Research Methods Flashcards
What types of variables are there (4)
- independent
- dependent
- extraneous
- confounding
What is the independent variable
- variable that the researcher manipulates in order to determine effects on the dependent variable
- may be divided into levels, sometimes referred to as experimental conditions
What is the controlled condition
- a standard against which the experimental conditions can be compared to
- IV is not manipulated at all
What is the dependent variable
- variable being measured
What are extraneous variables
- variables other than the IV that could affect the DV
What are confounding variables
- variables (other than the IV) that have affected the DV
What is operationalisation
- defining the variables and explaining how they would be measured
- necessary for any experiment to be successful
- IV and DV both get operationalised
What are laboratory experiments
- experiment carried out in a controlled environment (lab)
- high amounts of control over IV and eliminate EVs
- participants randomly allocated to condition
- conducted in an artificial setting
What are advantages of lab experiments (3)
- high control
- cause and effect relationship
- replicable => reliable
What are disadvantages of lab experiments (2)
- demand characteristics
- lack of mundane realism / ecological validity => cannot generalise
What are the different types of experiments (4)
- lab
- field
- natural
- quasi
What is a field experiment
- carried out in real world
- IV is manipulated to see effect on DV
What are advantages of field experiments (3)
- high mundane realism / ecological validity => can generalise
- cause and effect
- low chance of demand characteristics
What are disadvantages of field experiments (3)
- low control => low validity
- less control over sample
- hard to replicate
What are natural experiments
- research takes advantage of a naturally occurring IV to see effect on DV
What are advantages of natural experiments (2)
- high mundane realism / ecological validity => can generalise
- useful when it is impossible/unethical to manipulate IV/sample in lab/field experiment
What are disadvantages of natural experiments (3)
- less control
- difficult to replicate
- hard to establish cause and effect
What is a quasi experiment
- contain a naturally occurring IV
- however natural occurring IV is a difference between people that already exists (gender/age)
What are different types of observations (6)
- non participant
- participants
- covert
- overt
- naturalistic
- controlled
What is an observation
- when a research watches or listens to participants engaging in the behaviour that is being studied
What is a non participant observation
- when the researcher does not get directly involved with the interactions of the participants
What is a participant observation
- when the researcher is directly involved with the interactions of the participants
What is an overt observation
- researcher watches and records the behaviour of a group that knows it is being observed by a psychologist
What is a covert observation
- psychologist goes undercover and does not reveal true identity
- group does not know they are being observed
What is a naturalistic observation
- researcher observes participants in their own environment
- no deliberate manipulation of IV
What is a controlled observation
- research observers participants in a controlled environment
- allows for manipulation of IV
What are advantages of a naturalistic observation (3)
- low chance of observer effects
- high mundane realism / ecological validity => can generalise
- useful when manipulation of IV is impossible/unethical
What are disadvantages of a naturalistic observation (2)
- less control => low validity
- hard to determine cause and effect
What are advantages of a controlled observation (2)
- cause and effect can be determined
- high control
What are disadvantages of a controlled observation (2)
- low mundane realism / ecological validity => cannot generalise
- observer bias / observer effects
What are behavioural categories
- specific and observable behaviours to be recorded during an observation
What is observer bias
- observer knows aims of study/hypotheses and this knowledge influences their observations
How can observer bias be avoided (2)
- interrater reliability
- intrarater reliability
What is interrater reliability
- two observer agrees on a conclusion
- each researcher observes the participants at the same time, but records observations independently
- recordings then correlated using an appropriate statistical test to ascertain their level of agreement
What is intrarater reliability
- observation is video recorded so it can be watched several times to identify information that was previously overlooked
What are the the types of behavioural sampling (2)
- time sampling
- event sampling
What is event sampling
- recording every time a certain behaviour or event occurs in a target individual
What is time sampling
- recording all behaviours within a give time frame
What is self report
- when participants provide details of their own feelings, thoughts and/or behaviour to the research
What are the different types of self report techniques (2)
- interviews
- questionnaires
What are interviews
- interviews involve researchers asking questions in face to face situations
- different types
What are the different types of interviews (3)
- structured
- unstructured
- semi structured
What is a structured interview
- all participants asked same questions in the same order
- produces quantitative data
What is an unstructured interview
- informal in depth conversational exchange between interviewer and interviewee
- provides qualitative data
What is a semi structured interview
- combines mixture of structured and unstructured techniques
- quantitative and qualitative data
What are advantages of interviews (2)
