AO1 Research Methods Flashcards
What is a hypothesis?
A prediction
Directional hypothesis?
-States there will be a change and the direction that the results are expected to go
(only used if there is previous research to support it)
Non-directional hypothesis?
-States a change but does not mention the direction of the change
Operationalisation?
Clearly defining the variables in terms of how they can be measured
What is an extraneous variable?
Any variable other than the independent variable that affects the dependent variable if not controlled
(Nuisance variables)
Types of extraneous variables ?
-Demand characteristics
-Investigator effects
-Participant variables
-Situational variables
Demand charactersitic? (EV)
-Any cue from researcher / research situation that may be interpreted by the participant to reveal the purpose of the investigation ( participant changes behaviour)
Investigator effects? (EV)
Any effect of the researcher’s behaviour on the outcomes of the research ( Concious or unconcious)
Participant variables ?(EV)
Any individual differences between participants that may affect the DV
Situational variables ? (EV)
Any features ( environmental) of the experimental situation that may affect the DV
How can we control EV’s in an experiment ?
-Standardisation
-Randomisation
Standardisation
Using exactly the same procedures and instructions for all participants (eliminates situations variables)
Randomisation
The use of chance to control the effects of bias when designing materials and the order of conditions
Mundane realism /
External validity
How an experiment mirrors the real world
What is Experimental Design?
Refers to how participants are allocated to the different conditions in an experiment
What is Repeated measures design?
Only one group of participants.
This group takes part in both conditions
(both levels of the IV)
What is independent groups design?
Two separate groups of participants.One group takes part in condition A, other takes part in condition B
What is matched pairs design?
Two separate groups matched into pairs for certain qualities, such as age or intelligence. One of each pair takes part in condition A, the other takes part in condition B
Limitations of repeated measures design and how to deal with them?
The order effect.
For example fatigue, demand characteristics and boredom
How to deal:
Counterbalancing (ABBA)
Limitations of independent group design and how to deal with them?
Participant variables-Any differences between people in the two groups that could affect the results ( cant control but can restrict)
How to deal:
Random allocation
Limitations of matched pairs design and how to deal with them?
-Not possible to control all participant variables( can some)
-Time consuming
How to deal:
Pilot studies
Adavantages of the repeated measures design
-Participant variables can be eliminated( same people)
-Less participants so cheaper
Advantages of the independent group design
No order effects
Advantages of matched pairs design
Can control some participant variables
No order effects
What are order effects
An extraneous variable arising from the order in which the conditions are presented
E.G fatigue, demand characteristics, practise, boredom
Counterbalancing
Solution to order effects
-Half participants experience the conditions in one order and the other half experience them in the opposite order
(ABBA)
Random allocation
An attempt to control for participant variables in an independent group design which ensures each participant has the same chance of being in one condition as any other
Removes interviewer bias
For example, random number generator
Pilot study
A trial run of a research method, usually with a very small sample, with the aim of checking that the procedures and materials are standardised
Reliability
How consistent the findings from an experiment are ( need to be able to replicate it and standardise it)
Validity
Does the study measure what it intended to measure?
Internal Validity
Whether the effects of the experiment are down to the manipulation of the IV and not some other factor
what is a laboratory experiment
-Experiment conducted in a controlled artificial environment
-The IV is manipulated , the researcher observes the effect on the DV
Example of a lab experiment
-Milgram (1963)-
IV: Situation (authority figure)
DV: Obedience to authority
Strengths of a lab experiment
-Extraneous variables are controlled= high validity
-Standardised= easier to replicate
-More scientific and objective
-Researcher is detatched
Weaknesses of a lab experiment
-Lacks external validity (artificial environment)
-Investigator effects can occur
-Demand characteristics can occur
What is a field experiment
-Experiment in an everyday real life setting (E.G shopping centre)
-IV is manipulated, researcher observes effect on DV
Example of a field experiment
Bickman (1974)-
Social power of uniform
IV: Uniform worn
DV: Level of obedience
Strengths of a field experiment
-Eliminates demand characteristics (unaware they are being observed)
-High external validity
Weaknesses of a field experiment
-Extraneous variables are difficult to control#
-Unethical - unaware they are being observed
-Low internal validity so less replicable
What is a natural experiment
Experiment where the researcher has not changed the IV but it has occured ‘naturally’.
