Research Methods Flashcards
Aim
General expression of what the research intends to investigate.
Independent variable
The aspect of the experiment that the researcher changes or manipulates.
Dependent variable
The data that the researcher measures.
The data should only be affected by the IV.
Extraneous variable
A variable other than the IV that might affect the DV so therefore should be controlled.
Hypothesis
A prediction or testable statement about what the researcher thinks will happen.
Operationalisation
- Operationalised variables are carefully stated, demonstrating exactly how they are to be measured.
- This makes the hypothesis testable and measurable.
- This is so that the target behaviour can be observed and recorded.
Null hypothesis
- Predicts that there is no difference or relationship between the two groups.
- If any difference is found it is due to chance.
Alternative hypothesis
Predicts a difference/relationship between groups/conditions.
Directional hypothesis (one tailed)
Predicts a difference/relationship between conditions and states the direction of the difference.
Non-directional hypothesis (two tailed)
Predicts a difference/relationship between conditions and doesn’t state the direction.
When do you use directional or non-directional hypothesis?
Previous research evidence - directional
No previous research that suggests which direction - non-directional
How to write a null hypothesis
There will be no difference in DV in IV1 compared to IV2.
How to write a directional hypothesis
Participants who IV1 higher/lower DV IV2.
How to write a non-directional hypothesis
There will be a difference in DV in IV1 compared to IV2.
Levels of IV
Numbers of conditions
Lab experiment
- Carried out in an artificial environment
- Controlled and standardised procedure
- Researcher manipulates the IV to measure the effect on the DV
- Participants know they’re taking part in a study
Field experiment
- Conducted in a more natural environment
- Researcher manipulates the IV to measure the effect on the DV
- Participants do not know they are in an experiment
Natural experiment
- Conducted in a natural environment
- The IV is naturally occurring
- IV: setting
Quasi experiment
- Either lab or natural
- IV: something that occurs within the person (a characteristic)
- Not true experiments because you cannot randomly allocate participants to conditions
Standardised procedure
- Ensuring that all participants are treated in exactly the same way.
- Allows for reliable methodology
Reliability
Consistency
Internal validity
The extent to which it was the IV alone that caused a change to the DV.
Ecological validity
The extent to which the results can be generalised to another setting (e.g real life).
Mundane realism
The extent to which the task is representative of that behaviour in the real world.
Demand characteristics
- Cues in the environment that may reveal the aim of the experiment, and so participants may change their behaviour as a result.
- ‘Please you’ effect - changing your behaviour to try and ‘help’ the researcher.
- ‘Screw you’ effect - changing your behaviour to go against what the researcher is trying to find.
Random allocation
Each participant has an equal chance of being put into either condition.
Order effects
An extraneous variable where the order in which conditions of the experiment take place effects the results (e.g practice effects or fatigue effects).
Lab experiments strengths (x2)
- High control of extraneous variables (increases internal validity)
- Replication is possible due to standardisation (can test if the findings are reliable)
Lab experiments limitations (x3)
- Artificial environment (low ecological validity)
- Artificial task (low mundane realism)
- People know they are being tested (demand characteristics)
Field experiments strengths (x2)
- Natural environment (higher ecological validity)
- Participants do not normally know they are in an experiment (reduction in demand characteristics)
Natural experiments strengths (x2)
- They provide opportunity for research that might not otherwise be undertaken for practical or ethical reasons
- They often have high ecological validity because they study real-life events
Natural experiments limitations (x3)
- Lack of controls (difficult to establish cause and effect)
- A naturally occurring event may not happen very frequently (reducing the opportunities for research)
- Participants may not be randomly allocated to conditions (you cannot be sure the IV is affecting the DV - reducing validity)
Quasi experiments strength
They are often carried out under controlled conditions (same strengths as lab experiments).
Quasi experiments limitation
The participants cannot be randomly allocated to conditions (there may be participant extraneous variables).
What is meant by experimental designs
How the participants are organised across the conditions.
Independent groups design
Each participant takes part in one condition only.
Random allocation - the lottery method (x3)
- Obtain a list of all the people in the sample
- Put all the names in a lottery hat
- Select the number of names required for condition A and put the next names into condition B
Random allocation - random number generator (x2)
- Number every member of the sample
- Use a computer program to to get a random number and allocate half into one condition
Matched pairs design
Each participant only takes part in one condition only, but the participants are matched on variables considered relevant (e.g age, sex, IQ).
