Research methods Flashcards
What is an aim?
The purpose of a study, what the researcher intends to investigate
What is a directional hypothesis?
Shows the direction of the relationship between the variables
What is a non-directional hypothesis?
Does not show direction/difference between the variables
What is the experimental method?
Manipulation of the independent variable to see what effect this has on the dependent variable
When is it suitable to use a directional hypothesis?
When there is previous research which suggests a particular outcome
When is it suitable to use a non directional hypothesis?
When there is no previous research on what is being studied
What is the operationalisation of variables?
Clearly defining variables so they can be measured in an experiment
e.g- Anger: punching, screaming, kicking, shouting
What are extraneous variables?
Only thing that should influence the DV is the IV
Extraneous variables influence the DV/IV if not controlled, they do not vary systematically with the IV
What are confounding variables?
Like an extraneous variable but confounding variables do vary systematically with the IV. As a result it is difficult to see if change in the DV is caused by the IV or confounding variable.
What are demand characteristics?
Cues from the researcher or research situation that reveal the purpose of the experiment therefore participants may change their behaviour in order to meet the aims of the study.
What are investigator effects?
Any effect of the investigators behaviour on the DV such as the design of the study or interaction with participants during the study.
What is randomisation?
Use of chance methods to control bias effects when designing a study (to be able to control investigator effects)
What is standardisation?
Using all the same procedures and instructions throughout the study to all participants.
What are experimental designs?
How participants are arranged in experiments.
What are independent groups?
Two separate groups experience two separate conditions to allow for a comparison
What are the evaluations of independent groups?
Strengths:
Order effects are not a problem
Participants are less likely to guess the aims of the study as thy do not perform more than one condition of the experiment
Limitations:
Time consuming and costly compared to repeated measures design as each participant contributes to one single result
Differences between participants in the same groups (acts as a confounding variable) so researcher may not know if the DV has affected the IV
What are repeated measures?
All participants take part in all conditions of the experiment
What are the evaluations of repeated measures?
Strengths:
Participant variables are controlled -> higher validity
Fewer participants are needed so less time consuming when recruiting people
Limitations:
Order may be important in which participants do the tasks
Order effects can come about as participants may be bored/tired which affects their performance
What are matched pairs?
Participants are paired together based on a variable that can affect the dependant variable
What are the evaluations of matched pairs?
Strengths:
Order effects/demand characteristics are not a big problem as participants only take part in one condition
Weaknesses:
Participants can never be matched exactly which can have an effect on the DV
Can be time consuming if a pre test is required and to match all participants together
What is counterbalancing?
Attempt to control for the order effects in a repeated design - half of participants experience the conditions in one order and the other half in the opposite order
What are the different types of experiments?
Lab, Field, Quasi and Natural
What is a lab experiment?
Takes place in a highly controlled environment where the researcher manipulates the IV to see the effect on the DV as well as controlling any extraneous variables
What are the evaluations of lab experiments?
Strengths:
Control over confounding variables and extraneous variables so there is high internal validity (researcher can make sure the IV is the only thing having an affect on the DV)
Easy to replicate
Limitations
Lack of generalisability as the environment isn’t likely to be natural and more artificial compared to everyday life -> participants may behave unusually (low external validity)
Problem of demand characteristics as they may know they are being tested
What is a field experiment?
IV is manipulated in a natural setting so the researcher goes to the participants usual environment
What are the evaluations of field experiments?
Strengths:
Higher mundane realism than lab experiments as it takes place in a natural environment -> behaviour is more likely to be valid
High external validity as participants are unlikely to know that they are being tested
Limitations:
Hard to control confounding variables and extraneous variables so replication may not be possible
Ethical issues -> participants are unable to give consent to take part in the experiment
What is a natural experiment?
Researcher has no control over the IV or DV and they cannot change it. DV can be naturally occurring.
What are the evaluations of natural experiments?
Strengths:
Experiments may have never been done before/ wouldn’t have been done due to ethical or practical reasons
Have high external validity due to studying real life issues
Limitations:
Happens rarely so there is little opportunity for research
Participants cannot be randomly allocated to experimental conditions so it is hard to tell if the IV affected the DV
What is a quasi experiment?
IV is based on existing differences between people (like age/gender) and the independent variable cannot be changed. DV may also be naturally occurring.
What are the evaluations of quasi experiments?
Strengths:
Carried out under controlled conditions -> can easily replicate data
Limitations:
Cannot randomly allocate participants so there may be confounding variables
Researcher cannot claim that the IV has caused any observational changes as it is not manipulated
What is a random sample?
