Research Methods Flashcards
Define case study
An in-depth investigation, description and analysis of a single, individual, group, institution or event
What types of data is obtained when researchers obtain case histories during case studies?
Qualitative and quantitative data
Qualitative: through interviews, observations, questionnaires
Quantitative: sometimes during experimental testing when researcher assess pps to find out what they are/or not capable of.
Are case studies mainly longitudinal or cross-sectional?
longitudinal, but sometimes cross-sectional
Evaluate the use of case studies.
Strengths
- Rich, detailed insights that may shed light on atypical forms of behaviour: less likely to involve ‘superficial’ forms of data that may be present in experiments.
- Contributes to our understanding of normal functioning: e.g. HM case study
- Helps generate hypotheses for future studies
Limitations
- Generalisability
- Subjectivity: results influence by researchers interpretations
- Low validity: info provided by pps in study may be prone to inaccuracy due to factors such as memory decay.
Define content analysis
A research technique that enables the indirect study of behaviour by examining communications that people produce, for example, in texts, emails, TV, film and other media
Outline the initial stage of content analysis (GIVE EXAMPLE)
Coding
- communication to be studied is analysed by identifying each instance of the chosen categories (e.g. how many of a certain word appears in a text). This makes it easier to analyse very large pieces of data
- PRODUCES QUANTITATIVE DATA
Define thematic analysis
Thematic analysis
- when explicit/implicit ideas are identified within data.
- These will often emerge after data has been coded
- PRODUCES QUALITATIVE DATA
How does a researcher conclude their content analysis?
They write up their final report, typically using quotes from the data to illustrate each theme
Evaluate the use of content analysis
Strengths
- More ethical: much of the material used on content analysis is already available so researchers don’t need to gain permission to collect data
- Flexible: can produce both quantitative/qualitative data
Weaknesses
- Subjective: themes in thematic analysis may be subject to researchers influence
- Thematic analysis may not cover most aspects of data being analysed.
Define reliability
The idea that a researcher should produce the same (consistent) results every time
Define internal reliability
The idea that items within a test/questionnaire are consistent within themselves
Define external reliability
The idea that a test/questionnaire etc produces consistent results every time it is used
Outline a method to test external reliability
TEST-RETEST METHOD: participants are tested on more than 1 occasion to see if they produce consistent results. If they do, study has external reliability
Define inter-observer reliability and what else might it be known as?
Idea that observers provide consistent results during a small-scale study, in which they record their results independently so that they can be correlated and checked for consistency
Known as:
- inter rater reliability: content analysis
- inter interviewer reliability: interviews
Outline a test of correlation
Spearmans rank: data is reliable if co-efficient is +.80
How can you improve reliability of questionnaires?
TEST-RETEST (to find +0.80 correlation)
Questionnaire that produces low test-retest reliability may require some items to be deselected or rewritten.
- E.G. Complex questions may be interpreted by same ppt on 2 different occasions. This can be overcome by replacing open questions by closed questions.
How can you improve the reliability of questionnaires?
USE SAME INTERVIEWER EACH TIME
- If this is not possible, properly train interviewers so they don’t ask questions that are too leading/ambiguous. (this is less of a problem in structured interviews)
How can you improve the reliability of experiments?
USE LAB EXPERIMENTS
Lab experiments are described as ‘reliable’ as the high control over extraneous variables means researchers can precisely replicate a particular method, rather than reliable in the sense of demonstrating the consistency of a finding.
How can we improve the reliability of observations?
OPERATIONALISING BEHAVOURAL CATEGORIES
They should be measurable, self-evident (less open to interpretation), non-overlapping, and all possible behaviours should be covered. This avoids observers having to make their own judgements in what to record, and this can lead to inconsistent records.
Define correlation co-efficient
A number between -1 and +1 that represents the direction and strength of a relationship between co-variables
Define these key words:
- Validity
- Internal validity
- External validity
- Temporal validity
- Validity = The extent to which an observed effect is genuine
- Internal validity = Does the researcher show a clear cause and effect relationship between variables.
- External validity = can the results be generalised to other real-life settings/situations
- Temporal validity = The extent to which findings can be generalised to other time periods
Define face validity and concurrent validity
Face validity = whether a test looks like it measures what it should (achieved by passing measuring instrument to an expert to check)
Concurrent validity = whether findings are similar to those on another well-established existing measure (e.g testing effectiveness of an intelligence test by comparing student scores with those on a well-established test in hopes of showing 0.80+ correlation)
How can you improve the validity of experiments?
BY USING CONTROL GROUPS AND STANDARDISED PROCEDURES
- Control groups mean researcher can be more confident that changes in DV were due to IV (internal validity).
- Standardised procedures minimise impact of extraneous variables (e.g. investigator effects)
How can you improve the validity of questionnaires?
USE A LIE SCALE AND REMIND PPTS ABOUT CONFIDENTIALITY
- Lie scales control for effects of social desirability bias.
- Confidentiality encourages ppts to be truthful.
How can you improve the validity of observations?
OPERATIONALISING BEHAVOURAL CATEGORIES
To improve face validity, behavioural categories should be measurable, self-evident (less open to interpretation), non-overlapping, and all possible behaviours should be covered.
How can you improve the validity of qualitative research?
TRIANGULATION (using a number of different sources as evidence e.g. direct quotes from ppts, interview data)
- Triangulation increases the coherence of a report and as a result, increases interpretive validity.
What are statistical tests used for?