How is a matched pairs design done? (x3)
- The researcher recruits a group of participants
- They match the participants on specific variables (such as age or IQ) often done with a questionnaire
- One of the pair gets randomly allocated into condition A, the other condition B
Repeated measures design
Each participant takes part in both conditions.
Independent groups strengths (x2)
- Order effects are reduced as participants only take part in one condition
- Demand characteristics are reduced (less likely to guess the aim of the study if only taking part in one condition)
Independent groups limitations (x2)
- Participant extraneous variables between the groups (lowers the internal validity)
- Less economical than repeated measures (need twice as many participants)
Repeated measures strengths (x2)
- Participant extraneous variables are controlled for (reduced, never fully eliminated)
- Less participants needed as they appear in both conditions
Repeated measures limitations (x2)
- Order effects
- Demand characteristics
Matched pairs strengths (x2)
- Reduced order effects and demand characteristics (participants only take part in one condition)
- Participant extraneous variables are reduced (not eliminated)
Matched pairs limitations (x2)
- The participants cannot be truly matched
- Time consuming and expensive, so less economical than the other designs
Fixing problems - independent groups
- Participant variables and researcher bias: use random allocation
Fixing problems - repeated measures
- Order effects: use counterbalancing (half do A then B, half do B then A)
Fixing problems - matched pairs
- Participant variables: restrict the number of variables to match on
Experimental realism
Whether an experiment has psychological impact and ‘feels real’ to participants.
Confounding variables
Variables apart from the IV that have affected the DV.
Difference between extraneous and confounding variables
Extraneous - could affect
Confounding - have affected
Uncontrolled variables
Variables that cannot be controlled for (e.g weather) - they will become confounding variables.
Situational confounding variable
Features of the experimental situation
Participant confounding variable
Differences between the participants
Investigator effects
Where a researcher (consciously or unconsciously) acts in a way to support their prediction.
This is particularly a problem when observing effects that can be interpreted in more than one way.
Examples of direct effects (x3)
- Non verbal communication
- Spending more time with one group
- Asking leading questions
Examples of indirect effects (x2)
- Operationalised variables are designed in such a way that the desired result is more likely
- Loose procedure effect: an investigator may not clearly state the standardised instructions which leaves room for the results to be influenced by the experimenter
Randomisation
Presenting any stimuli in an experiment in a ‘random’ manner to avoid it having an effect on the DV.
It reduces the chance of practice effects becoming a confounding variable.
Single blind test
Where participants do not know which condition of a study they are in.
Double blind test
When neither participant nor the investigators know which condition the participants are in.
Target population
The group of people the researcher wants to study.
They cannot study everyone so they have to select a sample.
Sample
A small group of people who represent the target population and who are studied.
Random sampling
Sampling technique in which every member of the target population has an equal chance of being chosen.
How to do random sampling
- You need a sampling frame, which is a complete list of all members of the target population.
- All of the names on the list are assigned a number.
- The sample is selected randomly (e.g a computer-based randomiser or picking names from a hat).
Random sampling strength
Lack of bias because everyone has an equal chance (more likely to be representative)
Random sampling limitations (x2)
- Impractical (takes time and effort)
- Does not guarantee representativeness
Opportunity sampling
A technique that involves recruiting anyone who happens to be available at the time of your study.
How to do opportunity sampling
The researcher will go somewhere where they are likely to find their target population and ask people to take part.
Opportunity sampling strengths (x2)
- Simple and easy to conduct
- For field and natural experiments, the researcher must use those available
Opportunity sampling limitations (x2)
- Unrepresentative sample
- Researcher bias
Volunteer sampling
People volunteer in response to an advert.
The researcher may then select only those who are suitable for the study.
How to do volunteer sampling
Participants self-select by responding to an advert.
Volunteer sampling strengths (x2)
- Most convenient (economical method)
- Reach a wide audience
Volunteer sampling limitation
Biased sample (particular interests, altruistic (kind))
Systematic sampling
Selecting names from the sampling frame at regular intervals.
How to do systematic sampling
- A sampling frame is produced and organised (e.g into alphabetical order)
- A sampling system is nominated
- The researcher then works through the sampling frame until the sample is complete
Systematic sampling strengths (x2)
- Objective system so no researcher bias
- Simple (as long as you have a sampling frame)
Systematic sampling limitation
Not completely random, so not completely representative
Stratified sampling
Participants are selected from different subgroups (strata) in the target population in proportion to the subgroup frequency in the population.
