Research methods Flashcards
What is meant by participant reactivity?
Ppts are not passive in an experiment
An extraneous variable
Ppts will be trying to make sense of the situation
Effect of this is demand characteristics
What is an Independent variable?
Something that the researcher changes or manipulates to observe effects. It is the thing being changed
What is meant by Dependent variable?
The thing that is being measured
What is the definition of an extraneous variable?
An outside variable which can influence/ have an effect on the outcome
What is repeated measures design and what are the advantages and disadvantages?
-Same ppts used in both conditions
Advantages:
+ Controls for individual differences
+ Fewer total ppts required (saves time and energy)
Disadvantages:
- Order effects
- Demand characteristics
What is independent measures design and what are advantages and disadvantages?
-Different ppts used conditions
Advantages:
+ No order effects
+ Can be useful when looking at gender differences
+ Cheap and quick to recruit ppts compared to matched pairs design
Disadvantage:
- Ppts variables which are not controlled (personality, IQ…). Acts as confounding variables, researcher cannot control these variables.
Explain matched pairs design and its advantages and disadvantages
-Match similar ppts together so you can compare these two results together as they are similar
-Find out the type of people and match them with similar people to take part in the other condition
Advantage:
+ Controls for induvial differences between ppts
+ Researcher can compare results without individual differences affecting results
Disadvantage:
-Difficult to match people
-It is time consuming due to the pre test on matching which takes place before hand
-This can be costly financially
Strengths of laboratory experiments
+Control over extraneous variables
+Cause and effect be established
+Replicable due to high control of extraneous variables + use of standardised procedures
+Results can be checked for reliability as the same experiment can be conducted on multiple ppts
Weaknesses of laboratory experiments
-Lack of ecological validity due to artificial setting. Difficult to generalise the findings to the real world
-Demand characteristics. Ppts behaviour may not be natural due to the artificial set up of the environment. Ppts figure out the aims of the experiment (Please-U and Screw-U)
-Low mundane realism. Tasks carried out in lab experiments makes the results difficult to generalise to rea life
Difference between mundane realism and ecological validity
Ecological validity = To do with the environment
Mundane realism = To do with the task
Definition of a lab experiment
Takes place in a controlled artificial environment and the researcher directly manipulates the IV to see effects on DV
Definition of a field experiment
Field experiments are performed in a natural setting such as hospitals, schools, factories, trains or even on the street
IV is manipulated by researcher. Difficult to control extraneous variables in this type of experiment
What is a field experiment?
What are the advantages?
What are the disadvantages?
What it is
Conducted in a natural setting, IV manipulated by the researcher
Advantages:
-High external validity which means you can generalise it to real life situations (people show more naturalistic behaviours)
-No demand characteristics
Disadvantages:
-Hard to control extraneous variables, could argue that result may not be due to IV
What is internal validity?
Whether a psychological test, experiment or observation produces a genuine result
What is external validity?
Whether the research findings can be generalised beyond the research setting in which it was found
(generalisability)
What is a natural experiment and what are the advantages and disadvantages?
What it is
Change in IV has occurred naturally so not be manipulated by researchers e.g. would have happened even if the researcher had not been there
Advantages:
+High external validity (changes happened in real life)
+No demand characteristics
+Allow research in areas that could not happen due to ethical or cost reasons
Disadvantages:
-No control of extraneous variables which means it is hard to establish cause and effect
-Rare and can’t be replicated to see if we would get similar results not replicable
What is a quasi experiment and what are the advantages and disadvantages?
Change in IV cannot be manipulated or randomly assigned (male/female/old/new)
Advantages
-Only way to study these variables
-Often carried out in controlled conditions E.g. Bobo doll
Disadvantages
-Unable to know if gender is the reason for the result as you can’t control ppt variables
What is ecological validity?
When you can generalise to a different place or setting
What is mundane realism
Is the task similar to what we would do in real life
What is temporal validity?
