Research methods Flashcards
What is a hypothesis?
A statement of what the researcher believes to be true.
What is an aim?
A general expression of what the researcher intends to investigate.
What does operationalisation mean?
To make a variable defined and measurable.
Whats the difference between directional and non-directional hypotheses?
Directional = changes are greater/lesser, positive/negative.
Non-directional = doesn’t state a direction, just that there is a difference.
What are extraneous variables?
Nuisance random variables that muddy the water, make it more difficult to detect an effect.
What are confounding variables?
Change systematically with the IV. They obscure the effect of the DV and must be controlled.
What is a demand characteristic?
Cues from the researcher/research that may reveal the aim of the study and change N’s behaviour.
What are investigator effects?
When the investigator has any effect on the DV.
1) What is randomisation?
2) What is standardisation?
1) Use of chance when designing research to control effects of bias. Tackles confounding and extraneous variables.
2) Using exactly the same formalised procedures for all participants in a research study. Tackles extraneous variables.
What do researchers use to see if the IV does have an effect on the DV?
Control groups for comparison.
What are independent groups ?
One group does condition A, and a second group does condition B.
Positives:
- No order effects
- Will not guess aim
Negatives:
- Participant variables could reduce validity
- Less economical
What is repeated measures design
Same participants take part in all conditions of an experiment.
Positives:
- Participant variables controlled
- More economical
Negatives:
- Order effects
- May guess aim
What is matched pairs group design
Two groups of participants are used but they are paired on participant variables that matter for the experiment.
Positives:
- Participant variables somewhat controlled
- No order effects
Negatives:
- Pairing is not perfect
- More participants
How do you define a lab experiment?
- An environment whereby EVs and CVs can be regulated.
- IV is manipulated and the effect on the DV is recorded.
Positives:
- EVs and CVs can be controlled
- Can be more easily replicated
Negatives:
- Lack generalisability
- Demand characteristics
What is a field experiment?
A natural setting, IV is manipulated and the effect on the DV is recorded.
Positives:
- More natural environment
- Participants unaware of observation
Negatives:
- Difficult to control EVs and CVs
- Ethical issues
What is a natural experiment?
- Experimenter does not manipulate IV.
- IV would have varied even without manipulation.
- DV may be naturally occurring and can be devised and measured by experimenter.
Positives:
- May be the only ethical option for this effect (Romanian orphan study).
- Greater external validity
Negatives:
- Event may only occur once
- Participants not randomly allocated
What is a quasi-experiment?
- IV based on a pre-existing difference between people, e.g. age/gender.
- DV may be naturally occurring or measured by experimenter.
Positives:
- Often highly controlled
- Comparisons can be made between people
Negatives:
- Participants are not randomly allocated
- Causal relationships not demonstrated
What is an opportunity sample?
People who are simply most available, e.g. asking the students in your class to take part.
Positive:
- Quick method
Negative:
- Inevitably biased
What is a random sample?
Everyone has an equal chance of being selected, e.g. pulling names out of a hat.
Positive:
- Potentially unbiased
Negative:
- Time-consuming and may not work
What is a volunteer sample?
Participants selecting themselves, e.g. placing an ad in a newspaper.
Positive:
- Participants are willing
Negative:
- Volunteer bias
What is a systematic sample?
Participants selected using a set ‘pattern’ e.g. every Nth person is selected.
Positive:
- Unbiased
Negative:
- Time-consuming
What is a stratified sample?
- Participants selected according to their frequency in the target population, e.g. gender/age.
- Relative % of the subgroups are reflected in the sample.
Positive:
- Representative method
Negative:
- Stratification is not perfect
What is ethical conflict?
When conflict exists between the rights of the participant and the aims of the research.
What is informed consent?
Giving the participants full knowledge of the aims and purposes of the study so they can consent (or not) knowing what they will be doing.
What is deception?
Deliberately misleading or withholding info so consent is not fully informed.
How would a researcher overcome deception?
- Giving a debrief at the end of the study.
What should a debrief include?
1) True aims of the study and details not given during it.
2) Use of data acquired (about participant) and participant right to with-hold data.
How would protection from harm be enabled?
- Right to withdraw at any stage
- Reassured that their behaviour was typical/normal during debriefing
- Provide counselling if necessary
How would a researcher ensure privacy/confidentiality?
1) If personal details are kept, they must be protected and cannot be shared with other researchers.
2) Refer to participants using numbers, initials or false names.
What is a natural observation?
Taking place where the target behaviour would normally occur.
Positive:
- High external validity
Negative:
- Low control
What is a controlled observation?
Some control/manipulation of variables, including control of EVs.
Positive:
- Can be replicated
Negative:
- May have low external validity
What is a covert observation?
