Unit 2: Research methods Flashcards
1
Q
What is operationalisation ?
A
clearly defining variables in terms of how they can be measured.
2
Q
What is the independent variable ?
A
The variable that the researcher manipulates or changes naturally so the effects on the DV can be measured
3
Q
What is the dependant variable ?
A
the variable that is measured by the researcher.
4
Q
What are extraneous variables ?
A
any variable other than the IV that may effect the DV if not controlled
5
Q
What are confounding variables ?
A
any variable other than the IV that may have affected the DV
6
Q
Demand characteristics ?
A
any cue from the researcher that may have been interpreted by participants as revealing the purpose of the investigation. This can lead to participants changing their behaviour within the research situation.
7
Q
What are investigator effects ?
A
Any effect of the investigators behaviour on the research outcome ( the DV )
8
Q
What is randomisation ?
A
the use of chance In order to control for the effects of bias when designing materials and deciding the order of conditions
9
Q
What is standardisation ?
A
using exactly the same formalised procedures and instructions for all p/pants
10
Q
What are the types of experimental designs :
A
- independent groups
- matched pairs
- repeated measures
11
Q
What is an independent groups design ?
A
participants are allocated to different groups where each group represents one experimental condition
12
Q
What is a repeated measures design ?
A
all participants take part in all conditions of the experiement
13
Q
What is a matched pairs design ?
A
pairs of p/pants are first matched on some variables that may effect the DV. Then one is assigned to condition A and the other condition B.
14
Q
What is counterbalancing ?
A
an attempt to control for order effect in a repeated measures design.
half the p/pants experienced the conditions in one order the other half the other order.
15
Q
Strengths and issues with a matched pairs design :
A
+ order effect and demand characteristics aren’t a problem
- p/pants can never be matched exactly and the matching itself can be time consuming and expensive
16
Q
Strengths and issues with a independent groups design :
A
+ order effects not a problem
- less economical than repeated measures, individual differences
17
Q
Strengths and issues with a repeated measures design :
A
+ economical, fewer p/pants needed so participant variables are controlled.
- order effects and demand characteristics. order effects can be fixed by counterbalancing
18
Q
Strengths and limitations of a laboratory study :
A
+ high control over extraneous variables, replication is more possible
- low mundane realism, demand characteristics, low external validity, may lack generalisability.
19
Q
Strengths and limitations of field experiments :
A
+ high mundane realism and external validity
- ethical issues
20
Q
Strengths and limitations of natural experiments :
A
+ high external validity
- cannot be repeated
21
Q
Strengths and limitations of quasi-experiments :
A
+ controlled conditions
- cannot randomly allocate p/pants to conditions - confounding variable
22
Q
What are the types of sampling :
A
- random
- systematic
- stratified
- opportunity
- volunteer
23
Q
What is systematic sampling ?
A
when every nth member of a target population gets selected
24
Q
What is stratified sampling ?
A
composition of the sample reflects the proportions of people in different sub-groups (strata) within the target population or the wider population
25
What are the ethical issues stated in the BPS code of ethics :
- deception
- informed consent
- confidentiality
- protection from harm
26
What is a pilot study ?
a small scale version of an investigation that takes place before the real investigation to check if the procedure, materials , measuring scales etc work and allow the experimenter to tweak if necessary.
27
What is the difference between a single blind and double blind procedure ?
single blind the patient is unaware but experimenter Is not. In a double blind procedure both the participant and the researcher doesn't know the true purpose of the experiment.
28
What are the different types of observations :
- naturalistic
- controlled
- covert
- overt
- participant
- non-participant
29
What's a naturalistic observation ?
watching and recording behaviour in a setting which in would naturally occur in
30
What's a controlled observation ?
watching and recording behaviour in a controlled structured environment
31
What's a covert observation ?
p/pants behaviour is being watched and recorded without their knowledge or consent
32
What's an overt observation ?
p/pants behaviour is being watched and recorded with their knowledge and consent
33
What's a participant observation ?
the researcher becomes a member of the group which they are watching and recording
34
What's a non-participant observation ?
the researcher remains outside of the group that they are watching and recording.
35
What is event sampling ?
a target behaviour or event is established then the researcher records this event every time it reoccurs
36
What is time sampling ?
a group is established and the researcher records their behaviour in a fixed time frame like every minute.
37
What is inter-observer reliability ?
to make researcher bias less likely research should be done by several researchers and they should be trained to establish inter-observer reliability this includes:
- familiarising themselves with behavioural categories used.
- they then observe the same behaviour at the same time - in pilot study for example
- observers should compare the data they have recorded and discuss any differences in interpretations.
- finally observers should analyse this data. inter-observer reliability is calculated by correlating each pair of observations made and an overall figure is produced.
