Research Methods 1 revision
- Created by: Bambih369
- Created on: 23-03-21 08:52
Quantitative research
Experimental design
- · Between- groups (Independent measures) - Compare different participants in different conditions.
+ No carry-over effects.
+ Process is quicker for participants.
- Individual differences
- Twice the number of participants needed.
- · Within-groups - Compare the same participants in different conditions.
+ Individual differences reduced.
+ Fewer participants needed.
- Boredom.
- Carry-over effects.
Quantitative research
Validity
· Validity = the extent to which your study measures what you intended it to measure.
- Face = Do items on a test appear to measure what they said they would?
- Predictive = Can test scores be used to predict events?
- Concurrent = Do scores correlate with other measures taken at the same time?
- Construct = Does the test measure the construct it was designed to measure?
- Ecological = The extent to which the experiment reflects the real world.
Quantitative research
- Reliability = the extent to which a measure produces consistent results
- External reliability (Relates to consistency of a test over time)
- Test using test-retest reliability = assess the correlation between scores taken at 2 points in the time from the same sample.
- Internal reliability (Is the test consistent within itself?)
- Test using the split-half method or Cronbach’s alpha.
Quantitative research
Variables (e.g. IV, DV, extraneous)
- Independent variable = The variable which is manipulated by the researcher (causal variable).
- Dependent variable = The variable which is measured.
- Extraneous variable = variables that potentially affect the relationship of the IV and DV.
- Confounding variable = variables that differ systematically with the IV.
- To prevent confounding variables we can do 3 things:
1. Match conditions of key variables e.g age
2. Standardise the procedure
3. Randomise the sample
- Control variable = The condition when the IV is absent.
Quantitative research
Evaluating research
1. Individual differences - Randomly allocate.
- Use a within-subjects design.
2. Practice effects - Use a between-subjects design.
3. Demand characteristics - Use a between-subjects design.
- Deception.
4. Situational variables - Think more carefully when designing the study.
5. Floor and ceiling effects - Use a pilot study
6. Boredom/tired - Counterbalance
- Rest breaks
- Between-subjects design
Quantitative research
Hypothesis testing
· Null hypothesis = no difference will occur
· Alternate hypothesis = A difference will occur
- Directional (one-tailed) = Prior research
- Non-directional (two-tailed) = no prior research
Quantitative research
Types of studies (e.g. experimental, cross-sectional)
· Experiments explore causal relationships and manipulate the values of the independent variable to see if there is any effects in the dependent variable.
· To control for chance differences, we can use random allocation of participants.
· Quasi-experiments occur when the researcher cannot randomly allocate participants to the IV condition, as the change is naturally occurring.
Quantitative research
Sampling
- Random sampling (Leads to representative sample)
1. Simple random sample – everyone has an equal chance of being picked.
2. Stratified sample – The population is divided into groups and a simple sample is conducted on each.
- Non-random sampling (Less representative)
1. Voluntary sample – Members of the population self-select themselves to participate. It becomes a snowball effect if they ask their friends to participate.
2. Convenience sample – Researchers ask members of the population who are easy to reach.
Quantitative research
Effect size
· A measurement of the magnitude of the effect.
- If the effect is small, ensure the experiment is designed well enough to have a chance.
Effect size = (Mean of cond. 1 – Mean of cond. 2)
Pooled Standard deviation of both
Writing reports
Referencing
· Journal article – Surname, Initials. (year). Title. Title of the journal, Volume (Issue). DOI.
· Important to acknowledge the author to avoid plagiarism and give credibility to work.
Writing reports
Structuring sections
- Title
- Abstract
- Introduction - Overview of the topic , Relevant research, Gap in the literature, Aims and hypotheses.
- Method - Design, Participants, Materials, Procedure
- Results - Report and describe results relevant to the research question, No raw data, No rationale
- Discussion - Summarise key findings, Interpret results, Discuss limitations and wider implications.
- References
- Appendices
Writing reports
Extracting key information from an abstract
· Searching for background Info = Introduction
· Looking for the design of the study = Method
· Future research = discussion
Choosing a research design
Selecting research design to suit hypotheses
· Psychological investigations:
- Experiments (Cause + effect)
- Observations (Initial investigations)
- Qualitative (In-depth understanding)
- Cross-sectional (Relationships)
Choosing a research design
- Observational studies
- Ask several research questions
- Unstructured – Researchers record behaviour they see and monitor aspects of the phenomenon relevant.