Participants are unaware they are being studied.
Positive:
- Demand characteristics reduced
Negative:
- Ethically questionable
What is an overt observation?
Participants are aware of being studied.
Positive:
- More ethically acceptable.
Negative:
- Demand characteristics
What is a participant observation?
When the researcher becomes part of the group they are studying.
Positive:
- Can lead to greater insight.
Negative:
- Possible loss of objectivity.
What is a non-participant observation?
When the researcher remains separate from the group they are studying.
Positive:
- More objective.
Negative:
- Loss of insight.
In terms of observation, what are behavioural categories?
Target behaviours to be observed broken up in to a set of observable categories (operationalised).
Negatives:
- Difficult to make clear and unambiguous.
- Dustbin categories.
In terms of observation, what is time sampling?
Observations made at regular intervals, e.g. once every 15 seconds.
Positive:
- Reduces number of observations.
Negative:
- May be unrepresentative.
In terms of observation, what is event sampling?
A target behaviour/event is recorded every time it occurs.
Positive:
- Useful for infrequent behaviour.
Negative:
- Complex behaviour oversimplified.
What are questionnaires?
A pre-set list of written questions to which a participant responds. Can be used to assess DV.
Positives:
- Can be distributed to lots of people
- Straightforward to analyse
Negatives:
- Responses may no always be truthful
- Response bias
What is an unstructured interview?
No set questions in face-to-face interview but there is a general topic.
Positive:
- Greater flexibility
Negative:
- Increased risk of interviewer bias
What is a structured interview?
There is a list of pre-determined questions asked in a fixed order.
Positive:
- Easy to replicate
Negative:
- Interviewers cannot elaborate
What 3 things should questionnaires avoid having or doing?
1) Using jargon
2) Using double-barrelled questions
3) Using leading questions
What are closed questions?
Respondent has limited choices and data tends to be quantitative/ can be converted.
Positive:
- Easier to analyse
Negative:
- Responses are restricted
What are open questions?
Respondent provides fully worded answers. Data is qualitative.
Positive:
- Responses not restricted
Negative:
- Difficult to analyse
How can validity of an interview be improved?
1) Interview schedule
2) Quiet room
3) Rapport
4) Ethics
What is a pilot study?
A small-scale trial run. Used to find out if certain things don’t work so you have time for corrections before the real thing.
What is quantitative data?
Numerical data
Positive:
- Easier to analyse
Negative:
- Narrower in meaning
What is qualitative data?
Non-numerical data expressed in words
Positive:
- Richness of detail
Negative:
- Difficult to analyse
What is primary data?
‘First hand’ data collected for the purpose of the investigation
Positive:
- Fits the job
Negative:
- Requires time and effort
What is secondary data?
Data collected by someone other than the person who is conducting the research.
Positive:
- Inexpensive
Negative:
- Quality may be poor
What is a meta-analysis?
A type of secondary data that involves combining data from a large number of studies.
Positive:
- Increases validity of conclusions
Negative:
- Publication bias
What are the 3 measures of central tendency?
Mean
Positive:
- Sensitive measure - includes all values
Negative:
- Easily distorted by extreme values
Median
Positive:
- Less affected by extreme scores
Negative:
- Sometimes extreme values are important
Mode
Positive:
- Relevant to categorical data
Negative:
- An overly simple measure
What are the 2 measures of dispersion?
Range
Positive:
- Easy to calculate
Negative:
- Does not account for the distribution of the scores
Standard deviation
Positive:
- More precise than the range
Negative:
- Can be distorted by extreme values
What are the three types of distribution?
Normal:
- Bell shaped
Negative skew:
- Tail of bell to the left
Positive skew:
- Tail of bell to the right
How is significance shown in Psychology? How is it found?
- Difference/association between two sets of data is greater than what would occur by chance.
- Statistical tests.
What is determined at 5% or 0.05 in Psychology?
Accepted level of probability to decide whether we accept/ reject the null hypothesis.
What are calculated and critical values?
Calculated value is the outcome of the test.
The critical value is in the values table.
What three things are needed to find the critical value?
1) Significance level
2) Number of participants (N value) and degree of freedom (df)
3) Directional or non-directional hypothesis.
When would the sign test be used?
To analyse:
- A difference in scores
- Related design
- Nominal data
Note all the steps of the calculation of the sign test
1) Score for condition B is subtracted from condition A.
2) Total number of pluses and total number of minuses should be added up (separately).
3) Participants who achieved the same score in condition A and B are deducted from the N value.
4) The S value is the total of the less frequent sign.
- If S is equal to or less than the critical value, then S is significant and the alternate hypothesis is retained.
What is a peer review?
