2 - Research Methods Flashcards
1
Q
Describe what an aim consists of
A
It outlines the research topic
Always starts with “to investigate”
2
Q
What is a hypothesis?
A
A prediction on the outcome/results of the study/experiment
3
Q
What are the 2 types of alternative hypothesis and explain them
A
Directional (1-tailed) - states which way they predict the results will go. has to have previous research/ a valid reason as to why the direction is what it is.
Non-directional (2-tailed) - states there will be a difference but not what that difference will be. Will always start “there will be a difference”
4
Q
What is a null hypothesis?
A
A hypothesis that states there will be no difference OR any difference is down to chance
5
Q
What is an independent variable?
A
The thing that is manipulated/changed
6
Q
What is a dependent variable?
A
The thing that is measured
7
Q
Define operationalisation
A
Explaining how the variable can be manipulated/measured
8
Q
What is a correlational hypothesis?
A
There are 2 co-variables, 2 things which are measured and compared for a relationship. No IV and DV.
9
Q
List the 5 types of sampling
A
Random sampling Opportunity sampling Volunteer sampling Systematic sampling Stratified sampling
10
Q
Define random sampling, give an example and give both a strength and a weakness
A
Each participant has an equal chance of selection
Eg: name from a hat
+ not biased
- down to chance if you get a wide range of people
11
Q
Define opportunity sampling, give an example and give both a strength and a weakness
A
When easily available people are used in the sample
Eg: researcher may ask parents picking their children up from school
+ easy and straight-forward to carry out
- not representative of the whole population
12
Q
Define volunteer sampling, give an example and give both a strength and a weakness
A
When people put themselves forward after the researcher advertises the study
Eg: newspaper/poster
+ less likely to lose volunteers/drop out
- volunteers likely to be similar types of people
13
Q
Define systematic sampling and give both a strength and a weakness
A
Selecting the nth name from every list
+ fair and easy
- down to chance if you get a wide range of people
14
Q
Define stratified sampling and give both a strength and a weakness
A
Selecting people from every portion of the population in the same proportions
+ good representation - guaranteed to get grasp of whole population
- time-consuming, the ratio of population is not accounted for
15
Q
What does an experiment involve a change in?
A
Independent variable
16
Q
List the 4 types of experiment
A
Laboratory experiment
Field experiment
Natural experiment
Quasi experiment
17
Q
Define what a laboratory experiment is, give an example and give both a strength (2) and a weakness (4)
A
Controlled - artificial environment. The IV is manipulated. Participants are randomly assigned to their conditions.
Eg: Milgram, Asch, Pavlov, Skinner etc.
+ High control over extraneous variables, replicable
- Artifical setting, lacks generalisability, low external, demand characteristics, low mundane realism
18
Q
Define what a field experiment is, give an example and give both a strength (3) and a weakness (2)
A
Natural environment, the IV is manipulated
Eg: Piliavin - bystander behaviour
+ High mundane realism, behaviour is more authentic and valid, high external validity
- Loss of control of extraneous validity, ethical issues (no consent and invasion of privacy)
19
Q
Define what a natural experiment is, give an example and give both a strength (2) and a weakness (3)
A
IV is not manipulated - it’s unplanned and has occurred because of a naturally occurring event. Could be a natural or controlled setting
Eg: Hodges and Tizard - the effects of institutionalisation
+ Provides opportunities, high external validity
- Reducing opportunities - limits scope for generalisability to other findings, cannot be done randomly, can’t guarantee exact replication
20
Q
Define what a quasi experiment is, give an example and give both a strength (2) and a weakness (2)
A
IV is not manipulated - exists on (mostly pre-existing) difference between people (eg: gender, age, personality). Planned manipulation of natural occurring IV. Could be natural or controlled setting.
Eg: Anastasi and Rhodes - effects of age on eye witness test
+ High internal validity, control extraneous variable
- cannot randomly allocate participants to conditions, confounding variables manipulate DV consistently
21
Q
What is a self-report method?