- complicated or sensitive issues are best dealt with an interview
- if participants misunderstand a question, this can be clarified
What are disadvantages of interviews (3)
- risk of interviewer effects
- risk of social desirability bias
- training is needed for interviews, and the process can be time consuming and expensive
What are interviewer effects
- when the interviewer may inadvertently affect respondent’s answer
- can be unintentional and may even be a result of the interviewer’s appearance, manner or gender
What is social desirability bias
- people lie to present themselves in a positive light
- particularly when discussing issues that may be socially sensitive
- reduces validity
What are questionnaires
- participants are given a written set of questions and instructions on how to record their answers
- focus on individual’s behaviour, options, beliefs and attitudes
What types of questions can be on questionnaires (2)
- closed questions
- open questions
What are closed questions
- require participants to choose from fixed responses
- quantitative data
- can be collated and displayed easily
- allow for easier comparison
What are open questions
- allow participant to answer in their own words
- qualitative data
- allow respondents to interpret the question as they wish
- develop response with detail/depth
- allow researchers to pursue a line of enquiry that may not have been predicted but comes to light because of a response by an interviewee
What are advantages of questionnaires (3)
- easy to collect large amount of data quickly
- easy to collate when questions are closed
- standardised => replicable
What are disadvantages of questionnaires (3)
- participants may misunderstand questions
- low response rate
- can have sample bias => only suitable for those willing and able to spend time on them => certain people would be more willing to fill in questionnaires
What is correlations
- a technique for analysing the strength and direction of the relationship between two variables
What are the different types of correlations
- positive => as one variable increases, so does the other
- negative => as one variable increases, the other decreases
- no correlation => no relationship between the two variables
What are the advantages of correlations (2)
- strength of relationship can be established
- allows for predictions to be made
What are the disadvantages of correlations (3)
- correlational analysis does not demonstrate cause and effect
- may be a third unknown variable influencing both
- correlation only measures linear relationships, not curvilinear
What is an aim
- precise statement about the purpose of the study and what it intends ro find out
What is a hypothesis
- specific, testable statement about the expected outcome of an investigation
- should be operationalised
- first part of hypothesis needs to address whether the study predicts causation or correlation
What is the difference between causation and correlation
- causation => research predicts a difference in the DV because of manipulation of an IV
- correlation => research predicts a relationship between the two variables being investigated
What are the different types of hypotheses (2)
- null hypothesis => states IV will have no effect on the DV
- alternative hypothesis => predicts IV will have an effect on the DV
=> two categories
What are the different categories for an alternative hypothesis
- non directional hypothesis (two tailed) => does not state direction of predicted differences
- directional hypothesis (one tailed) => states direction of predicted differences
What are pilot studies
- small scale investigations conducted before research
- useful as they help identify whether there needs to be any modifications in the design of the planned study
- also help to determine whether it would be feasible and worthwhile to conduct a full scale study
What is a target population
- group who researchers are studying and want to generalise their results to
- sampling techniques are used to obtain a sample of the target population and are essential to avoid studying entire population
- should be representative
What are the different sampling techniques (5)
- random sampling
- systematic sampling
- stratified sampling
- opportunity sampling
- volunteer sampling
What is random sampling
- every member of the target population has same chance of being selected
- like to be representative so findings can be generalised (positive)
- difficult to get full details of target population and not all selected to take part will be willing to (negative)
What is systematic sampling
- participants are selected by taking every Nth person from a list
- simpler than random (positive)
- can interact with a hidden periodic trait (negative)
What is stratified sampling
- involves classifying the target population into categories and then randomly choosing a sample that consists of participants from each category in the same proportions as they appear in the target population
- all groups in target population included (positive)
- time consuming (negative)
What is opportunity sampling
- selecting participants who are readily available and willing to take part
- easiest and most practical method (positive)
- high chance sample is not representative (negative)
What is volunteer sampling
- people self selecting to take part in a study
- research usually advertises for people to take part in study
- saves time (positive)
- certain type of person is likely to volunteer => unrepresentative (negative)
What is the experiment design
- how the participants are organised
What are the different types of experiment designs
- independent groups
- repeated measures
- matched pairs
What is an independent groups design
- different participants used in each conditioned
- randomly allocated to each condition
What are advantages of independent groups design (3)
- order effects do not occur
- reduced chance of demand characteristics