+ Qualitative data
+ Rich and detailed
- Subjective?
- Structured – Researchers do not observe anything. Predetermined behaviours are observed.
+ Quantitative
+ Objective
+ Observer consistency
- May miss details
Choosing a research design
- Cross-sectional research
- Usually consist of questionnaires
- Gives rise to correlational data
+ Naturalistic
+ Can recruit lots of participants
+ Ask lots of questions
+ Investigate many topics
+ Can measure many variables at once
+ Stronger if use validated scales
- People may not tell the truth
- Can not infer causality
Choosing a research design
- Longitudinal studies
- Repeated observations over an extended period of time
- Usually, cross-sectional
- Advanced experimental design
- More than 1 Independent variable
- Factorial
- Explore how variables interact
Ethics
Principles
1. Respect
- Informed consent
2. Competence
3. Responsibility
- Deception
- Protection from harm
- Debriefing
- Confidentiality
4. Integrity
Ethics - Ethical requirements
- Informed consent
- Participant information screen
- What the study’s aims are and what it will entail
- Contact details
- Deception
- Only used when necessary
- Explain as early as possible in the study
- Protection
- Put in place resources for support
- Potential harm should be made explicit
- Debriefing
- Tell the true aims at the end of study
Qualitative research
What is qualitative data?
· Focuses on the smaller picture
· Gains rich descriptive and possible explanations of peoples meaning making.
Advantages of qualitative research
+ Can answer the ’how’ and ‘why’ questions
+ Help make sense of patterns
+ Can help generate theories
Qualitative research
Approaches to qualitative research
· Insiders
- Researchers who share similar backgrounds to the group being studied
+ Greater understanding of issues and more aware of ethical issues
- Lack critical distance, biased observation
- Participants may treat you as a friend
· Outsiders
- Researchers do not share similar backgrounds
+ Make conclusions insiders could not
- Unable to understand experiences
- Miss contextual aspects
Qualitative research
Methods of data collection
- Ethnography
- Immersion in a particular group
- Examine group for a period of time and observe behaviour
- Issues: - Gaining access, Structured or unstructured?, Video record?
- Meta data - Newspaper, Tv programmes, Radio programmes
- Diaries and documentaries
- Diaries are often used in health psychology
- Documents = letter or autobiographies
- Internet-mediated research - Publicly available research
- Issues: - Ethics – Best to ask for consent
- · Naturally occurring data - Produced without intervention of researcher
Qualitative research - Interviews
- Semi structured interviews
- Most widely used in qualitative research
- Issues to consider: - What questions to use to get to research question?
- Who and how to recruit?
- Where to interview?
- How to record?
- How to transcribe?
- Interview schedule
- Guides the interview
- Forces the researcher to explicitly think about what to cover
- Potential difficulties
Qualitative research - Interview questions
- Types of questions
- Descriptive - Participants provide an account
- Structural - How the participant organises knowledge
- Contrast - Participants make comparisons between events and experience
- Evaluative - Feelings towards something
- Probing - Explain more
- Questions to avoid: - Closed questions, 2 in 1 Questions, Value laden questions, Jargon, Questions that do not make sense
Qualitative research - Focus groups
- Focus groups
- 4-8 participants recruited under some remit
- Informal group discussions that are focused
- Facilitates personal discussions
- Issues: - How many pts?
- Session prep
- Ethics (Permission)
- Ethical considerations
- Access to people
- Vulnerable pts
- Skills to handle difficulties
- Withdrawal
Qualitative research
Thematic analysis
- Simplest method of data analysis - Rich and detailed data
- ‘Method for identifying, analysing, & reporting patterns in data.’