38
What Is standard deviation ?
a value which tells us how far scores deviate from the mean. The larger the standard deviation the greater the dispersion within a set of data suggesting that not everyone was effected by the IV in the same way or that there was anomalies within the data.
A low standard deviation reflects tightly clustered data around the value of the mean suggesting the p/pants all responded in a similar way towards the IV
39
What is the accepted level of probability ?
p < 0.05
in other words the probability that results occurred by chance is equal to or lower than 5%
40
What are the main aims of peer review ?
- to allocate research funding
- to validate the quality and relevance of the research
- to suggest amendments or improvements
41
Requirements for the sign test :
we use this to determine whether the difference we have found is significant or not. To use this there are three requirements :
- we need to be looking for a difference
- we need to have used a repeated measures design
- we need atleast nominal data
42
How to do the sign test :
add up pluses and minuses of results . take the less frequent sign and this is our S value
43
Economical implications of psychological research :
- psychological research has shown that both parents are equally capable of providing emotional support needed for a healthy psychological development , this understanding has the potential to promote more flexible working arrangements within the family. Meaning that modern parents are better equipped to maximise their income and contribute more effectively to the economy.
- psychological research into the causes and treatment of mental illness has an important role in supporting a healthy workforce as in 2014 it was reported that 1/3 of work absences were as a result of mild to moderate mental health disorders.
44
Evaluation of random sampling:
+ free from researcher bias
- difficult and time consuming
- may end up with a sample that is still unrepresentative
- selected participants may refuse to take part, so you end up with something more like volunteer sampling.
45
Evaluation of systematic sampling:
+ avoids researcher bias
+ fairly representative
46
Evaluation of stratified sampling:
+ avoids researcher bias
+ representative, designed to accurately reflect the composition of the population
- cannot reflect all the ways in which people are different so complete representation of target population is impossible
47
Evaluation of opportunity sampling:
+ convenient and less costly
- suffers from 2 types of bias, unrepresentative of target population as participants are drawn from a particular area and researchers have complete control over the selection of participants ( researcher bias )
48
Evaluations of Volunteer sampling:
+ less time consuming
- attracts a certain 'profile' of person - volunteer bias
49
How to deal with the ethical issue of informed consent?
participants issued with a consent letter detailing relevant information. If under 16 parents must sign this
50
What are the alternative ways of getting consent?
- Presumptive consent -
instead of getting consent from the participant themselves, a similar group of people are asked if the study is accepted. If they agree the consent of the participant is 'presumed'
- Prior general consent -
participants give there permission to take part in a number of different studies , including one that involves deception. By consenting they are effectively consenting to be deceived
- Retrospective consent -
participants are asked for their consent during debriefing when they have already taken part in the study
51
How do you deal with the ethical issue of deception and protection from harm?
participants should be given a full debrief so they are aware of main aims.
They should also have the right to withdraw their data.
If the study makes them require counselling the researcher must provide this.
52
How do you deal with the ethical issue of confidentiality in research?
- anonymity - people must remain anonymous
53
Evaluation of naturalistic
observations:
+ high external validity - findings can be generalised to real life as behaviour is studied in an environment in which it would normally occur
- replication difficult as there many be uncontrollable extraneous variables
54
Evaluations of controlled observations:
- cannot be as readily applied to real-life situations
+ extraneous variables less of a factor so replication is easier
55
Evaluation of covert observations:
+ removes problem of participant reactivity as behaviour watched will be natural - increases validity
- ethics can be questioned
56
Evaluation of overt observations:
+ more ethical than covert
- knowledge participants have that they are being observed may act as a significant influence on behaviour
57
Evaluation of participant observations:
+ increased insight into the lives of the people being studied - increasing validity
- researchers may come to identify too strongly with those they are studying and lose objectivity ( 'going native' line between participant and researcher blurs )
58
Evaluation of non-participant observations:
+ researchers maintain a objective psychological distance from their participants so there is less danger of them 'going native'
- may lose valuable insight as to far removed from the people and behaviour they are studying
59
What is a structured observation?
allow the researcher to determine their observation using a pre-determined list of behaviours and sampling methods
60
What is a unstructured observation?
researcher writes down everything they see
61
Evaluation of structured observations:
+ behavioural categories make recording of data easier and more systematic
+ data produced numerical quantitative data so analysing and comparing behaviour observed more straightforward
62
Evaluations of unstructured observations:
- qualitative data more difficult to record and analyse
+ benefits from more richness and depth of detail in the data collection
- greater risk of observer bias as behavioural categories are not present
63
Evaluation of behavioural categories:
+ can make data collection more structured and objective
- must be clear and unambigiuous
- ensure all behaviour included in categories
- categories should be exclusive and not overlap
64
Evaluation of event sampling:
+ useful when the target behaviour or event happens quite infrequently and could be missed if used time sampling
- if the specified event is too complex, the observer may look over important details if using event sampling
65
Evaluation of time sampling:
+ effective in reducing the number of observations that have to be made
- might be unrepresentative of the observation as a whole
66
What may a questionnaire be assessing?