Can you generalise to a different century, or decade
What is naturalistic observation and what are the advantages and disadvantages
In a real-life setting
Advantages
+ High ecological validity due to the natural setting/environment in which observation takes place. The researcher doesn’t manipulate any aspects of the situation
+ Generalisability of findings as behaviour applies to real-life, everyday setting
Disadvantages
-Low levels of control may be unknown extraneous variables contributing to behaviour meaning it is hard to replicate these results
What is a controlled observation and what are the advantages and disadvantages
Aspects of the environment are controlled, to give ppts same experience, Often conducted in a lab (Ainsworth and Bandura)
Advantages
-High control reduces the likelihood of extraneous variables being responsible for the observed behaviour
-Results are reliable as they used the same standardised procedures
Disadvantages
-Low external validity because the environment is artificial, Behaviour may not be repeated in the actual environment
3 strengths of longitudinal studies
-Give us deeper insight into behaviour by seeing how behaviour changes overtime
-Give us insight into how early experiences shapes behaviour
-More reliable results
What is attrition?
When there is a loss of ppts across the course of a study
Definition of a case study
-An in-depth analysis of individual, group, institution/event
-Typically involves analysis of unusual individuals or disorders.
-They are idiographic and very individualistic
-Typically longitudinal
Strengths of case studies
+ Allows researchers to study the individuals/events/complex psychological areas they could not practically or ethically manipulate
+ Offers rich detailed insights into behaviours which cannot be studied scientifically and may not be understood
+ Useful as it can be used to develop theories E.g. HM demonstrated separate stores for LTM
Weaknesses of Case Studies
- Small samples make it difficult to generalise results to the wider population
- Risk of bias as researchers can become too involved and lose their objectivity: misinterpreting or influencing outcomes
What is meant by the target population?
People the psychologist is specifically interested in
What is random sampling?
When all members of the population have an equal chance of being selected
Strengths of random sampling
+ No selector bias
+ Everyone has an equal chance of being selected
Weaknesses of random sampling
-Takes more time to carry out compared to other methods
- Freak sample
What is opportunity sampling?
Recruiting people who are most convenient or available
Strengths of opportunity sampling
+ Easy to find ppts
+ Takes less time to find ppts
Weakness of opportunity sampling
- Sample bias - PPTs are drawn from a small part of the population. Maybe all from the same ethnic background, social class, race, and age … So the sample isn’t representative of the wider population
What is a covert observation?
What are the strengths and weaknesses of covert observation?
Ppts behaviour is watched and recorded without them knowing.
+ No demand characteristics
+ Higher validity
- Unethical, ppts haven’t given informed consent to being watched
What is an overt observation?
What are the strengths and weaknesses of an overt observation?
Participants behaviour is watched and recorded with their knowledge or consent
+ No ethical issues
-Participant reactivity, leads to demand characteristics, weakening the validity of results
What is a participant observation?
What are the strengths and weaknesses of participant observation?
Psychologists will join the group they are studying to better observe the behaviour
+Gain insight
-Lacking objectivity. Researchers may become less neutral, creating bias
What is event sampling?
Involves recording the number of times a particular behaviour within the behavioural category occurs whilst observing participants
What is time sampling?
Recording the behaviour in an established time frame
Weakness of using correlations
- Doesn’t establish cause and effect. Doesn’t tell us how X causes Y, meaning we can’t gain deeper insight into what is really happening between two variables
Strengths of using correlations
+ Highlights potential causal relationships
+ Can show the direction and strength of the relationship
Strength of qualitative data
+ High external validity. Researchers can gain a better insight into participant worldview
+Rich detail - Pmts fully able to report their thoughts, feelings and opinions
Weakness of qualitative data
-Data is often difficult to analyse. Conclusions rely on subjective interpretations of researcher meaning it could be biassed
-Described as not scientific
Strengths of quantitative data
+ Easy to make comparisons and trends between groups
+ Objective
+ Data is easy to analyse
Weakness of quantitative data
- Cant help us properly gain insight
- Responses can be narrow in explaining complex human behaviour. May fail to represent ‘real life’
-Superficial
Definition of a case study
An in-depth study of an individual, group, institution/event. Typically involves analysis of unusual individuals or disorders. They are idiographic and individualistic
Weaknesses of Case Studies
-Small samples make it difficult to generalise findings
- Risk of bias as researchers become too involved and lose their objectivity, misinterpreting or influencing outcomes
- Difficult to establish cause and effect as case studies happen after the event
- Case studies often depend on the memory of participants: retrospective data might be inaccurate
Strengths of case studies
- Allows researchers to study events/ complex psychological areas they could not practically or ethically manipulate
- Offers rich and detailed insights into behaviours which cannot be studied scientifically and/or may not be understood
- Useful as it can lead to the development of theories E.g. HM demonstrated separate stores of LTM
What is reliability a measure of?
