Research Methods Flashcards
Correlation coefficient
Correlation is ranked 1 to -1. Stronger correlation is + or -0.8 or more
Difference between experiments and correlations
- it’s not possible to establish cause and effect using correlation
- it’s an association not a cause
- there may be an association between canine and sleep but there’ll be other variables
Advantages of interviews (structured and unstructured)
- replication is easy (structured)
- can elaborate
Weaknesses of interview (structured and unstructured)
- cannot elaborate (structured)
- very time consuming
- social desirability
Structured interview
- predetermined set of questions that are asked in a fixed order
- conducted in real time
Unstructured interview
- conversational-no set questions
- general aims are discussed and interaction is free flowing
- interviewee is encouraged to expand answers if prompted
Content analysis
- qualitative data
- analysed as typologies, quotations and summaries
- hypotheses are grounded in the data
- coding units are identified and number of times code appears is counted
Process of content analysis
- representative sample collected
- coding units identified
- see how often code appears
Advantages of content analysis
- clear summary of data is established
- reliable
Disadvantages of content analysis
- can be subjective
- reducing coding units removes detail
Advantages of mean
- representative of all data
- takes into account distances between values
Weaknesses of mean
- anomaly’s may distort data
- can’t be used with nominal data
Advantage and disadvantage of mode
+ unaffected by extreme values
- often multiple modes
Advantages of median
- easy to calculate
- unaffected by anomaly’s
Weaknesses of median
- less sensitive as median
- doesn’t reflect exact values
Advantage and disadvantage of range
+ easy to calculate
- affected by extreme values
- doesn’t take into account distribution
Advantage and disadvantage of standard deviation
+ precise measure of distribution
- may hide some characteristics
Qualitative data
Non-numerical values
Quantitative data
Numerical values
Questionnaires
- open: no fixed range of answers, qualitative data
- closed: fixed number of responses, quantitative data
Advantages of questionnaires
- cost effective
- can gather large data
- easy analysis
Disadvantages of questionnaires
- response bias/untruthful
- answer the desirable answer rather than their own
Social desirability
When a person answers what they believe to be desirable rather than what they believe to be right. This affects validity as data collected will support assumptions when really it may not have
Case studies
- in depth, detailed analysis of an individual, group or event. Qualitative data. Longitudinal
- Freud’s little Hans was a case study
Advantages of case studies
- detailed insights that might shed light on unusual and atypical behaviour
- contributed to our understanding of normal functioning
Weaknesses of case studies
- cannot generalise
- subjective selection and interpretation of the researcher
- low validity
- inaccuracy and memory decay
Question asking in an interview (don’t)
- overuse of jargon
- emotional leading questions
- double barrel questions
Thematic analysis
Involves making summaries of data and identifying key themes and categories
Advantages of thematic analysis
- qualitative analysis
- clearing hypothesis during analysis allows for new insights to develop
Disadvantages of thematic analysis
- how to decide categories
- subjective decisions
Role of peer review
- involves all aspects of psychological research being scrutinised by a small group of 2-3 experts in a particular field
- peers should be objective and unknown to researchers
Aims of peer review
- allocate research funding
- validates the quality and relevance of research
- suggest amendments or improvements
Anonymity
- the peer should remain anonymous to maintain honesty
- some reviewers use this to criticise rival researcher to gain better funding
Publication bias
- there is a tendency for editors to publish headline grabbing research so may create a false impression of the current state of psychology if editors are selective
- ground breaking research is buried as reviewers will approve more research that fits current research rather than innovative research
Reporting psychological investigations
- title-should say what the study is about and include IV and DV ‘s
- content page
- abstract-concise summary of the report
- introduction-should review general area of investigation
- procedure-recipe style list of what happened
- results
- conclusions
- references
Hypothesis
A testable statement used to carry out research
Correlational analysis (+ and -)
Two variables having a demonstrated relationship
+ can be used when an experiment is unethical
- no cause and effect established
Aim
A statement of a study’s purpose
Independent variable
Thing that is changed e.g. different groups/conditions
Dependent variable
Thing that is measured/will be affected by changes
Operationalisation
How we are going to measure the variables e.g. after drinking red bull, more words are dais than after drinking water
Randomisation
The use of chance in order to control for the effects of bias when designing materials and deciding the order of conditions
Standardisation
All participants should be subjected to the same environment, information and experience including the same instructions
Extraneous variables
Anything that impacts dependent variable but isn’t independent variable
Confounding variables