- same task/materials can be used in all conditions
What are disadvantages of the independent groups design (2)
- more participants needed
- more chance of different results due to participant variables rather than manipulation of IV
What is a repeated measures design
- each participants is tested in all conditions of the experiment
What are order effects
- when the sequence in which participants take part in condition influences their performance
- participants may also get bored/tired when being asked to take part in more than one condition
What are advantages of a repeated measures design (2)
- no participant variables
- half as many people needed compared to independent groups design
What are disadvantages of a repeated measures design (3)
- order effects may affect results => can be avoided by counterbalancing
- demand characteristics more likely
- takes more time, especially if a time gap between different conditions is required
What is counterbalancing
- half participants do condition A then B while other half do the other way
- does not eliminate order effects but controls impact of order effects and allows order effects to be evenly distributed across both conditions
What is a matched pairs design
- different participants are used in all conditions
- however participants in two groups are matched on characteristics that are important for that study
What are advantages of a matched pairs design (3)
- less risk of order effects
- less risk of demand characteristics
- participant variables unlikely as groups have been closely matched
What are the disadvantages of matched pairs design (2)
- twice as many participants needed compared to repeated measures design
- matching process is difficult and time consuming
What are different extraneous variables (3)
- participant variables
- environmental variables
- experimenter variables
What are participant variables in terms of extraneous variables
- characteristics of participant that may affect DV
- matched pairs and repeated measure can prevent this
What are environmental variables in terms of extraneous variables
- factors in the environment that could affect the DV
- avoided through standardisation
What are experimenter variables in terms of extraneous variables
- person collecting data has knowledge of what the research aim is and that knowledge affects data obtained
- can be overcome by double blind technique
What are ethics
- high quality research involves good ethical practise and ethical issues must be fully considered before research is conducted
- most research institutions have ethical committees
What are different forms of ethics (6)
- informed consent
- protection from harm
- right to withdraw
- confidentiality
- deception
- debriefing
Explain what informed consent is
- inform participants about the objectives where possible
- no pressure to consent, can withdraw at any time
- data will be confidential and can ask questions
- full debriefing occurs at the end
- different types
What are the different types of informed consent (3)
- presumptive => consent from people with a similar background to participants => assume they will also consent
- prior general => agree to be deceived but don’t know how or when => aim is withheld
- retrospective => asking for consent after study
Explain what protection from harm is
- researchers have a responsibility to protect participants from physical and psychological harm
- risk of harm should not be greater than in ordinary life
- stop study immediately if they suspect harm
Explain what right to withdraw is
- at start of research, participants should be made aware they can leave at any time
- difficult to implement during covert observations
- should be made aware they can withdraw data in future
Explain what confidentiality is
- participants’ data is confidential and should not be disclosed to anyone unless it has been agreed in advance
- numbers/letters used instead of names when published
Explain what deception is
- cannot intentionally with old information or deliberately mislead them without scientific justification
- sometimes unavoidable to prevent demand characteristics
- ethics committee conducts cost benefit analysis to determine whether potential harm is lower than potential gains
Explain what debriefing is
- takes place after study
- participants told aim of study and information about other conditions
- check welfare
- remind about right to withdraw and right to confidentiality
- allow them to ask questions
- does not provide justification for unethical aspects of research
What is peer review
- process of research proposal being assessed for merit before research is conducted
- panel decides if the research is worth funding
- peer review happens again before research report is published
What happens during a peer review
- psychologists conduct an independent scrutiny of a research report before deciding whether it should be published
- considered in terms of its validity, significance and originality
- appropriateness of the methodology and experimental design used are also assessed
What is the purpose of peer review
- ensure quality and relevance of research, to ensure accuracy of findings, and to evaluate proposed designs
- prevents dissemination of irrelevant findings, unwarranted claims, unacceptable interpretations, personal views and deliberate fraud
What are positive evaluation points for peer review (3)
- increases probability of finding errors
- double blind procedure can be used
- involves specialist psychologist
What are negative evaluation points for peer review (2)
- journals prefer positive results to increase standing => bias in published research => misperception of facts
- can be an unfair process => some reviewers have connections with certain universities => bias/favouritism
How has social influence affect the economy
- understand how behaviours/attitudes change