A
Where the participant reports their own thoughts and feelings about a particular matter
22
Q
What are questionnaires and interviews examples of?
A
Self-report methods
23
Q
What are the 2 types of question? Describe them and give the type of data they use
A
Open question - the participant can give any answer they wish - qualitative
Closed question - there are a set number of responses which the participant selects from - quantitative
24
Q
Define questionnaire
A
A self-report method with written questions which could be open or closed that are used to record thoughts and feelings
25
List and explain the 3 types of closed questions used in questionnaires
Fixed choice option - list of options, tick a box
Likert scale - respondent indicates their agreement
Rating scales - select a value most representative about a person’s feelings about a particular topic
26
What are the evaluation points that questionnaires need to be to be used and carried out effectively (7)?
Fixed choice option questions need to cover all bases
Open questions need to be specific
Overall questions need to be appropriate/understandable
Questions can’t have double negatives (eg: do you not agree that we shouldn’t...)
Questions can’t be double-barrelled (2 questions in 1)
They can’t be biased or have emotive language
They can’t be misleading questions
27
What are interviews?
Mostly face-to-face questions though some may be conducted over the phone
28
List the 3 types of interview
Structured
Un-structured
Semi-structured
29
Explain what a structured interview is
Like questionnaires, but face-to-face or over the phone. Consists of standardised preset answers. A computer with pre-set questions CAPI. Sometimes has a list of pre-determined questions
30
Explain what an un-structured interview is
A conversation. The interviewer has a general idea of topic to discuss. They are able to probe deeper and follow interesting avenues
31
Explain what a semi-structured interview is
Still has a list of issues/questions to ask/discuss but they take place in any order. The interviewer can veer away from standardised questions. They are generally open-ended but data can still be collected.
32
What does CAPI stand for?
Computer Assisted Personal Interviews
33
Give 2 strengths and 4 weaknesses of un-structured interviews
+ More detailed information can be obtained from each participant
+ Information can be accessed that might not revealed by using pre-determined questions
- Interviewer bias may be a particular issue as the interviewer is improvising
- Reliability may be affected by different interviewers asking different questions, or asking the same questions in different ways
- More difficult to analyse data - more of it and different participants may have been asked different questions
- Different questions may be interpreted in different ways by different participants
34
Give 4 strengths and 1 weakness of structured interviews
+ Requires less interviewing skill, therefore can be done by non-professional interviewers
+ Easier to analyse as the answers are more predictable
+ Can be easily replicated because the questions are standardised
+ Responses tend to be more honest so social desirability is less of a problem
- The answers the participants give may be restricted by the questions asked
35
Define interviewer bias
Where the interviewer’s own opinions may influence the interviewee
36
Give a weakness of both structured and un-structured interviews
Reliability may be affected by the same interviewer behaving differently on different occasions
37
List the 8 different types/factors of an observation
Overt/covert
Structured/unstructured
Participant/non-participant
Controlled/naturalistic
38
Explain a overt and covert observation, with strengths and weaknesses for each
Overt: the participants are aware they are being observed
+ Ethical - no deception
- Lacks validity - may not act naturally (Hawthorne effect)
Covert: Participants are unaware they are being observed
+ Increases validity, acting naturally (no Hawthorne effect)
- Less ethical - deception
39
Explain a structured and un-structured observation, with strengths and weaknesses for each
Structured: The researcher determines precisely what behaviours are to be observed and uses a standardised checklist to record the frequency with which they are observed within a specific timeframe
+ Miss less, focus/specific on certain behaviours
- Additional behaviour is ignored
Un-structured: The observer recalls all relevant behaviour but has no system
+ Additional behaviour is not ignored
- Lots of detail - easy to miss things
40
Explain a participant and non-participant observation, with strengths and weaknesses for each
Participant: researcher actively gets involved with participant activity so they can experience it for themselves
+ Better insight to behaviour
- Going native - experimenter bias
Non-participant: the observer remains separate from the participant to maintain objectivity
+ No risk - eyes always on objective
- Less insight
41
