researcher
- Often participants do not know they are being obsevered
Strength: High external validity
Limitation There are ethical issues
What is a Controlled observation?
Strength & Limitation
The observation happens in a carefully controlled and structured environment
- The researcher set specific conditions, variables, and procedures to systematically observe and measure behaviour
Example: Mary Ainsworth’s strange situation to measure attachment in children
Strength: More control over what is being observed, more replicable + more extraneous variables are controlled
Limitation: Low external validity
What is a Covert observation?
Strength & Limitation
Where the participant does not know they are being observed
- As you cannot get informed consent, it must be behaviour that is public and happening anyway to be ethical
Strength: Avoids demand characteristics or participant reactivity
Limitation: Cannot demonstrate causal relationships
What is a Overt observation?
Strength & Limitation
Where the participant know they are being observed and have given informed consent.
- Participants have given informed consent prior to the observation
Strength: More ethical
Limitation: There are more demand characteristics
What is a Participant observation?
Strength & Limitation
Where observer goes ‘undercover’ and joins group that is being observed - they become part of the research
Strength: Allows the researcher to get in depth information - Increased insight may increase external validity
Limitation: Cannot demonstrate causal relationships
What is a Non-participant observation?
Strength & Limitation
Where the observer remain separate from those they are studying and observes in a more objective way
Strength: It avoids ethical issues involved in participant observation
Limitations: Cannot demonstrate causal relationships
Why can’t cause and effect be established in observations?
Because there is no IV and therefore no DV
What are behavioural categories?
When a target behaviour is broken down into components that are observable and measurable
What is event sampling?
Involves counting the number of times a particular behaviour occurs
Example: the number of aggressive acts during a school playtime
Strength: Good for when a behaviour occurs infrequently and could be missed through time sampling
Limitation: Important details may be overlooked during more complex observations
What is time sampling?
Involves recording behaviour within a predetermined time frame, record what behaviour is occurring at ever Nth time
Strength: Effective in reducing the number of observations that have to be made
Limitation: The behaviour sampled may be unpresentable of the observation as a whole
What is meant by inter-observer reliability?
Observer bias can be a problem in observations. To avoid this, observations should be carried out by at least 2 observes, using the same behavioural categories who independently observe the observation.
How do researchers check (assess) for inter-observer reliability?
- Each observer independently rates the observation using the same behavioural categories
- Correlate the findings using a Scatter Graph
- The observation is reliable if the level of agreement is +0.8 (80%) or above.
How can the reliability of an observation be improved?
Use two observers observing the same behavioural Characteristics
What is meant by a ‘self-report’ technique?
Any method where the person is asked to explain their own feelings, opinions, behaviours on a topic
What type of data do closed questions produce, qualitative or quantitative?
Qualitative data - wide range of more detailed data but harder to analysis
What type of data do open questions produce, qualitative or quantitative?
Quantitative data - lacks depth but easy to analysis. If data is not quantitative it can be turned into quantitative data e.g. through counting number of Yes vs No responses.
Give an example of an open question asking about someone’s view on school
What do you think about school?
Give an example of a closed question asking about someone’s view on school
Do you like school? Yes/No
Strength of Open questions in psychological research
- Provides full and in-depth information
- Allows participants to answer how they really want to
Limitation of Open questions in psychological research
- Participants may not bother to answer at all
- Difficult to compare one answer with another
Strength of Closed questions in psychological research
- Easier to answer
- Allows comparisons to be made between different answers easily
Limitation of Closed questions in psychological research
- Participants may not be able to answer how they want to
Strength of Questionnaires in psychological research
- Cost effective: allows lots of data to be collected relatively cheaply
- Data can be easily analysed: if closed questions are used (fixed choice) the results lend themselves to statistical analysis and comparisons between groups can easily be made
How might Social Desirability Bias affect the way people respond to a question in a self-report study?
Type of demand characteristic where humans wish to be seen / portrayed in a positive way –> may change response.
What is meant by Acquiescence Bias is elf-report studies?
AGREE - humans have the tendency to agree with a statement, regardless of the content.
Explain the difference between structured and unstructured interviews
What is an Interview?