- used to encourage people to engage in more healthy behaviours
- results in healthier people
- reduced pressure on NHS resources and people taking less time off of work sick, improving productivity
How has memory affect the economy
- cognitive interview
- imporved amount of accurate information
- less money spent on wrongful arrests/imprisonments and wasted police time will be vastly reduced
How has attachment affect the economy
- shown importance of father
- normal for households to have flexible working arrangements
- parents better equipped to maximise income and contribute more effectively to the economy
How has mental health affect the economy
- direct cost of mental health issues on economy in England predicted to be £22.5bn annually
- absence from work costs £15bn /year => 1/3 due to mental health
- research on effective drug therapies have helped people manage mental health and take less time off work
- reduced costs to economy
- also helps improve productivity
What are the different types of data
- quantitative
- qualitative
- primary
- secondary
What is quantitative data
- involves numbers and can be measured objectively
- immediately quantifiable
=> DV
=> closed questions in experiment
=> structured interviews
=> tally of behavioural category in observation
What is qualitative data
- involves words
- based on subjective interpretation of language
- only quantifiable if put into categories and frequency is county
=> open questions
=> transcript from unstructured interview
=> researchers describing what they see in an observation - challenging to analyse as it relies on interpretation and is not easy to collate
What is primary data
- collected directly by researcher for the purpose of the investigation
What is secondary data
- information that was collected for a purpose other than the current use
What is a meta analysis
- the process of combining results from a number of studies on a particular topic to provide an overall view
- allow data to be viewed with more confidence
- results can be generalised to larger populations
- can be prone to publication bias
How can quantitative data be presented
- tables
- bar charts
- histograms
- line graphs
- scattergrams
What are tables
- not raw scores
- converted into descriptive statistics
- paragraph underneath explaining data
What are bar charts
- used for nominal data
- shows frequency data for discrete variables
What are histograms
- used for ordinal and interval data
- bars are proportional to frequencies
What are line graphs
- used for ordinal or interval data
- points connected by lines
- show change in value over time
What are scattergrams
- relationship between covariables
- correlation shown
What are distributions
- normal distribution
=> most people located in middle
=> mean, mode and median all in the middle
=> ends never touch x axis - skewed distribution
=> positive skew => central tendencies on the left side
=> negative skew => central tendencies on the right side
What are descriptive statistics
- analyse data to describe/show/summarise it
- central tendency and dispersion
What are central tendencies
- central value for a set of data
- mean, median, mode
What are measures of dispersion
- how spread the data is
- range => difference between highest and lowest value
- standard deviation => average amount each score differs to mean
What are the different types of statistics
- descriptive
- inferential
What are descriptive statistics
- measures of central tendency and measures of dispersion
What are inferential statistics
- when a sample is used to test something and the findings are generalised to the target population
- inferential statistics are used to see if results are significant
=> work out probability (p) that something occurs due to chance and not the IV
=> accepted level of probability tends to be p<0.05 (less than 5%)
What is a sign test
- can only be used when there is one group of participants and numerical data
=> repeated measures design
=> quantitative data
=> calculating difference between data
How is a sign test carried out
- state hypothesis
- record data and sign (difference between set 1 and set 2) => sign depends on whether difference is positive or negative
- add up + and - values and select the smaller value which is the S value
- find the critical value using N and the table, compare this to the S value => S must be equal to or less than the critical value for significance to be shown
Hypothesis test conclusions
- if S≤Critical Value = Significant
=> reject H0 and accept H1 - if S>Critical Value = Not significant
=> accept H0 and reject H1 - H0 = Null Hypothesis
- H1 = Alternative Hypothesis
What is a content analysis
- method used to analyse qualitative data
=> interview transcripts, documents, texts
=> allows qualitative data to be transferred into quantitative - research uses coding units
=> e.g. positive/negative words and count them
How is a content analysis carried out
- data is collected
- research reads data, making themselves familiar
- research identifies coding units
- data is analysed by applying the coding units
- tally is made of the number of times a coding unit appears
What is a thematic analysis
- method for analysing qualitative data involving identifiying and reporting patterns in material
=> TV ad, interview transcripts
How is a thematic analysis carried out, use the example of an interview
- a transcript of the interview is made
- coding units are used to initially analyse the transcript
- coding units are reviewed to look for themes
What are positive evaluation points for content analyses (3)
- reliable => not open for interpretation
- easy and not time consuming
- allows for statistical analysis to be conducted
What are negative evaluation points for content analyses (2)
- causality cannot be established as it merely describes the data
- cannot extract deeper meaning/explanation from data for the patterns as it is only descriptive