Explain a controlled and naturalistic observation, with strengths and weaknesses for each
Controlled: observing behaviour under controlled conditions
(eg: Zimbardo)
+ Good internal validity - control of extraneous variables. The more reliable the more replicable
- Artificial environment, bad external validity, Hawthorne effect
Naturalistic: Research method carried out in a naturalistic setting, in which the investigation doesn’t interfere in any way but merely observed the behaviour in question
+ Good external validity, no Hawthorne effect
- Lacks internal validity, isn’t replicable and therefore reliable
42
Define the Hawthorne Effect
The alteration of behaviour by the participants of a study due to their awareness of being observed
43
Define sampling
The method is used to select participants, such as random, opportunity and volunteer, or to select behaviours in an observation
44
What are behavioural categories? Give strengths and weaknesses
Where the observer divides a target behaviour into a subset of specific and operationalised behaviours
+ Makes data collection more structured and objective. When done right, they are observable, measurable and self-evident
- Categories may overlap
45
List the 3 sampling methods used in observations
Continuous sampling
Event sampling
Time sampling
46
Define and evaluate event sampling
An observational technique in which a count is kept of the number of times a certain behaviour (event) occurs
+ Useful when the target behaviour/event is infrequent - can be missed during time sampling
- If specified event is too complex then the observer may overlook important details
47
Define and evaluate time sampling
An observational technique in which the observer records behaviours in a given time frame
+ Reduces number of observations that have to be made
- Activity of intervals may not be representative of the whole observation
48
Define and evaluate continuous sampling
An observational technique where all instances of target behaviour are recorded. In complex observations this is not always possible so behaviour is missed
49
What unit is given when interpreting correlations
Number between -1 and 1. The closer to either 1 or -1 it is the stronger it is (1 is positive, -1 is negative). The closer to 0 it is the weaker it is, (whether it is positive or negative)
50
List and explain the relationships of the 4 types of correlation
Positive correlation - when one variable increases, the other increases at the same rate
Negative correlation - when one variable increases, the other decreases at the same rate
No correlation - no relationship between the co-variables
Curvilinear correlation - the relationship is predictive, but it is curved not linear; it peaks at a certain point (rarely is but can be negative)
51
What is an intervening variable?
A variable that comes between 2 other variables, which is used to explain the association between those 2 variables
52
Define correlation
Determining the extent of an association between 2 variables
53
Define co-variable
The 2 measured variables in a correlation
54
What is a continuous variable?
A variable that can take on any value within a certain range
55
What is the difference between an experiment and a correlation?
In an experiment the researcher controls or manipulated the IV.
In a correlation there is no manipulation of the 2 variables.
It is therefore not possible to determine cause and effect.
56
List 5 factors that occur in a correlation, 6 that occur in an experiment, and 4 that occur in both
C: Scattergraph, co-variables, looking for a relationship (me), correlation co-efficient, continuous variable
E: Bar charts, IV and DV, looking for a difference, cause and effect, independent measures design, matched pairs design
B: Hypothesis, quantitive data, repeated measures design, testing data significance
57
What is a sampling frame and what is it used in?
A list of names which a sample is then drawn from
| Used in random and systematic sampling
58
Define validity
Accuracy
59
List the 3 types of experimental design
Independent groups
Matched participants
Repeated measures
60
What are experimental designs?
How psychologists organise groups of participants
61
Define what an independent groups design is and give positives (3) and negatives (2)
A separate group of participants for each condition of the IV (music/no music etc. Quasi experiments can only be this type of experimental design)
+ least time consuming
+ no demand characteristics
+ no order effects - when you do it again
- could be biased (deliberate or accidental)
- individual differences
62
What are order effects?
They can occur in a repeated measures design and and refers to how the positioning of tasks influences the outcome e.g. doing a test first with no revision then again with revision or vice versa
63
Define what a matched participant/matched pairs design is and give positives (3) and negatives (1)
A separate group of participants for each condition of the IV but they are fitted for certain characteristics.