A ‘live’ encounter (face to face or on the phone) where the interviewer asks a set of questions to a single participant about their thoughts and/or experiences
What are the types of Interview?
- Structured Interviews
- Semi-Structured Interviews
- UnStructured Interviews
What are Structured Interviews?
The list of questions that make up the interview is ‘pre-set’: the interviewee is required to answer a predetermined set of questions in a fixed order
What are Semi-Structured Interviews?
- Most interviews fall somewhere on the middle between structured + unstructured e.g. a job interview
- There is a list of questions that have been set in advance in an expected order but there is the freedom for interviewers to ask follow up questions based on the previous answers.
What are UnStructured Interviews?
- Works a lot more like a conversation - the interviewer guides the choice of topic and has an idea about what they want to find out but they are not too directive
- There is no list of predetermined questions that are asked in a fixed order
- Encourages the interviewee to express their own views on a topic in a way that is free-flowing. Interviewee is encouraged to elaborate on answers by interviewer.
2 strengths of Structured interviews in psychological research
- Easy to replicate due to standardised format
- Can ask about everything you want and ensure nothing is missed out
1 strengths of Unstructured interviews in psychological research
- Provides rich data - interviews can ask follow up questions so can get more detailed responses and insight
2 limitations of Structured interviews in psychological research
- Likely to be a social desirability bias
- Participants not free to answer in the way you want + interviewers cannot ask follow up questions to gain more insight
2 limitations of Unstructured interviews in psychological research
- Bias can easily occur as the interviewer can change questions and may ask them in a leading way
- Difficult to make comparisons between answers as not all participants are asked the same questions
How might researcher bias be reduced in interviews
- Standarises all the questions
- Have a difficult (independent) researcher carry out the interview rather than the main researcher for study
Designing Interviews
- Interviews normally have an ‘interview schedule,’ which is a list of questions that the interviewer intends to cover
- Interviews should take place in a quiet, private place
- Interviews often begin with neutral questions to put interviewees at ease
What is the difference between Quantitative and Qualitative data?
- Qualitative is descriptive (words) and non-numerical
- Quantitative that can be counted, usually given as numbers
Which research methods produce Quantitative data?
Methods that end to lead to qualitative data include: Interviews using open questions, case studies, some observations
Which research methods produce Qualitative data?
Methods producing Quantitative data include: experiments, questionnaires with Closed questions ect.
Strength of Quantitative data
- Particularly useful where deep understanding is required
- In-depth- gets views and feeling of participants
Limitation of Quantitative data
- Difficult to replicate
- Difficult to make comparisons
- Often based on subjective accounts, maybe retrospective and open to distortion
Strength of Qualitative data
- Comparisons can be made between people / answers
- More objective
- Trends can be identified
Limitation of Qualitative data
- May provide statistics that look impressive but little real meaning
- Not in depth
What is Primary Data?
Is data collected for the purpose of the investigation by the researcher. It arrives first-hand from the participants themselves.
Which research methods produce
Primary Data?
Experiments, questionnaires, interviews or observations that are being used for the purpose they were created
What is Secondary Data?
- Is data that has already been collected by other researchers (pre-existing data)
- Has often been subject to statistical testing already - we know the significance level of the data
Which research methods produce Secondary Data?
It includes research conducted by other psychologists, government records e.g. National statistics such as Census, information on websites, employment absence records ect
Strength of Primary Data
Authentic and fit for purpose - targeted to get the exact information needed
Limitation of Primary Data
Takes a lot of time, effect + expensive
Strength of Secondary Data
Inexpensive, requires minimal effort, already statistically tested
Limative of Secondary Data
Variation in quality of secondary data - you cannot quality control and may not end up matching researchers needs
What is Meta-analysis?
- A Meta-analysis is the process of combining the data from a large number of studies that have been carried out into a particular area of study to see if the findings are consistent
- Can include both quantitative (effect size of findings) and qualitative data (discussion of all results + Methods).
- It is a type of secondary data
Strength of Meta-Analysis
Increases confidence in findings + can generalise to wider target population
Limitation of Meta-Analysis
Prone to publication bias/file drawer effect as the researcher may not select all relevant studies or leave out non-significant studies leading to biased results