All participants have an equal chance of being selected
People are selected through a lottery method
What are the evaluations of random sampling?
Strengths:
Unbiased and objective
Representative
Limitations
Time consuming
People may refuse to take part
What is a systematic sample?
Every nth member of the target population is selected using a sampling frame (list of population is organised into an order -> alphabetical)
What are the evaluations of systematic sampling?
Strengths:
Unbiased and objective
Limitations:
Time consuming
Difficult to obtain a complete list of the whole population
What is a stratified sample?
Dividing the target population into sub categories then select the participants based on the proportion of that category
What are the evaluations of stratified sampling?
Strengths:
Produces a representative sample -> generalisable
Limitations:
Categories do not represent every way that people are different
Can be time consuming to select categories/select participants based on these
What is an opportunity sample?
Selecting people that are available at the time of the experiment
What are the evaluations of opportunity sampling?
Strengths:
Low cost
Less time consuming
Limitations:
Unrepresentative as only takes place in one location
Researcher may be biased
What is a volunteer sample?
People choose to take part in the study
What are the evaluations of volunteer sampling?
Strengths:
Less time consuming
Engaged participants
Limitations:
Volunteers may be interested in the study therefore demand characteristics could be a problem -> effects generalisability
What does DRIPP stand for (ethical issues)
Deception Right to withdraw Informed consent Protection from harm Privacy and confidentialty
What is deception?
Misleading/withholding information from participants
What is right to withdraw?
Participants are allowed to leave the study at any time
What is informed consent?
Making participants aware of the aims of the research, procedures, their rights + what data will be used
What is protection from harm?
Participants should be protected from physical and psychological harm
What is privacy and confidentiality?
Participants have the right to control information about themselves and their personal data should be protected
What is the BPS code of conduct?
British Psychological society has a code of ethical conduct and researchers should use these when conducting a study
How is informed consent dealt with?
Participants should get a consent letter/form to sign in order to agree with the experiment
How is deception and protection from harm dealt with?
Participants should all be given a full debrief at the end of the study so that they know the true aims and full details. Also they should know what their data is being used for and have the right to withhold this data.
Researchers should also offer counselling if participants experienced any stress during the study.
How is confidentiality dealt with?
Researchers should maintain anonymity of participants throughout the study and ensure that their data will be protected/remain anonymous.
What is cost-benefit analysis?
Weighing up the pros and cons of the study to see if it should go ahead
What is a pilot study?
Small-scale trial run of the investigation
What is the purpose of a pilot study?
Allows researchers to identify any issues and know if any changes need to be made in order to save time and money.
What is a single blinded procedure?
Researcher is aware of the test being conducted but participants are not told and details or aims until the study is over. This is to reduce the effects of demand characteristics
What is a double blinded procedure?
Both the participants and the researcher are not aware of the aims of the study -> important for drug trials
What is naturalistic observation?
Watching and recording behaviour in a setting where it would usually occur
What is a controlled observation?
Watching and recording in a controlled/structured setting -> variables are managed
What is a covert observation?
Participants behaviour is watched and recorded without them knowing/any consent given
What is an overt observation?
Participants behaviour is watched and recorded with them knowledge/they gave consent
What is a participant observation?
Researcher becomes a member of the group they are watching/recording
What is a non-participant observation?
Researcher is not part of the group they are watching/recording
What are the evaluations of all observations?
Strengths:
Can see what people do -> unexpected behaviour therefore there is special insight into a person’s behaviour
Limitations:
Observer bias -> observers interpretation of a situation may be affected by their expectations
Observational studies do not show casual relationships (may detect cause and effect relationships however)
What are the evaluations of Naturalistic observations?
Strengths:
High external validity as findings can be generalised to everyday life
Weaknesses:
Replication of the study is difficult -> as lacks control
May be confounding/extraneous variables
What are the evaluations of Controlled observations?
Strengths:
No issues with confounding/extraneous variables so replication is easier
Weaknesses:
Findings cannot easily be generalised to everyday life
What are the evaluations of Covert observations?
Strengths:
No issues with demand characteristics -> higher internal validity
Weaknesses:
Not very ethical as no informed consent is given by participants
What are the evaluations of Overt observations?
Strengths:
More ethically acceptable
Weaknesses:
As participants know that they are being watched, demand characteristics may become a problem
What are the evaluations of Participant observations?