-Researcher does not measure its effect on DV
-Used when it’s not ethical to manipulate IV
Example of natural experiment
-Hodges and Tizard’s attachment research (1989):
Compared the long-term development of children who had been adopted, fostered or returned home
Strengths of a natural experiment
-High external validity- involves the study of real world issues (for example effect of natural disaster on stress levels)
-More ethical
Weaknesses of a natural experiment
-Less likely to be randomly allocated to experimental conditions. Researcher may be less sure if the IV affected the DV.
-Ethical issues
-Participant variables
-Investigator effects
-Demand characteristics
What is a quasi experimental design
Conducted when the IV is based on existing difference between people (can be manipulated by the researcher e.g. gender, race, IQ)
Population
-A specific group of people who are the focus of research .From this group a small sample is drawn
Sample
A small group of people drawn from target population, represent this target population in a research investigation
Generalisability
The extent to which the results of the investigation can be applied to the target population
Random sampling?
-A sample where each member of the target population has the same chance of being chosen for the sample
-E.G assign each person a random number and select participants with a random number generator
Systematic sampling
-Researcher numbers the participants in a sampling frame (e.g 1,2,3) and then picks their participants at a set interval
-E.G every nth member of the target population
Stratified sampling
-Researchers divide participants into sub groups called strata, based on characteristics they share
-E.G Age, race, gender
Opportunity sampling
-Researcher selects the most convenient and available people for the experiment
-E.G in the streets
Volunteer sample
-Participants self-select to become part of the study after seeing it being advertised
Strengths of a random sample
-No researcher bias as they have no influence over who is selected, meaning EVs are controlled, enhancing internal validity
-Equal chances of getting selected
-Simple
-
Weaknesses of random sampling
-Time consuming
-Selected participants may chose not to take part
-Difficult to obtain a complete list of the target population
Strengths of a systematic sample
-No researcher bias
-Produces a representative sample
-simple
Weaknesses of a systematic sample
-Could refuse to participate
-Time consuming
-Difficult to obtain a complete list of the population
-May as well use random sample
Strengths of stratified sampling
-No researcher bias
-Produces a representative sample (generalised), more generalisable than other methods
Weaknesses of stratified sampling
-Complete representation of target population can not be achieved
-Could refuse to participate
-Strata can not reflect all the ways in which people are different
Strengths of opportunity sampling
-Convenient
-Quick
-Cheaper
Weaknesses of opportunity sampling
-Could refuse to participate
-Unrepresentative of the target population ( drawn from a specific area so cannot be generalised)
-Researcher bias as they ask people to participate
Strengths of volunteer sampling
-Easy
-less time consuming
Weaknesses of volunteer sampling
-Could refuse to participate
-Volunteer bias can’t be generalised ( asking for volunteers might attract a certain ‘profile’ of a person E.G someone helpful, keen)
Ethical issues
-A conflict between the rights of the participants in an investigation and the goals of the research to produce valid data
E.G
-Deception
-right to withdraw
-Informed consent
-Protection from harm
-Privacy and confidentiality
Deception
-Purposely keeping information about the investigation from the participants or misleading them
How to deal with the ethical issue deception?
-Briefing and debriefing: making participants aware of the aims and any other details they were not provided with before
Right to withdraw
-Making sure participants are aware that they can withdraw from the experiment at any stage, if they wish to do so
How to deal with the ethical issue right to withdraw?
-Provide participants with a form beforehand about all info they may need, including about how they can withdraw at any point
-Reminded throughout and at the start of each stage
Informed consent
-Making participants aware of the investigation that they are going to be involved in, including all details, and ensuring they still want to participate
How to deal with the ethical issue informed consent?