the dependant variable in an experiment
67
What is a structured interview?
made up of a pre-determined set of questions that are asked in a fixed order
68
What is an unstructured interview?
works like a conversation. There are no set questions but a general aim that a certain topic will be discussed but interaction is free flowing
69
What is a semi-structured interview?
there is a list of questions that have been written in advance but interviewers are also free to ask follow-up questions where they feel appropriate. Job interview for example.
70
What are the three types of closed questions?
- likert scales
- rating scales
- fixed choice option
71
How does a likert scale work?
respondent indicates their agreement. for strongly disagree to strongly agree
72
How do rating scales work?
similar to likert scale but respondent indicates a value that represents their strength of feeling about a particular topic. 1 - 10 scale
73
How to design an interview?
- the interview schedule should be standardised to reduce effect of interviewer bias
- interviewer can either take notes throughout interview or record it and analyse it later
- interviews usually involve a single participant however group interviews may be appropriate in some cases especially a clinical settings
- in one on one interviews setting should be quiet so interviewee is more likely to open up
- neutral questions to begin to make interviewee comfortable
- they should also be reminded that their answers will be treated in the strictest confidence
74
What to avoid when writing interview questions:
- overuse of jargon
- emotive language
- leading questions
- double-barrelled questions
- double negatives
75
Evaluations of primary data:
+ authentic data obtained from the participants themselves for the purpose of a particular investigation
- requires time and effort from the researcher
76
Evaluations of secondary data:
+ easily accessed requiring minimal effort
- substantial variation in the quality and accuracy of secondary data - may be out of date or incomplete
- the content of the data may not quite match the researcher's needs or objectives
77
Evaluation of qualitative data:
+ rich in detail - meaningful insight into participants worldview
+ greater external validity
- difficult to analyse - doesn't lend itself to be summarised statistically so patterns and comparisons within data may be hard to identify
- conclusions often rely on subjective interpretations of the researcher
78
Evaluation of quantitive data:
+ simple to analyse, therefore comparisons between groups can be easily drawn
+ numerical data tends to be less open to bias
- narrower in scope and meaning than qualitative data, may fail to represent 'real-life'
79
What are the measures of central tendency?
- mean
- median
- mode
80
What are the measures of dispersion ?
- range
- standard deviation
81
What is it known as when data is divided into categories ?
discrete data
82
What are raw scores?
scores derived from a test or observation yet to be summarised in a table or chart
83
What kind of data / scores are in tables?
descriptive statistics
84
What does a normal distribution look like in a graph?
symmetrical bell shaped curve
85
What does a skewed distribution look like on a graph?
appear to lean on side or the other. In a positive skew distribution is concentrated towards the left of the graph. In a negative skew distribution is concentrated towards the right of the graph
86
When to use the sign test:
1. when looking for a difference
2. when used a repeated measures design
3. when we have nominal data ( this can be converted for the purpose of carrying out the test )
87
Evaluations of peer review:
+ anonymity
produces a more honest appraisal
- publication bias
tendency for editors of journals to want to publish significant 'headline grabbing' findings to increase the credibility of their publication. Also prefer to publish positive results - false impression
- burying ground-breaking research
the peer review process may suppress opposition to mainstream theories, wishing to maintain the status quo within particular scientific fields. They can also be critical of research that contradicts their own view and favourable to one that matches it. Established scientists are also more likely to be chosen as reviewers so findings that correlate with current opinion are more likely to be published. Effect of slowing down the rate of change within a particular scientific discipline.
88
What is a case study?
an in-depth investigation, description and analysis of a single individual, group, institution or event
89
What is content analysis?
a research technique that enables the indirect study of behaviour by examining communications that other people produce, for example, in text, email, TV, film and other media
90
What is coding?
The stage in content analysis in which the communication to be studied is analysed by identifying each instance of the chosen categories ( e.g words, sentences, phrases etc.)