How to do stratified sampling
- Identify the number of people in the target population
- Calculate the frequency of the subgroups
- Apply the frequency to the sample
Stratified sampling strength
Representative
Stratified sampling limitations (x2)
- Knowledge of population characteristics is required
- Time consuming
Test-retest reliability
The reliability of a test measured over time (measures consistency).
Inter-rater reliability
The degree of agreement amongst raters.
Population validity
How well the sample can be generalised to the population as a whole.
Temporal validity
Whether the findings are still valid today (high when research findings successfully apply across time).
Construct validity
The degree to which a test measures what it claims, or purports, to be measuring.
Concurrent validity
Asks whether a measure is in agreement with a pre-existing measure that is validated to test for the same (or a very similar) concept.
This is gauged by correlating measures against each other.
Predictive validity
The degree to which a test accurately predicts a criterion that will occur in the future.
Face validity
Where you apply a superficial and subjective assessment of whether or not your study or test measures what it is supposed to measure.
Quantitative data
Data that is expressed numerically.
Quantitative data strengths (x2)
- Relatively simple to analyse (comparisons between groups can be easily drawn)
- Data in numerical form tends to be more objective and less open to bias
Qualitative data
Data that is expressed in words, and may take the form of a written description of the thoughts, feelings and opinions of participants (or a written account of what the researcher saw in the case of an observation).
Qualitative data strengths (x2)
- More richness in detail
- Much broader in scope and gives the participant the opportunity to more fully report their thoughts, feelings and opinions on a given subject
Quantitative data limitation
Much narrower in meaning and detail than qualitative data (may fail to represent ‘real life’)
Qualitative data limitations (x2)
- Often difficult to analyse (cannot be summarised statistically)
- Conclusions often rely on the subjective interpretations of the researcher
Primary data
Original data that has been collected specifically for the purpose of the investigation by the researcher.
Primary data strength
Specific to the investigation
Primary data limitation
Requires time and effort (planning, preparation and resources)
Secondary data
Data that has been collected by someone other than the person who is conducting the research.
Secondary data strengths (x2)
- Quick and cheap to access
- The researcher may find that the desired information already exists and so there is no need to conduct primary data collection
Secondary data limitations (x3)
- Variation in the quality and accuracy
- May be outdated or incomplete
- May not match the researchers needs or objectives (could challenge the validity of any conclusions)
Case study
The detailed study of a single individual or a small group of people.
Triangulation
Using more than one method to check the validity of the findings.
Longitudinal study
Research carried out on an individual or group over a long period of time.
Longitudinal study strength
Allow to look at changes over time
Longitudinal study limitation
Participants may drop out (attrition rate) which can lead to a small sample size
Case study strengths (x4)
- High levels of validity (go into depth and give a rich insight)
- They allow multiple methods to be used (triangulation) which increases validity
- They allow researchers to study events or complex psychological areas they could not practically or ethically manipulate
- Efficient as it only takes one case study to refute a theory
Case study limitations (x3)
- Researcher bias (researchers can become too involved and lose their objectivity)
- Lack of control
- Difficult to replicate so lack scientific rigour (each case study is unique)
Observation
Simply observing behaviour and looking for patterns.
Participant reactivity
Individuals modify an aspect of their behaviour in response to their awareness of being observed (slightly different to demand characteristics).
Inter-rater reliability (observations)
There should be at least 2 observers to make the observational data more objective and unbiased.
They should then compare their data at the end, and the correlation should be as close to 1 (0.8 minimum) to have good reliability.
Naturalistic observations
The observation of behaviour in its natural setting.
Naturalistic observation strengths (x2)
- High ecological validity
- Participants are less likely to be affected by demand characteristics
Naturalistic observation limitations (x2)
- Little control over extraneous variables (hard to establish causality)
- Replication is often not possible (cannot check the reliability of the findings)
Controlled observations
An observation taking place in a controlled setting, usually behind a one way mirror so they cannot be seen.
Controlled observation strength
Controlled environment (less risk of extraneous variables affecting behaviour)
Controlled observation limitation
Artificial setting (results may lack ecological validity)
Structured observations
The researcher creates a behavioural checklist before the observation in order to code the behaviour.
Behaviour can be sampled Using time or event sampling.
Behavioural checklist
The researcher determines precisely what behaviours are to be observed before the observation.
The target behaviour is split up into a set of behavioural categories (behaviour checklist).
Criteria for a behavioural checklist (x4)
The behaviours should:
- Be observable
- Have no need for interferences to be made
- Cover all possible component behaviours
- Be mutually exclusive / not overlap
Pilot study
A small scale study carried out before the actual research.