-Providing participants with a form beforehand about all information they need about the experiment, including anything that may affect their decision to participate
-Sign a form if they agree
-Parental signature for anyone under 16
Protection from harm
-Putting measures in place to ensure participants are not harmed physically or psychologically from the investigation
How to deal with the ethical issue protection from harm?
-Participants must be reassured that their behaviour was typical or normal, should they have any concerns related to their performance in the experiment
-If participants have been subject to stress or embarrassment during the experiment, they may require counselling.
Researchers must provide this.
Privacy and confidentiality
-Protecting any personal information about the participants that they do not wish to share with anyone else and respecting their privacy
How to deal with the ethical issue privacy and confidentiality?
-Researcher does not record any personal details (remain anonymity)
-Refer to the participants using numbers or initials when writing up the results of the investigation
-During debriefing and briefing they should be reminded that only data will be protected
-Given the right to withold data
What is meant by BPS?
(code of authentics)
-A quasi legal document produced by the British psychological society
-Instructs psychologists in the UK what behaviour is and isn’t acceptable when dealing with participants
-Built around 4 major principles: Respect, competence, responsibility and integrity
What is a single blind trial?
-Participants are unaware of the aim and the other condition of the experiment, however the researcher is aware
What is a double blind trial?
neither the participants nor the experimenters know who is receiving a particular treatment.
What is a control group?
-A neutral group to formulate comparisons with or set a baseline
Are observations a non experimental or experimental method of research?
-Non experimental
This means there is no manipulation of variables. The researcher observes behaviour and looks for patterns
What are the types of observation?
-Naturalistic or controlled
-Structured or unstructured
-Participant or non participant
-Overt or Covert
What is a Naturalistic observation?
-An observation where behaviour is studied in a natural situation where everything has been left as it normally is
(an everyday situation)
What is a controlled observation?
-Some variables are controlled by the researcher, reducing the naturalness of the behaviour being studied.
Participants are likely to know that they are being observed and it is likely to take place in a lab
What is a participant observation?
-The observer acts as part of the group being observed
What is a non participant observation?
-The experimenter does not become part of the group being watched
(It is easier to record data and the observer can remain unbiased)
What is an Overt observation
(Open observation)
-Participants know they are being observed and why
What is a Covert observation
(Closed observation)
-The observation is kept secret from the participants
The observer is undercover and this can be done by CCTV or a one way mirror
What is a structured observation (design)
- The researcher has a system that is used to record behaviour called a coding system to tally the number of times a behaviour has occured and will use various sampling procedures to decide what to observe and when
What is an unstructured observation
-The researcher will record all relevant behaviour but has no system.
The results can be used to create a coding system that can be use for further structured observations
What is a coding system
- When behaviour is operationalised by being divided into different behavioural categories
What is time sampling?
(how we record data)
A way of sampling the behaviour that is being observed by recording specific behaviours at set time intervals.
E.g noting what a target individual is doing every 30 seconds
What is event sampling
(how we record data)
-Counting the number if times a particular behaviour (the ‘crent’) occurs in a target individual or group
What are behavioural categories
-Dividing a target behaviour into a subset of specific and operationalised behaviours
What is the Hawthorne Effect
-When you change your behaviour when you know you are being watched
(Demand characteristics)
Problems with using a coding sytem
-The Hawthorne effect
-Too many behavioural categories
-Need to be well trained to use
What is inter observer reliability?
The degree of agreement between different people observing an individual
Use multiple observers. -Calculated by correlating their observations. If there is more than 80% agreement between observers, the data has inter observer reliability
Strength and weakness of participant observations
-Researcher gains insight into the lives of the people as they are part of the group. This means the results will be more valid.