Before publication, experts in the field (who are not known to the researchers to maintain objectivity) review in depth the research.
Positive:
- Protects quality of published research
Negatives:
- Anonymity may be used to criticise rival research.
- Publication bias
- Ground-breaking research may be buried
What are the aims of peer review?
1) Funding allocation
2) Quality control
3) Suggest improvements
How does psychology benefit the economy?
1) Attachment research into the role of the father.
- Modern parents better equipped knowing flexibility of roles, so both can still work.
2) Development of treatment for mental illness
- 1/3 of all days off work are caused by mental disorders, treatment aids workers contributing to economy.
Describe what a case study is
Detailed, in-depth study of individual/ group/ institution/ event and is longitudinal. They are used to research usual and unusual cases. They often produce mostly qualitative data.
Positives:
- Rich in detail so can provide new insight
- Allows for study of unusual behaviour
Negatives:
- Prone to researcher bias
- Small samples lack generalisability
What is a content analysis?
Type of observational research in which people are studied indirectly via the communications they have produced, e.g. conversation. newspaper reports.
Positives:
- Ethical issues avoided, consent not always needed.
- Flexible method, adapts to aims of research.
Negative:
- Communications studied out of context, reduces validity.
- May lack objectivity, choice of categories may depend of researchers personal views.
What are the two types of content analysis?
Coding
- Quantitative data
- Categorise information into meaningful units and the count number of words or phrases.
Thematic analysis
- Qualitative data
- Identify recurrent ideas - more descriptive than coding units, broader categories.
What is reliability and give two ways of testing it.
Reliability is a measure of consistency.
1) Test-retest
2) Inter-observer
Measured using correlation, two sets of scores from the tests above should produce a correlation of at least +.80 for reliability.
How would you improve the reliability of:
1) Questionnaires
2) Interviews
3) Experiments
4) Observations
1) Test-retest method
2) Use same interviewer each time
3) Strict control of standardised procedures
4) Operationalised behavioural categories
What is validity and is it possible to obtain reliability without validity?
Validity is a measure of legitimacy (genuine effect).
Yes, e.g. broken scales may report additional weight - but it’s not true to life.
What are the two types of validity and their divisions?
1) Internal validity = Control within study
2) External validity = Generalisability
- Ecological validity = Can it be generalised to specific situations, everyday life.
- Temporal validity = Findings remain true over time, not historically specific.
What 2 ways would you assess validity?
1) Face validity
- Test looks like it measures what it should. Its eyeballing.
2) Concurrent validity
- Findings similar to well-established test.
How do you improve validity of;
1) Experimental research
2) Questionnaires
3) Observations
4) Qualitative methods.
1) - Using a control group/s and standardised procedures, single/ double blind.
2) Incorporating a lie scale within the questions and ensure participants of confidentiality.
3) Well-defined categories with no overlap. Covert observations for greater authenticity.
4) Interpretive validity and triangulation (use multiple sources).
What are statistical tests used for and what 3 criteria must you take into consideration before choosing a statistical test?
Used to determine whether difference or association/ correlation is significant.
1) Difference or correlation
2) What experimental design is being used.
3) Level of measurement.
Picture the statistical test box, flip the card when ready and see if you got it right…
What are the 3 types of data?
1) Nominal data - Data presented in categories.
2) Ordinal data - Data in order on numerical scale but the intervals are variable.
3) Interval data - Based on numerical scales with units of equal, precisely defined size.
If the statistical test is not significant, what hypothesis is accepted?
The null hypothesis is accepted and the alternative hypothesis is rejected.
The null hypothesis is accepted or rejected at a particular level of probability.
What 3 criteria do you need when studying a table of critical values?
1) One-tailed or two-tailed hypothesis?
2) Number of participants in study (N) or degrees of freedom (df).
3) Level of significance (p value).
What is a Type I error?
When the null hypothesis is rejected even though it is true, false positive result.
What is a Type II error?
When the null hypothesis is accepted even though it is false, false negative result.
When are you likely to accept each type of error?
Type I - significance level too lenient, e.g. 10%
Type II - significant level too stringent, e.g. 1%
What are the sections of a scientific report?
1) Abstract
- Short summary of the study.
2) Introduction
- Review of literature, logical progression to hypothesis.
3) Method
- Design, sample, materials, procedure, ethics, detailed replication. Detailed enough for replication.
4) Results
- Descriptive and inferential statistics, raw data in appendix.
5) Discussion
- Summary, links to earlier research, limitations and implications of research.
6) Referencing of work informing the research.
What are the features of science?
1) Objectivity
2) Empirical method
3) Replicability
4) Falsifiability
5) Theory construction
6) Paradigms/ shifts