It allows the researchers to practice using the behaviour checklist / observation schedule.
Event sampling
Counting each time a particular behaviour is observed.
Event sampling strength
Useful when the target behaviour or event happens infrequently and could be missed if time sampling was used.
Event sampling limitation
If the situation is too busy and there is lots of the target behaviour occurring then the researcher may not record it all.
Time sampling
Recording behaviour at timed intervals.
Time sampling strength
The observer has time to record what they have seen.
Time sampling limitation
Some behaviours will be missed outside the intervals - observations may not be representative.
Structured observation strengths (x2)
- The behavioural checklist allows objective, quantifiable data to be collected which can be statistically analysed.
- Allows for more than one observer (due to checklist) which can increase the (inter-observer) reliability.
Structured observation limitation
The pre-existing behavioural categories can be restrictive and does not always explain why the behaviour is happening.
Unstructured observations
The observer notes down all the behaviours they can see in a qualitative form over a period of time (no behavioural checklist is used).
Unstructured observation strengths (x2)
- Can generate in-depth, rich qualitative data that can explain why the behaviour has occurred
- Researchers are not limited by prior theoretical explanations
Unstructured observation limitations (x2)
- The observers can get down to eye catching behaviours that may not be representative of all behaviours occurring
- More subjective and less comparable across researchers
Overt observations
Participants are aware that their behaviour is being studied - the observer is obvious.
Overt observation strength
Better fulfils ethical guidelines (compared to covert)
Overt observation limitation
Participant reactivity - participants know they are being observed and so they may change their behaviour
Covert observations
Participants are unaware that their behaviour is being studied - the observer is covered
Covert observation strength
Behaviour is more likely to be natural (higher validity)
Covert observation limitation
Can break ethical guidelines as deception is used (it may cause the participants some psychological harm)
Participant observations
The observer becomes involved in the participant group and may not be known to other participants.
Participant observation strength
Being part of the group can allow the researcher to get a deep understanding of the behaviours of the group (increasing validity).
Participant observation limitations (x2)
- The presence of the researcher might influence the behaviour of the group
- The researcher may lose objectivity as they are part of the group
Non-participant observations
The observer is separate from the participant group that are being observed.
Non-participant observation strength
Researchers’ observations are likely to be more objective as they are not influenced by the group.
Non-participant observation limitation
It is harder to produce qualitative data to understand the reasons for the behaviour.
Self-reports
Methods of gathering data where participants provide information about themselves (e.g thoughts, feelings, opinions).
Psychometric measure
Tests that have been assessed for validity and reliability.
Self-report strengths (x4)
- Provides rich qualitative data about complex human behaviour
- Can help explain reasons behind behaviour
- An easy way to gather a large amount of data (increases generalisability)
- You can ask people hypothetically what they would do without having to set up an experiment and observe behaviour
Self-report limitations (x5)
- Social desirability bias (wanting to come across in a certain way)
- Only useful if the participant is willing to disclose the information
- Relies on participants having the introspective ability to understand their own thoughts and feelings
- Acquiescence bias (people tend to agree with questions)
- Participants may misinterpret the questions (subjective)
Questionnaires
A written self-report technique where participants are given a pre-set number of questions to respond to.
How should questions be designed in a questionnaire?
- Questions should progress logically from least to most sensitive, and from more general to more specific
- The researcher should ensure that the answer to a question is not influenced by previous questions
Types of questions (x4)
- Likert scales (strongly disagree…strongly agree)
- Rating scales (1-10)
- Closed questions (yes/no)
- Open questions (describe…)
Closed questions
There are only a certain amount of choices available to answer.
Open questions
Allow participants to give a full, detailed answer and there is no restriction on what the participants can say.
Standardised instructions
A set of written or recorded instructions that are given to ensure that all participants receive them in the same way.
Filler questions
Questions put into a questionnaire or interview to disguise the aim of the study (to reduce demand characteristics p).
Questionnaire strengths (x3)
- Social desirability bias is reduced (no interviewer present, and often anonymous)
- A large amount of data can be controlled very quickly (increase representativeness and generalisability)
- Data can be analysed more easily than interviews (if mostly quantitative)
Questionnaire limitations (x2)
- Opinions given may not reflect the participant’s opinion and they may be forced into answering something which does not fit (lowering the validity of the findings)
- The quantitative data produces less rich data than interviews
Interview
A self-report technique that involves an experimenter asking participants questions (generally on a one-to-one basis) and recording their responses.