Strengths:
Increased insight into the lives of people -> increase in external validity
Weaknesses:
Researcher may lose objectivity if they identify too strongly with participants
What are the evaluations of Non-participant observations?
Strengths:
Less danger of loosing objectivity of the study
Weaknesses:
Will most likely loose valuable info about the lives of participants
May miss info
What are the differences between observations and experiments?
Observations have no independent variable that is being manipulated by the researcher whereas in an experiment there is an IV
What are the issues in observational design?
Ways of recording data
Behavioural categories
Sampling methods
What are the ways of recording data?
Unstructured -> Writing everything that is seen
Structured -> Using behavioural categories
What are behavioural categories?
Breaks the target behaviour into categories -> behaviour checklist
What is Event sampling?
Counting the number of times a particular behaviour occurs in a target individual/group
What is Time sampling?
Recording behaviour seen in a pre-established time frame
What is Inter-rater reliability?
Two or more observers agree on behaviour seen -> there is a positive correlation between their scores and high agreeability
What are the evaluations of Structured observations?
Strengths:
Data recording is easier/more systematic
Data is likely to be quantitative-> easier to analyse
Weaknesses:
Not as much detail so information may not be very helpful
What are the evaluations of Unstructured observations?
Strengths:
More depth of detail
Weaknesses:
Procedures qualitative data (harder to record/analyse)
Greater risk of observer bias
What are the evaluations of Behavioural categories?
Strengths:
Makes data collection more structured/objective
Weaknesses:
Categories have to be very clear/unambiguous which can be difficult
What are the evaluations of Time sampling?
Strengths:
Reduces the number of observations that have to be made
Weaknesses:
Time frame may not be representative of the data collected
What are the evaluations of Event sampling?
Strengths:
Useful when target behaviour occurs infrequently which could be missed if time sampling was used
Weaknesses:
If event is too complex, observer may overlook important details
What are questionnaires and their purpose?
Pre-set list of questions that participant responds to
Used to assess thoughts/feelings and dependant variable
What is an open question? + what data do they produce
No fixed range of answers, participants can respond how they wish
Mainly produce qualitative data, which is very detailed but difficult to analyse
What is a closed question? + what data do they produce
Fixed response
Produces quantitative data, which is easy to analyse but there is little detail
What are the 3 types of interview?
Structured- Pre determined set of questions asked in a fixed order
Unstructured- No set questions but there is a general topic, interviewee can expand/elaborate
Semi-structured- (e.g job interview) List of questions have been decided beforehand but the interviewer can also ask more questions based on previous answers
What are the evaluations of Questionnaires?
Strengths:
Cost effective -> lots of info can be gathered quickly as they can be distributed to a large amount of people quickly
Data is easy to analyse
Researcher does not need to be present
Comparisons can be made between responses
Weaknesses:
Responses may not be truthful
Produce a response bias (respondents reply in a similar way) + -acquiescence bias- which is the tendency to agree with questions on a questionnaire.
What are the evaluations of Structured interviews?
Strengths:
Straightforward to replicate due to standard format
The format reduces differences between interviewers
Weaknesses:
Not possible to elaborate on different topics so there is not a lot of depth/no unexpected info
What are the evaluations of Unstructured interviews?
Strengths:
More flexibility
Gain more info/world view of interviewee
Weaknesses:
Interviewer bias
Difficult to analyse data/make conclusions
Interviewees may lie due to social desirability
What is the difference between reliability and validity?
Reliability-> consistency of the study/data (if study was repeated, same results should be obtained)
Validity-> does the method measure what its supposed to
What are the evaluations of Open questions?
Strengths:
Allows respondents to answer how they want
Generate qualitative data
In-depth responses
Weaknesses:
Time consuming to answer
What are the evaluations of Closed questions?
Strengths:
Easy to analyse response
Quicker to gather
Weaknesses:
Forces respondents to select an answer that may not represent their real thoughts
What are Likert scales?
Respondent indicates their agreement with a statement
Strongly agree -> Strongly disagree
What are rating scales?
Respondents select a value that represents their strength of feeling towards a statement
(1 -> very entertaining, 5-> not entertaining at all)
What is fixed-choice option?
A list of possible options and respondents have to select all that applies to them
What are the things that make a bad question? + what do these mean?
Overuse of jargon
-Using complex words that a normal person would not understand
Emotive language/leading questions
- Questions should not include any words that may influence a persons answer
- Leading questions guide people towards a certain answer
Double-barrelled questions and double negatives
- There should not be two questions in one as respondents may agree with one half of the question but not the other
- Double negative questions make it difficult for respondents to answer
What is a correlation?