What are case studies
- involve detailed research into an individual/group/institution
- scientific approach
- objective and systematic
What is the significance of case studies
- involve a small sample size
- rare and fascinating behaviour
- can be either qualitative or quantitative data
- can be done over a long time => longitudinal
What are positive evaluation points for case studies (2)
- rich and detailed insights into behaviour => qualitative valid data collected
- can investigate rare/unusual behaviour which would be unethical to do otherwise
What are negative evaluation points for case studies (3)
- small sample size => difficult to generalise, may lead to researcher bias (subjective selection and interpretation of results)
- little control over variables => difficult to establish causal relationship
- rare behaviour difficult to be replicated => reduced reliability
What is reliability
- the consistence of a research study or a measuring test
What are the different types of reliability
- internal reliability
- external reliability
What is internal reliability
- extent to which a measure is consistent within itself
- can be assessed using split half method
What is the split half method
- measures the extent to which all parts of the test contribute equally to what is being measured
- compare results of one half to the other (split in any way)
- if there are similar results, there is internal reliability
What is external reliability
- extent to which a measure varies from one to another
- can be assessed using test retest
What is a test retest
- same test on two separate occasions
- same participants
- results are correlated on scattergraph
- strength can be assessed using Spearman’s Rho or Pearson’s R
- degree of reliability is determined by the correlation and statistical table
- should have a correlation of 0.8 for a strong correlation => same with interrater reliability
What is validity
- whether a measure is actually measuring what it intends to
What are the different types of validity
- internal validity
- external validity
What is internal validity
- when effects observed are due to the IV and not chance
- causal relationship can be established
- improved by controlling EV
=> standardises instructions, counterbalancing - different types
What are the different types of internal validity
- face validity => when something appears at first sight to represent what is being measured
=> improved by expert examination - concurrent validity => validity of a new test can be compared to an older established test where the validity is known (e.g. Stanford-Binet IQ Test)
=> improved by removing irrelevant and ambiguous questions
What is external validity
- extent to which findings can be generalised
=> improved by using natural settings and random sampling
What are the different types of external validity
- ecological validity => accurately reflects normal circumstances
- temporal validity => reflects behaviour at different time periods
- population validity => generalised to the wider population
What are the key features of science
- empirical methods
- paradigms and paradigm shifts
- objectivity
- replicability
- falsifiability
- theory construction
Explain empirical methods as a feature of science
- method of gaining knowledge which relies on direct observations or testing
- separates unfounded beliefs from real truth
Explain paradigms are a feature of science
- shared set of assumptions and agreed methods
=> psychology is seen as a pre science
=> lacks universal acceptance of paradigms
=> too many internal disagreements and conflicting approaches
Explain paradigm shifts are a feature of science
- when the results of a scientific revolution occurs
- a signing change in the dominant unifying theory of a scientific discipline occurs and causes a paradigm shift
- occurs in two stages
What are the two stages of a paradigm shift
- one theory remains dominant
=> some researchers question the accepted paradigm and have contradictory research that disagrees
=> counter evidence accumulates against main paradigm
=> present paradigm might then be overthrown due to emergence of a new one - established science makes rapid progress and a scientific revolution occurs due to the paradigm shift
Explain objectivity are a feature of science
- dealing with facts in a way that is unaffected by beliefs, options, feelings or expectations
- good researcher keeps a critical distance from research
- high objectivity makes research replicable
- basis of empirical method
Explain replicability are a feature of science
- extent to which findings can be repeated in different contexts and settings
=> guarding against scientific fraud
=> check to see if results were gained due to a fluke cause by EV or CV
=> reliable
=> validity - highest in lab, lowest in observations
Explain falsifiability are a feature of science
- the notion that scientific theories can potentially be disproved by evidence
- Popper (1969) => genuine scientific theories should be tested if not been proven false - yet
=> good sciences are constantly challenged => not disproved as strong
=> pseudoscience cannot be falsified, e.g. Freud
Explain theory construction are a feature of science
- constructed via hypothesis testing and retesting
- based on results of a range of work conducted by many researchers
- must be testable and falsifiable
- split into two methods
What are the methods of theory construction
- deductive reasoning
- inductive reasoning
Explain the stages of deductive reasoning
- propose a theory
- develop a hypothesis
- test the theory
- draw conclusions
Explain the stages of inductive reasoning
- observe facts about the environment
- develop a hypothesis
- test the hypothesis
- draw a conclusion
- devise a theory
What are the different components of a psychological report (7)
- title
- abstract
- introduction