- Themes - Prevalent across the data set
- Captures something important in relation to research question
TA steps:
1. Transcription of data
2. Make notes of 1st impressions
3. Initial coding of data
4. Gradually move from descriptive to conceptual themes
Qualitative research
- Inductive
- Data driven
- ‘Bottom up’
- No pre-existing coding frame
- Theoretical
- Driven by interest
- ‘Top down’
- Rich descriptive data and more detailed analysis
Measuring people
- Reaction time
- Stimulus, Perception, Processing, Produce response, Response
- Provides an indirect measure of mental processes
- Types of RT: - Simple choice RT – 1 type of stimulus; 1 type of response
- Choice RT – 1+ stimulus; each with its own response
- Discriminant reaction time – 1+ stimulus; pts only responds to 1
Measuring people
- Positron emission tomography (PET)
- Uptake of glucose is greater in active brain areas
- A radioactive substance is injected into the bloodstream
- Active cells take up the substance readily
- Use the subtraction method
- Evaluation:
+ Creates high spatial res. Images
- Poor temporal res.
- Individual exposed to radioactive substances, so limits number of scans
Measuring people
- Functional Magnetic resonance imaging (fMRI)
- Active brain regions require more oxygen so blood flow increases
- Oxygenated blood produces a different signal to deoxygenated blood
- Evaluation:
+ Nothing is injected to pts
+ Better spatial res.
- Poor temporal res.
Measuring people
- Transcranial magnetic stimulation (TMS)
- Used to establish cause and effect
- Magnetic field applied to scalp, inhibiting neurons below
Measuring people
- Electroencephalography (EEG)
- Measures brain’s electrical activity
- Electrodes attracted to scalp
- Different waveforms produced reflect different functional states of the brain
Measuring people
- Event related potentials
- Interested in EEG waves in response to psychological events
- Peaks observed in ERP
- Researchers interested in how the task conditions affect the amplitude and latency
- Evalution:
+ Excellent temporal res.
- Poor spatial res.
Measuring people
- Test items
- Items take the form of closed questions or statement
- Psychological scales provide quantitative data
- Derived from theory and research
- Response biases
- Acquiescence bias = Tendency to respond positively to all items
- Response bias = Tendency to give the same response to all items
Philosophy, Science and Open Science
Philosophy of Science
- Science = a systematic enterprise that builds knowledge in testable explanations
- Foundations in empiricism
- The scientific method:
1. Create hypotheses
2. Test hypotheses with observations
3. Accept/Refute hypotheses
4. Integrate findings into theory
· Carefully design the study and eliminate bias
Philosophy, Science and Open Science
Is Psychology a Science?
· Psychology is made up of many different approaches e.g cognitive neuroscience and psychoanalysis
· Quantitative and qualitative methodologies
· Popper – science as deduction
Philosophy, Science and Open Science
Falsification
- Falsification = you can only prove that a prediction of a theory is false, not true
- For a theory to be scientific: - Logically coherent, Testable via experience, Parsimonious, Components of theory must reflect real experience
* Why do we need theories?:
- Can’t describe a notion unless a theory of underlying process is present
- A theory that explains certain data is unsolvable
- Can have alternative models that describe data
- Theories allow us to make predictions or account for data
Philosophy, Science and Open Science
Parsimony & Paradigm shifts
· Parsimony = Preference for the simplest theory
· If the theory doesn’t capture data, there are infinite numbers of ‘add-on’.
· Paradigm = A typical example/pattern of something
- In a field of enquiry, a dominant way of doing + thinking about what is being explored occurs
- Over time, we experience a paradigm shift
Philosophy, Science and Open Science
Replication
· Attempt to replicate a study and produce the same finding
· Fundamental principle of scientific developments
· Replications studies relatively rare as harder to publish
Philosophy, Science and Open Science
Open Science
· Many labs (2014)
· Many labs 2 (2018)
· Open science collab (2015)
- Replications of 100 experimental and correlational studies
- Designed a protocol to follow
- Registered protocol of design, participant numbers and analysis
· Open science is a movement to make parts of the research openly available
· Sharing prevents making up theory to explain data, and allows comparisons of data with other sets
Philosophy, Science and Open Science
Publication bias
· A lot of publishers have a bias for positive results
- Exaggeration
- Post-hoc
- P-value fishing
- Outliers
- Non-publication
Philosophy, Science and Open Science
Confirmatory vs exploratory analysis
· Exploratory
- Not sure what you are doing or to expect
· Confirmatory
- Rationale and hypotheses known in advance
Comments
No comments have yet been made