Changes systematically with the IV. In some circumstances we might end up with extra IV that is unintentional therefore we are unsure weather DV is the source of change
Ethics
Consideration of what is acceptable or right behaviour in the pursuit of a personal or scientific goal
Informed consent
Knowing aims and giving your permission to take part in the study
Deception
Deliberately misleading or withholding information. If there is spring scientific justification for research, deception is acceptable
Right to withdraw
All participants are able to leave when desired
Confidentiality
Details of participants and research should be kept private
Debrief
Returns the participant to the state they were in before the research
Independent groups (+ and -)
Each participant takes part in one condition
+ no order effects-no boredom or practice
+ fewer demand characteristics
- more participants needed
- individual differences as some are just worse at tasks
Repeated measures (+ and -)
Each participant takes part in both conditions
+ no individual differences as the same person does both conditions
- order effects
- demand characteristics-participants know what experiments expect
Matched pairs
Use of independent measures but each participant in group A is measured with one from group B \+ no order effects \+ controls for individual differences - costly in money and time - difficult to make perfect matches
Demand characteristics
Any cue from the researcher or from the research situation that may be interpreted by the participants as revealing the purpose of the research outcome. Participants may look for cues of how to behave in an experiment
Double blind trial
Neither participants or researcher are aware of aims of investigation
Single blind trial
Participants are unaware of conditions they are in. Attempts to control for the confounding effects of demand characteristics
Quasi experiment
The IV is a naturally existing characteristics between people and has nor been changed by anyone or anything e.g. gender, eye colour etc
Advantages and disadvantages of quasi experiments
+ often carried out under lab conditions
+ enables psychologists to study ‘real’ problems
- participants cannot be randomly allocated to conditions therefore may be confounding variables
- this means we cannot say cause and effect
Naturalistic observation (+ and -)
Studying behaviour in a natural setting where everything has been left as it is normally
+ high external/ecological validity
+ natural environment so generalisable to real life
- replication is difficult
- uncontrolled extraneous variables
Behavioural categories
Devising a set of componente behaviours/checklists
Event sampling
Counting the number of times a certain behaviour occurs in a rather individual/individuals
Time sampling
Recording behaviours in a given time frame e.g. niticijhnwhay an individual is doing every 30 seconds
Controlled observation (+ and -)
When the researcher has some measure of control over the environment e.g. zimbardo, bobo doll
+ easy to replicate
+ control over extraneous variables
- cannot be applied to real life
- may be subjective towards what researcher wants to see
Covert observation (+ and -)
The participants are not aware that they are being observed
+ less ethical issues as no deception
- may be demand characteristics as they know they are being observed
Overt observation (+ and -)
The participants are aware that they are being observed
+ no demand characteristics
- ethical issues as they do not know they are being observed
Participant observation (+ and -)
The observer acts as part of the group being watched
+ increased validity
- ethical issues
- difficulty in recoding observations
Non participant observation (+ and -)
The experimenter does not become part of the group being observed
+ more ethical and objective
- lower validity
Investigator effects
Any effect of the investigators behaviour on the research outcome. Coolican (2006) ‘expectancy effects unconscious cues’
Pilot studies
A small scale verisions of an investigation that takes place before the real investigation is conducted. The Siam is to check they the procedures, materials, measuring scales works nd to allow the research to make changes if necessary
Random sampling (+ and -)
Each participant has an equal chance of selection
+ each participant has equal chance of selection
- sample may not be representative
Volunteer sample (+ and -)
People volunteer to take part in sample
+ quick condiment and ethical
- sample is biased as participants are likely to be motivated
Opportunity sample (+ and -)
People who are participating and available at the time
+ easiest and fastest method
- biased as sample is small
- unlikely to be representative
Types of consent
- presumptive consent
- prior general consent
- retrospective consent
- informed consent
Researcher bias
When the researcher skews the entire process towards a specific research outcome by introducing a systematic error into the sample data
Nominal Data
- data represented in the form of categories ‘how many students drive to school, how many walk etc’
- discrete
- one item can only appear in one category
Ordinal data
- data which is ordered in some way ‘ask everyone in class how much they like 6th form on a scale of 1-10’
- does not have equal intervals between each unit. Someone who rated an 8 enjoys it twice as much as someone who rated it 4
- lacks precision and is subjective
Interval data
Based in numerical scales that include units of equal, precisely defined size. Measurement for height, time and temperature