-Becoming part of the group may mean that they identify too strongly with the group. This means they may lose their objective interpretation and bias the results
Advantage and disadvantage of non participant observation
-The results are less likely to be influenced by bias and so be more valid as they are not part of the group
-Lose insight that they would gain if they participated in the group so results may not be realisitic
Advantages and disadvantages of overt observation
-More ethical as participants are aware they are being observed so they would have given consent beforehand
-Demands characteristics could occur so will lead to invalid results
Advantage and disadvantage of covert observation
-Removes issue of demand characteristics making results more valid
-Participants may not have given consent so less ethical
Advantage and disadvantage of controlled observation
-Researcher manipulates aspects of the situation so variables are controlled and results can be replicated
-Lacks external validity. Possibly know they are being observed so demand characteristics
Advantage and disadvantage of Naturalistic observation
-High external validity so results can be generalised to real life
-Less control over extraneous variables so more difficult to judge patterns of behaviour and makes reliability an issue
Ways validity can be increased in observations
-Conduct further observations in different settings with varied people so the results can be more generalisable
-Multiple observers so observer bias can be reduced and nothing is missed
-Double blind technique to remove observer bias
Ways reliability can be increased in observations
-Inter observer reliability-
-Training observers on how to use the coding system through practise
Open question
The participant can answer however they wish
( usually gives long detailed answers)
Closed question
(fixed choice question)
-There are set number of responses which the participant selects from
Likert scales
-A scale of responses to a question, often 1 to 5 demonstrating a level of agreement
Rating scales
Participants identify the value that represents their strength of feeling (e.g between 1-10)
Quantitative Data
-Data that focuses on numbers and frequencies which can be counted
Qualitative Data
-Data that describes meaning and experiences which is expressed in words
Structured interview
-A list of questions that the researcher reads out to the participant in order
-They typically contain closed questions and so largely produce quantitative data
Unstructured interviews
-The interview has ideas and general topics to cover, there are no set questions
-It is less formal and so rapport is built between participant and interviewer
Semi structured interview
Combines both structured and unstructured interviews
What type of data does a coding system produce
Quantitative data
What is a questionnaire
-A set of questions designed to collect information about a topic or topics
What are two strengths of a questionnaire
-Easy to repeat so data can be collected from a large number of people
-May feel more able to reveal personal information than they would face to face
Two weaknesses of using questionnaires
-Sample bias because only certain types of people fill in questionnaires
-Social desirability bias as some may deliberately respond with socially desirable answers
-They are not flexible so the researcher is unable to tailor it to their needs
Advantages and disadvantages of open questions
-Provide qualitative data, which gives valuable insight that closed questions would not give and can answer however they wish
-Qualitative data is more difficult to analyse, making it difficult to compare and draw conclusions
Advantages and disadvantages of closed questions
-Provides quantitative data which is easier to analyse and draw conclusions from
-May feel forced to select answers which may not represent their thoughts and feelings, meaning the data has less reliability
-Gives less detailed responses
Advantages of unstructured interviews
-Produces qualitative data
-Requires less interviewing skill so can be done by non professional interviewers
-Less formal so rapport can be built between interviewer and respondent so feels more like a conversation = more inclined to reveal more
-Qualitative data
Disadvantages of unstructured interviews
-Interviewer bias as they are making up questions on the spot and
interviewers own opinions may influence their answers
-Less reliable= different interviewers asking different questions and may behave differently on different occasions
-Harder to compare and draw conclusions
Advantages of structured interviews
-Easier to analyse as the answers are more predictable
-Can easily be repeated because the questions are standardised
-Quantitative data is easier to compare and analyse
Disadvantages of structured interviews
-Quantitative data lacks detail
-Interviewers cannot elaborate
-reliability may be affected by the interviewer behaving differently on different occasions
-Different questions may be interpreted in different ways by different participants
What is meant by correlation and what is it plotted on
-A relationship between 2 variables
-Plotted on a scatter graph
What is meant by correlation coefficient
-A number between -1 and 1 that tells you the strength and direction of a relationship between variables
a correlation can be +, - or have no correlation
What does a correlation tell us about the cause of one variable on the other
-It doesn’t. A correlation does not mean causation
-We know that there is an association between variables but we do not know which co variable caused the other to change
Give a non correlational hypothesis on the co variables; calories eaten and weight gained
-There will be a relationship between calories eaten and weight gained
Give a correlational hypothesis on the co variables; calories eaten and weight gained
-There will be a positive relationship between calories eaten and weight gained
Positive correlation
Means that as one variable increases, the other also increases
/
Negative correlation
Means that as one variable increases, the other decreases
\
No correlation
-A correlation of 0 or close to 0 means that there is no relationship between the two variables
-correlation coefficient= 0 or close to 0
Advantages of correlation analysis
-Allows predictions to be made
-Allows quantification of the relationship- correlations can show the strength of a relationship
-Some hypothesis can not be tested experimentally
-Do not require the manipulation of behaviour so are quick and ethical method of data analysis
Limitations of correlation analysis
-Cannot be assumed that one variable can cause another. Interpretation of results is therefore difficult
-Other variables may influence both variables, affecting the outcome of the results so may not be entirely accurate
Primary data
-Information that has been obtained first hand.