Used to investigate an association between co-variables
What is a positive correlation?
As one co-variable increases so does the other
What is a negative correlation?
As one co-variable increases the other decreases
What is a zero correlation?
There is no relationship between the co-variables
What is the difference between correlations and experiments?
Correlations involve no manipulation of variables so it is not possible to establish a cause and effect relationship between co-variables
On the other hand experiments the researcher in an experiment controls the IV to measure the effect on the dependent variable
What are the evaluations of correlations?
Strengths:
Show how two variables are related, if there is a strong correlation this can lead to further research
Quick/economical to carry out as a controlled environment is not required + secondary data can be used
Limitations:
Do not tell us the reason why variables are related
Don’t demonstrate a cause and effect relationship
Can be misinterpreted so relationships can be presented as facts which is not true
What are measures of central tendency?
Mean
Median
Mode
What are the measures of dispersion?
Range
Standard deviation
What is standard deviation?
Measures how spread out data is from the mean
What does a small standard deviation indicate?
Most values in the data were close to the average score -> no high / low values
What does a large standard deviation indicate?
There is a large spread in the data
- > some high / low values
- > higher peak on graph
What is the difference between positively and negatively skewed?
Positively:
Mean is towards left of peak due to higher scores which causes a higher mean value
Negatively:
Mean is towards the right of the peak due to lower scores which caused a lower mean value
How can quantitative data be presented?
Scattergram
Bar chart
Histogram
Line graph
What type of data do bar charts present?
Discreet data, data that is placed in categories
What type of data do histograms present?
Continuous data like time
What are the differences between bar charts/histograms?
Bar charts-> Bars do not touch
Histograms-> Bars touch each other + heigh shows frequency
What do line graphs present? + what is their purpose?
Numerical/continuous data
Can be used to make estimations about scores
Points are joined by straight lines
What is qualitative data?
Data expressed in words/non numerical
What is quantitative data?
Data expressed in numbers
What is primary data?
Data collected yourself
-> interviews, questionnaires, observations, physical testings
What is secondary data?
Data already collected by others
-> government, publications, books, journals, articles, websites, social media
What is meta analysis? + what are the evaluations of this?
Number of studies which investigate the same aims/hypothesis to form a joint conclusion
Strengths:
Allows us to create a larger and varied sample therefore data can be generalised across a population so validity increases
Weaknesses:
Prone to publication bias as researcher may not select all relevant studies so conclusions will be based and may not represent all data
What are the evaluations of primary data?
Strengths:
Unbiased
Up to data
Reliability-> lots of controls, IV and DV are operationalised
Weaknesses:
Time consuming
Expensive
May not be feasible in some cases
What are the evaluations of secondary data?
Strengths:
Cheaper than primary
Quicker as background work already done
Ethical as do not need to worry about informed consent etc
Weaknesses:
May be outdated/incomplete
May not be specific enough
Mixed validity to studies
What are the evaluations of qualitative data?
Strengths:
Rich detail -> higher external validity
Weaknesses:
Difficult to analyse so its hard to find patterns
What are the evaluations of quantitative data?
Strengths:
Simple to analyse so comparisons are easily drawn
Data is objective and less open to bias
Weaknesses:
Little detail
What is peer review?
Assessment of scientific work by others who are specialists in the same world to ensure that research that will be published is high quality
What are the main aims of peer review?
- Allocate research funding
- Validate the quality and relevance of research
- Suggest improvement/amendments
What are the problems of peer review?
Publication bias
Valued work may be disregarded if it is seen to not be significant enough therefore journalists are selective in what they published which doesn’t show the true light of psychology
Burying groundbreaking research
Peer review may slow down the rate of change in a particular field of science
What is the purpose of the sign test?
Statistical test which analyses differences in scores between related items to see if they are significant (or not)
What are the conditions required to use the sign test?
- Need to look for difference rather than association
- Need to use a repeated measures design
- Need nominal data - data organised into categories
What are the steps of the sign test?
- Work out the sign - has the scores gone up or down (for each person/value)
- Calculate the S value - number of times less frequent time occurs (not including any nil scores)
- Calculate the value of N - the total number of scores excluding nil scores
- Read critical value S using value table
- Determine whether the result is significant - If the S value less than/equal to critical value it is not significant (has to be greater to be significant)