91
What is thematic analysis?
an inductive and qualitative approach to analysis that involves identifying implicit or explicit ideas within the data. Themes will often emerge once the data has been coded
92
Evaluations of case studies:
+ detailed insights on unusual atypical forms of behaviour
+ may contribute to our understanding of 'normal' functioning ( case of HM - existence of separate stores in STM and LTM )
+ may generate hypothesis for future study, one contradictory instance may lead to the revision of an entire theory
- issue of generalisability
- personal accounts may be prone to inaccuracy and memory decay ( low validity
93
Evaluations of content analysis:
+ produce both qualitative and quantitative data depending on aim of research
+ high external validity
+ gets around ethical issues. Much of info is in public domain
- studied indirectly so analysed outside of the context within which it occurred - danger researcher may attribute options and motivations that weren't intended originally
- researcher own bias may effect process
- lack of objectivity
94
What is reliability?
refers to how consistent the findings from an investigation or measuring device are. A measuring device is seen to be reliable if it produces consistent results every time it is used.
95
What are the two ways in which you can assess reliability?
- test-retest
- inter-observer reliability
96
What is test-retest reliability?
a method of assessing the reliability of a questionnaire or psychological test by assessing the same person on two separate occasions. Showing the extent the test produces the same answers, is consistent/reliable
97
What is inter-observer reliability?
The extent to which there is agreement between two or more observers involved in observation of a behaviour. This is measured by correlating the observations of two or more observers. A general rule is if total number of agreements divided by total number of observations is higher than 0.8 the data has high inter-observer reliability
98
How to improve reliability:
questionnaires -
should be measured using test-retest if score is low it may require some items to be deselected or rewritten ( replacing open questions with closed ones which are less ambiguous
Interviews -
same interviewer each time or interviewers must be properly trained - easily avoidable in structured interviews
experiments -
more achievable in a lab than field. more about precise replication of a method than reliability of a finding. However one thing that may effect reliability is if participants were tested under slightly different conditions each time they were tested
observations -
improved by making sure that behavioural categories are properly operationalised and that they are measurable and self evident. shouldn't over lap and all possible behaviours must be covered in checklist
99
What is validity?
the extent to which an observed effect is genuine - does it measure what it is supposed to ? can it be generalised beyond the research setting it was found in ?
100
What is face validity?
does it appear to measure what it is supposed to
101
What is concurrent validity?
the extent to which a psychological measure relates to an existing similar measure
102
What is ecological validity?
extent to which findings can be generalised to a different setting and situation
103
What is temporal validity?
extent to which findings from a research study can be generalised to another era
104
What is internal validity?
refers to whether effects observed are due to the manipulation of the independent variable and not some other factor
105
What are the levels of measurement:
nominal
ordinal
interval
106
How is nominal data represented ?
in the form of categories. one item can only appear in one category
107
How is ordinal data represented ?
it is ordered in some way. it is also based on a subjective opinion rather than objective measures
108
How is interval data represented ?
based on a numerical scale that includes units of equal and precisely defined size
109
What is a type 1 error ?
the incorrect rejection of a null hypothesis - ( false positive )
110
What is a type 2 error ?
a false negative - accepts the null hypothesis but shouldn't
111
What is the Chi-squared test ?
a test for difference or correlation between two variables or conditions.
data used is nominal and an unrelated ( independant ) design
112
When do you use the Mann-Whitney test ?
a test for difference between to sets of scores.
data at least ordinal and using an unrelated design ( independent groups )
113
When do you use the Pearson's r test ?
a parametric test for correlation when data is at interval level
114
When do you use the Related t-test ?
a test for difference
data must be interval with a related design
115
When do you use the Sign test ?
to analyse difference
data should be nominal or better
116
When do you use the Spearman-rho test ?
correlation when data is at least ordinal
117
When do you use the Unrelated t-test ?
when testing for difference
data must be interval with an unrelated design
118
When do you use the Wilcoxon test ?
when testing for difference and data is at least ordinal and a related design
119
What do you need to include in a scientific report ?
- abstract
- introduction
- method
- results
- discussion
- references
120
What is a paradigm ?
a set of shared assumptions and agreed methods within a scientific discipline
121
What is a paradigm shift ?
the result of a scientific revolution - a significant change in the dominant unifying theory within a scientific discipline
122
What does Kuhn ( 1962 ) say distinguishes scientific disciplines from non-scientific ones ?
he saids scientific disciplines have a paradigm ( universally accepted belief) unlike social sciences like psychology who lack this - has to many conflicting approaches
123
How does theory construction occur ?
through gathering evidence via direct observation
124
What did Kuhn and Popper argue in 1934 ?
that the key criterion of a scientific theory is its falsifiability
125
What is objectivity ?
When all sources of personal bias are minimised so as to not distort or influence the research process
126
What is the empirical method ?
scientific approaches are based on the gathering of evidence through direct observation and experience
127
What is replicability ?
the extent to which scientific procedures and findings can be repeated by other researchers
128
What is falsifiability ?
the principle that a theory cannot be considered scientific unless it admits the possibility of being proved false