- method
- results
- discussion
- reference
Explain the title component of a psychological report
- provide a clear focus involving key variables
Explain the abstract component of a psychological report and what is included (10)
- conscious summary => 150-200 words
- background research
- aims
- H0
- H1
- research methods and procedure
- experimental design
- sample used and sampling method
- brief account of findings => statistical test, results, significance level
- conclusion
- limitations/implications
Explain the introduction component of a psychological report
- previous research (review of related research)
- why it was studied
- general discussion => become focused
- aim (maybe H0 and H1)
Explain the method component of a psychological report
- design
- sample
- apparatus / materials
- procedure
Explain the results component of a psychological report
- descriptive statistics
- inferential statistics
- qualitative data => categories and themes
- H0 and H1, accepted or rejected
Explain the discussion component of a psychological report
- interpret results
=> summary (some explanation about results)
=> relationship to background research
=> limitations of methodology and modifications
=> implications and suggestions
Explain the reference component of a psychological report
- full details of journals / books referenced
- journal references
=> surname, first name, date of publication, title, volume, page number - book references
=> surname, first name, title, place of publication, publisher
What is the level of statistical significance, chance, significance level and probability
- LoSS => level at which H0 is rejected
- chance => something which has no real cause
- SL => level of testing
- p => a numerical measure that determines whether results are due to chance or are significant
What is the conventional SL used
- p<0.05 or less than 5%
- probability the findings were due to chance is 5%
- 1% is used for critical and important findings
What are the different types of errors that can occur from hypothesis testing
- Type I => rejected H0 even though the findings were due to chance
- Type II => accepted H0 even though there was a real difference
What are levels of measurement
- used to try categorise data into types so most appropriate statistical test can be used
What are the different levels of measurement
- nominal
- ordinal
- interval
Explain nominal as a level of measurement
- categorical
- the data consists of the numbers of participants that might fall into different categories
- person can only be placed in one category
Explain ordinal as a level of measurement
- ordered
- data can be placed in rank order from lowest to highest
- ordinal scale can consist of measurements than are of unequal intervals
- data is concerned with the order that the data can be presented in
Explain interval as a level of measurement
- data has fixed and even intervals (differs from ordinal data and that has unequal intervals)
- units of data are fixed and have the same distance throughout the range
What are different types of statistical tests
- parametric
- non parametric
What are examples of parametric tests
- Pearson’s R
- Related T Test
- Unrelated T Test
What are examples of nonparametric tests
- Chi Squared
- Sign Test
- Spearman’s Rho
- Mann Whitney
- Wilcoxon
How to decide which statistical test to you
- does the research involve a test of difference or a test of association/correlation
- if research uses a test of difference, is it an independent measures design or a repeated measures/matched pairs
- which level of measurement is being used: nominal, ordinal or interval
- is the test parametric or non parametric
What is a way to remember statistical tests
- carrots should come
- mashed with swede
- under roast potatoes
What is the table for statistical tests
KNOW THIS
When doing a non parametric test, what do you need to look out for
- Spearman’s Rho => calculated value ≥ critical value
- Sign Test => calculated value ≤ critical value
- Mann Whitney => calculated value ≤ critical value
- Chi Squared => calculated value ≥ critical value
- Wilcoxon => calculated value ≤ critical value
Explain Spearman’s Rho
- used when we wish to test relationship or correlation between two variables
- data should be ordinal
- data are in related pairs
- non parametric test
- calculates strength between two variables
Explain Mann Whitney
- test used when we are looking for a test of difference
- used when we have an independent group design
- data is ordinal or interval
- test is non parametric
Explain Chi Squared
- can be used for either a test of association or for a test of difference
- used for test of difference if there is an independent measures design
- nominal data
- non parametric test
Explain Wilcoxon
- measure test do difference
- repeated measures design or matched pairs design
- data is ordinal
- non parametric test
How to justify using a non parametric test
- refer to whether it was a test of difference, correlation or association, what design was used and what the level of measurement was
- calculate results of statistical test
- compare results to critical value
- mention SL selected and whether hypothesis was one or two tailed
- state whether experimental and null hypothesis were accepted or rejected
When doing a parametric test, what do you need to look out for
- Related T Test => calculated value ≥ critical value
- Unrelated T Test => calculated value ≥ critical value
- Pearson’s R => calculated value ≥ critical value
Explain Related T Test
- used when we wish to test a difference
- repeated measures
- interval data
- parametric test
Explain Unrelated T Test
- looking for a test of difference
- independent group design
- level of measurement is interval
- parametric test
Explain Pearson’s R
- investigates correlations or relationships between variables
- level of measurement is interval
- parametric test