- Measure of consistency
- If a particular result can be repeated then that measurement is described as being reliable
Ways to ensure reliability in interviews
- Use the same interviewer
-Dont ask questions which are open to ambiguity - Use a trained interviewer - less likely to ask ambiguous questions which are open to interpretation
-Dont ask leading questions - Use structured interviewers
Ways of testing reliability (Test-retest)
- Giving the same questionnaire to the same person/group of people on a different occasion
- If the test is reliable, the result should be the same or very similar
- If the correlation is above 0.8 then there is good reliability
- Must be sufficient time between two tests
Ways to increase the reliability of observations
- Should be more than one observer
- Conduct a small-scale ‘pilot study’
- Administer appropriate behavioural categories
- Observers should watch the same event independently and record data using agreed behavioural categories
- Ensure behavioural categories have been operationalised
Why are lab studies easily replicable?
Due to the high/strict control the researcher has over extraneous variables
- Researcher manipulates the IV to see an effect on DV
- Researchers can control experimental conditions but also the instructions ppts are receiving
- Means lab experiments are much easier to replicate
4 types of quantitative data?
- Nominal
- Ordinal
- Ratio
- Interval
When is the sign test used?
- Need to look for a difference rather than a correlation
- Data has to be nominal
- Repeated measures design
What is ordinal data?
Data which exists in natural categories
good, fair, poor, awful…
e.g.
Grades
Income
Frequency of zoo visits
Sleep quality
What is nominal data?
Data which exists in categories with no natural order
e.g.
Nationality
Blood Type
Personality Type
Employment Status
Zip Code
Movie Genre
What is ratio data?
What is interval data?
Ratio = Regarding number values, we can directly see how much bigger one value is than another. Can’t go below 0
Interval = Numbers which can go below 0 (E.g. Temperature or money in a bank account)
Continuous vs Discrete data
Continuous - Not restricted to certain numbers. E.g. Height or weight. You can be 70.9 kg or 178.5 cm tall
Discrete—Restricted to certain numbers. For example, the number of children somebody has has to be a whole number; they can’t have 2.4 kids.
Ordinal and nominal data are always …
DISCRETE
When to use the Sign test
- When testing for a different
-Nominal data
-Repeated measures design
What does the t-test tell us?
The probability of observing our results if the null hypothesis is correct
The smaller the t-value, the bigger the probability of the null hypothesis being…
correct
As the sample size gets bigger, the probability of observing our results if the null hypothesis is correct gets…
Smaller
What is the p-value?
Probability of observing our results if the null hypothesis is correct
What is a type 1 error?
Incorrectly reject the null hypothesis, and say there is a real difference between two experimental groups when there isn’t one.
What is a type 2 error?
When researchers incorrectly accept the null hypothesis and conclude their results happened by chance, when there is a difference
What does the significance level tell us?
How likely we are to make a type 1 error
To balance the risk of a Type 1 and Type 2 error, researchers usually use a significance level of…
5%
We reject the null hypothesis if the obtained t-value is…
Bigger than, or equal to, the critical t-value for our significance level.
When is chi-squared test used?
-Testing for significance to see if a relationship exists between two variables
-Independent design
-Nominal data
-Testing of difference
When is Mann-Whitney test used?
-Determines whether two uncorrelated means differ significantly
-Independent design
-Ordinal data
-Test of difference
When is unrelated t-test used?
-When a difference between two sets of scores is being used
-Data must be interval
-Independent groups design
When is related t-test used?
-Testing for a difference between two sets of scores
-Repeated design
-Interval data
When is Wilcoxon test used?