They are used to determine whether a difference or correlation found in an investigation is statistically significant (whether results could have occurred by chance or whether there is a real effect)
What 3 pieces of criteria do you need to identify which statistical test to choose?
- Whether you’re looking for a difference or correlation
- Whether the experimental design is independent group design (unrelated) or repeated measures (related)
- The level of measurement (nominal/ordinal/interval)
Fill in this statistical test table.
Test of difference Test of correlation
unrelated related
Nominal
Ordinal
Interval
Test of difference Test of correlation
unrelated related
Nominal Chi-squared Sign test Chi-squared
Ordinal Mann-Whitney Wilcoxon Spearman’s rho
Interval Unrelated t-test Related t-test Pearson’s r
(though spearman’s rho can also use interval data)
What is nominal data?
Data that can appear in categories
- e.g. people naming their favourite food
What is ordinal data? (give an example in your definition and also give a weakness of this kind of data)
Data that is collected on a numerical, ordered scale but intervals are variable
e.g people rating how much they like pizza on a scale of 1-10.
WEAKNESS: It lacks precision as it’s based on subjective opinion rather than objective measures (a ranking of 4 in the example may mean something very different to someone else)
What is interval data? (give an example in your definition and also give a STRENGTH of this kind of data)
Data that is based on numerical scales that include units of equal, precisely defined size.
e.g. time/temperature/volume
STRENGTH: It is more precise than ordinal data as it uses objective measures.
When do we accept the null hypothesis?
When a statistical test shows that results are not significant
Define significance
An indicator of the degree of certainty that a difference or correlation exists
when are results significant in:
- the mann-whitney test?
- the Wilcoxon test?
- the unrelated t-test
- the related t-test
- tests of correlation
- Mann-Whitney, Wilcoxon = When the calculated value is less than the critical value
- Unrelated/related t-test, tests of correlation = When the calculated value is more than the critical value
Define parametric tests
Parametric tests are tests that assume that a population show a normal distribution
e.g Unrelated t-tests, Related t-tests, and Pearson’s r
What is the level of significance in psychology? (the number)
It is 0.05 (this means that the probability that results occurred by chance is 5% or less)
What is a type 1 error?
An error that occurs when null hypothesis is rejected and alternative hypothesis is accepted, even though no real difference/correlation is present between the 2 variables.
- It is more likely to occur when the level of significance is too lenient (e.g. 0.1/10%)
What is a type 2 error?
An error that occurs when the alternate hypothesis is rejected, and the null hypothesis is accepted, even though there IS a real difference/correlation between the 2 variables.
- It is more likely to occur when the level of significance is too strict (e.g. 0.01/1%)
Name the sections of a scientific report
(AIM RDR)
- Aim
- Introduction
- Method
- Results
- Discussion
- Referencing
What is the abstract section?
Short summary of aims and hypotheses, method, results and conclusion (around 150 words)
What is the introduction section (in a scientific report)?
A look on past research (theories/studies) on a similar topic. Includes the aims and hypothesis of research
What is the method section?
A description of what researchers did, including design, sample, apparatus, procedure, ethics (ways ethical issues were addressed)
What is the results section?
A description of what the researchers found, including descriptive and inferential statistics
What is the discussion section?
Summary where results are verbally explained, limitations of study is discussed, and wider implications of research
What is the referencing section?
Lists of sources that are referred to or quoted in the research e.g. journals, articles
Name the 6 features of a science?
FORTEP
- Falsifiability
- Objectivity
- Replicability
- Theory construction
- Empirical methods
- Paradigms/Paradigm shifts
What are paradigms/paradigm shifts and how do they relate to psychology?
Paradigms = set of shared assumptions and agreed methods within a scientific discipline
Paradigm shifts = A change in the dominant unifying theory within a scientific discipline
Psychology doesn’t have these as there’s too much internal disagreement (e.g. whether gender is based on nurture/nature). This makes it more of a pre-science than a science
What is objectivity and how does it relate to psychology
Objectivity = All sources of personal bias are minimised so as not to distort the research process
Psychology uses lab experiments and controlled/ standardised procedures to minimise bias. This gives t scientific credibility.
What is replicability and how does it relate to psychology?
Replicability = If findings are repeatable across a number of different contexts
Psychology uses lab experiments and replicable procedures, so that we can see if findings can be generalised across different contexts (increasing the validity as well as the reliability of research)
What is theory construction and how does it relate to psychology?
Theory construction = Creating a set of general laws/principles that have the ability to explain particular events or behaviours.
- Testing a theory depends on the ability to make clear and precise hypotheses on the basis of the theory. This can then be tested using scientific methods.
Psychology includes many theories that have been tested using scientific methods (e.g. E.g. Watson and Raynor used a lab experiment to investigate the behavioural theory to learning behaviour)
Define deduction?
The process of deriving a new hypothesis from an existing theory
What are empirical methods and how do they relate to psychology?
Empirical methods = Scientific approaches that rely on direct observation and experience
Psychology relies on evidence and experience in order to generate laws/principles. The Bobo doll experiment supports social learning approach by suggesting that behaviour is learnt through observation and imitation.
What is falsifiability and how does it relate to psychology?
Falsifiability = The principle that a theory cannot be considered scientific unless it admits the possibility of being proved untrue.
This is shown through the different approaches that aim to explain one phenomena. (e.g. behavioural scientists aim to explain behaviour through experience e.g. schizophrenia being caused by upbringing, whilst biological approach will aim to explain the behaviour through genes e.g. dopamine’s role in schizophrenia)