This data is also known as field research
Secondary data
-Information that has already been collected by someone else
This data is also known as desk research and has already been subject to statistical testing
-For example, Government statistics, NHS and the criminal justice system
Advantage and disadvantage of primary data
-Designed to meet the researchers aims- Directly relevant
-Time consuming and requires more effort, planning and preparation
Advantage and disadvantage of secondary data
-Inexpensive exists and requires a minimum amount of effort to access ( can access within minutes)
-Can access statistics that you may not otherwise be able to get first hand ( E.G from 1920s)
-Might be out of date and so unreliable
What are the measures of central tendency
-Mean
-Median
-Mode
What are the measures of dispersion
-Range
-Standard deviation
What is standard deviation
-A single value that tells us how much a score varies from the mean
What does a large standard deviation mean
Large SD= Not all participants were affected by the IV in the same way
What does a low standard deviation mean
Data is tightly clustered around the mean, which means participants responded in a similiar way
What are co variables
The variables investigated in a correlation
What is a confounding variable
Any extraneous variables that influences the relationship between the IV and the DV, leading to unreliable results
5 ways of displaying data
-Scattergram
-Histogram
-Line Graph
-Bar chart
-Table
What is the purpose of a sign test
To determine whether the difference found in the research is significant or not
What are the 3 conditions for a sign test
-Test of difference
-Repeated measures design
-Nominal data (Data that can be organised into catrgories
What is the accepeted level of probability in psychology (sign test)
5%
(0.05)
What is the S value (sign test)
-The least frequently occuring sign (+ and -)
How is the N value calculated (sign test)
No. of participants - any who got the same result in both conditions (0, no change)
In a sign test, how can it be determined whether the results are significant
If the S value if less than or equal to the critical value, results are significant
What is a one and two tailed hypothesis
One Tailed: directional hypothesis
Two tailed: Non directional hypothesis
What is a peer review
-The assessment of scientific work by other psychologists to ensure that any research intended for publication is of high quality.
-The report is considered in terms of its validity, significance and originality.
What is the purpose of peer review
-To ensure quality and relevance of article and accuracy of findings
-To evaluate the research (methodology, data analysis etc)
-To ensure appropriate allocation of research funding
What is the process of peer review
-Author submits their manuscript to a journal editor
-The journal editor determines whether it is of sufficient quality and appropriate content. If they accept it, then the manuscript is sent to two or more independent reviewers who are experts in the same field as the author.
-The reviewers evaluate the manuscript for its quality, considering its originality, significance and validity to the field. They check for any errors or flaws in the results.
-The reviewers then provide feedback to the editor, who relays it to the author and the author may be asked to revise the manuscript based on the feedback received.
-This process may continue until the manuscript reaches an acceptable standard for publication.
Strengths of peer review
-Protects the quality of published research
-Preserves the reputation of psychology as a science and increases the credibility and status of the subject
Weaknesses of peer review
-Anonymity:
A minority of reviewers may use their anonymous status to criticise rival research.
-Publication bias: Tendency for editors of journals to want to publish ‘headline grabbing’ findings. This means that research that does not meet this criteria is ignored
-Maintaining the status quo:
Reviewers may be more critical of research that contradicts their own view.