Eg: the IV is gender, but the 2 groups are the same age
+ no demand characteristics
+ no order effects
+ individual differences are minimised - variables between each participant that affect ability to do a task
- there will always be some individual differences
64
Define what a repeated measures design is and give positives (1) and negatives (2)
Every participant completed all conditions.
Eg: one group has music playing but then the same group does another test without music. This method cannot be used if the IV is quasi.
+ no bias/individual differences
- order effects
- demand characteristics
65
What is a pilot study and what is their purpose?
Mini versions of the experiment to analyse it before carried out.
It also tests:
The measures used
Reliability - test and re-test
Identifies extraneous variables so controls can be put in place for the actual study.
It ensures all the ethical issues have been dealt with
66
Define ethics
“The consideration of what is acceptable or right behaviour in the pursuit of personal or scientific goal” - Caldwell, 2000
67
Who created the 5 ethical guidelines?
The British Psychological Society (BPS)
68
List the 5 ethical guidelines
```
Informed consent
Right to withdraw
Deception
Confidentially
Protection of participants
```
69
Define informed consent and give an example of a study where it is lacked
Making participants aware of the aim of the study, procedures, participants’ rights and what their data is used for.
Milgram
70
Define right to withdraw and give an example of a study where it is lacked
The participant has the right to leave at any time and withdraw their data.
Zimbardo
71
Define deception and give an example of a study where it is lacked
Deliberately misleading or withholding information regarding the experiment or the use of the data.
Asch
72
Define cofidentiality and give an example of a study where it is lacked
Participants have the right to control information about themselves. They have the right to remain anonymous and their data not to be shared.
Confidentiality - the right to have any data
Patient HM, Clive Wearing
73
Define protection of participants and give an example of a study where it is lacked
This includes protection and welfare of animals.
Participants should not be placed at any more risk than usual as a result of the study - physical or psychological.
Skinner, Pavlov
74
How do you obtain informed consent?
Consent letter/form that details everything.
| If the participant is under 16, parental consent is required
75
Give 3 other ways of getting consent if it is impractical to ask them
Presumptive consent - ask a similar group of people to the participant if it’s acceptable
Prior general consent - participants give their permissions to take part in a number of different studies - one includes deception. They consent to being deceived.
Retrospective consent - participants are asked for consent after the study (during the debrief). They may not have been aware of their participation or that they may have been deceived.
76
How can a researcher deal with deception and protection of participant?
Complete debrief - the participants are told about their data usage and right to withdraw it.
Offer (if necessary) counselling - reassure them that their actions where normal/typical behaviour.
77
How can a researcher deal with confidentiality?
Protect personal details - or keep anonymity.
| Remind/reassure participant in debrief that their data will be protected
78
Explain internal validity
Are we measuring what we set out to measure?
It is lowered if there are extraneous or confounding variables because we are then no longer testing the effect of the IV or DV.
79
Define and give examples of extraneous variables
“Nuisance variables” which don’t affect with the IV. They directly impact the DV
Eg: social desirability, demand characteristics
80
Define what confounding variables are
Variables that vary systematically with the IV so we cannot be sure what caused the change in the DV (affects everyone the same)
81
Explain external validity
Can we accurately generalise to the wider population?
82
List and define the 3 types of external validity
Population validity - is our sample representative of the whole population?
Ecological validity - is the environment accurate to real life?
Validity over time (AKA: temporal validity) - is the experiment still accurate to today’s society?
83
Define what participant variables are
Any individual difference between the people taking part that may interfere with the outcome of the investigation
84
Define what situational variables are
Any aspect of the experimental environment that may interfere with the outcome of the investigation
85
Define what demand characteristics are
A type of extraneous variable
Deliberate and difficult to control
Where participants may guess the aims of the research and then may act in a way that they think is expected
86
Define what investigator effects are and give an example
Unwanted influence of the researcher on the experiment.
This may be unconscious behaviour, such as smiling more with one condition compared to another.