-Used to compare repeated measures design or matched pairs on a single sample to assess whether their population mean ranks differ
-Ordinal data
-Repeated measures design
When is Spearman’s rank used?
-Tests for strength of correlation
-Used for nominal and ordinal data
When is sign test used?
-Test of difference
-Nominal data
-Repeated measures design
When is Pearson’s r test used?
-Measures the direction and strength of the linear relation between two variables
-Interval data
Briefly explain one reason why research should be peer reviewed.
[2 marks]
-To reduce chances of flawed/unscientific research being published and therefore treated as ‘fact’ and misinforming the public
Explain the difference between a Type I and a Type II error.
A type I error (false-positive) occurs if an investigator rejects a null hypothesis that is actually true in the population; a type II error (false-negative) occurs if the investigator fails to reject a null hypothesis that is actually false in the population.
Explain the advantage of using the standard deviation instead of the range as a measure of dispersion
One advantage is that the standard deviation is a measure of dispersion that is less easily distorted by a single extreme score
A researcher used content analysis to investigate how the behaviour of young children changed when they started day care.
He identified a group of nine-month-old children who were about to start day care. He asked the mother of each child to keep a diary recording her child’s behaviour every day for two weeks before and for two weeks after the child started day care.
(a) Explain how the researcher could have used content analysis to analyse what the mothers had written in their diaries. (4)
Content analysis is a way of analysing data such as text using coding units
such as themes. In this case mothers were asked to write down how their child
behaved, so students might suggest.
Create a checklist / categories
Relevant example(s) of behaviours eg aggression, crying
Read through the diaries / mothers’ writing / reports
Counting behaviours or tallying
Compare before and after day care
What is meant by validity? (1)
Validity refers to how well a test or a piece of research measures what it says it
measures
Strengths and weaknesses of peer review
-Peer reviewers may not always be objective when reviewing research as it may not be in their personal interest to see the research get published
+Protects society from harmful / bad research
+Helps researchers improved their research
What happens in peer review?
-Journals can ask for changes to be made to a report based on the comments left by reviewers
-Peer reviewing involves multiple reviewers, all from the same field
-Reviewers may suggest that further analysis of the results is needed before the research can be published.
-A journal will decide whether to accept or reject a report based on the feedback from the reviewers.
Explain two strengths of peer reviewing.
The process of peer reviewing highlights the good and bad of the report. One strength of this is that suggestions made can help researchers to improve their work, and learn better ways to conduct research in the future. Another strength of this is that it helps make sure that research is of a high quality, as poor quality research could have negative implications in real life.
Features of a pilot study
-A test used to identify potential flaws in an experiment
-A study with only a few participants
Benefits of pilot studies
+ It is cost effective.
Explain thematic analysis
-Researchers use codes to label the data only after they have familiarised themselves with the data
-The data used in thematic analysis must be in written form, qualitative data
-Interprets the data to identify common themes
Process of thematic analysis
First, a researcher converts their data into written form.
Second, they familiarise themselves with the data.
Third, they label the data using codes.
Fourth, they categorise their codes into themes
`
And, finally, they write a report interpreting their themes, and relating them back to the research topic.
Content analysis involves…
-Turning qualitative data into quantitative data
-Establishing coding units before a researcher looks through the data
-Counting up whenever a coding unit appears in the data
Strength of content analysis
+It allows us to test hypotheses about qualitative data.
Strength of thematic analysis
+It provides a more detailed understanding about participants’ experiences
Weakness of thematic analysis
-Lacks external reliability as different researchers may view the subjective experiences differently
Explain why it might be better for the researchers to use content analysis instead of thematic analysis
In thematic analysis, the researchers generate their codes while they read through transcripts. They then base their themes on these codes. This means that the themes are created based on what the researchers think is important, and is the reason why the four researchers came up with different themes. Therefore, the data lacks reliability.
However, in content analysis, the coding units are determined before the researchers read through the transcripts. Therefore, the researchers are all looking for the same content units, and this means content analysis is more reliable than thematic analysis. Additionally, as the data gets turned from qualitative data into quantitative data, researchers can also test how reliable the analysis was. They could do this using the test-retest method or use inter-rater reliability.