Eg: the green spoon effect, interviewer and experimenter bias
87
List, define and state where they are most commonly found, the 3 types of participant activity
Hawthorne effect - when the added attention of being in a study affects participant behaviour - most common in observations
Demand characteristics - when participants think they have figured out the aims of the experiment and act in a way they think is expected - M.C.I experiments
Social desirability bias - when participants try to look good by answering/behaving in a socially acceptable way - M.C.I questionnaires/interviews
88
List and define the 3 types of investigator effects
Experimenter bias - when the experimenter effects the results eg: body language etc.
Interviewer bias - when the interviewer affects the responses of the interviewee
Greenspoon effect - when the interviewer makes affirmative noises - the interviewee thinks they’re giving good answers
89
List the 5 controls of extraneous variables
```
Randomisation
Counterbalancing
Single blind design
Standardisation
Double blind design
```
90
Define randomisation and state what it controls
Using chance at every opportunity
| Experimenter bias
91
Define counterbalancing and define what it controls
When half of the participants do condition one and the other half do condition two. Then they swap.
Oder effects
92
Define what a single blind design is and define what it controls
The use of deception to mislead participants
| Demand characteristics
93
Define standardisation and state what it controls
Keeping everything the same for every participant
| Experimenter bias
94
Define what a double blond design is and state what it controls
When both the researcher and participant don’t know the aims of the study
Demand characteristics and experimenter bias
95
Define reliability
Consistency - getting the same results on the same experiment every time
96
What is inter-rater reliability?
Whether the observers are scoring in the same way
97
How do you check for reliability?
Conduct the test again and we if you get the same results (test-retest reliability)
Conduct a spearmans rho test comparing the scores - this tests for a correlation
98
What is test-retest reliability?
When you conduct the test again and see if you get the same results
99
What is a spearmans rho test?
Used when checking for reliability
| Doing the same test again and comparing the score, this tests for a correlation
100
How can you improve reliability? (5)
Observers familiarise themselves with the behavioural categories first
Conduct a small scale pilot study first
Compare the data observers have got by calculating a correlation coefficient
Operationalise variables if needed
Repeat the experiment
101
Explain the scenario of Sir Cyril Burt
He falsified he findings and claimed that intelligence was inherited.
This led to the 11+ test which determined which school everyone went to.
Kamin challenged him and he was exposed as a fraud.
Nowadays people move away from grammar schools and the 11+ test.
102
List the 3 purposes of peer review?
To validate the quality and relevance of research
To suggest amendments or improvements
To allow allocation of research funding
103
Explain the process of peer review
Other psychologists working in similar fields check report
Things considered:
Validity, significance, originality, methods, design
The report can be accepted, amendments can be suggested or it can be rejected
The final report is submitted to the panel or is assessed for publication
104
What 5 things are considered during a peer review?
```
Validity
Significance
Originality
Methods
Design
```
105
Explain in detail 3 evaluation points of peer reviews
- anonymity - reviewers are more honest (+) if anon. but some get revenge/abuse anonymity. Researchers are in direct competition.
- publication bias - editors want to publish “headline grabbing” findings and positive results. Research could be ignored/disregarded. This creates a false impression of the current state of psych if publishers are selective.
- burying ground breaking research - suppress opposition to mainstream theories. Researchers tend to be really critical on opposing work and favourable to supporting work. P.R. may slow down change in psych
106
List 2 positive points and 8 negative points when evaluating peer reviews
+ essential for high-quality research
+ keeps check on dishonest psychologists
- publication bias, expensive, time-consuming, subjective, anonymity, bias, preserving status-quo, Internet
107
Define and evaluate qualitative data
Expressed in words, non-numerical
+ greater external validity - covers all bases, more meaningful insight
- difficult to analyse
- conclusions are subjective/subject to bias
108
Define and evaluate quantitative data
```
Expressed numerically rather than in words
+ easy to compile or analyse
+ conclusions aren’t subjective
- narrow scope
- less detail
- may not represent real life
```
109
Define and evaluate primary data
First-hand from participants, collected scientifically for the purposes of the research
+ fits the job - specific info for what the researcher wants
- time and effort - requires considerable planning
110
Define and evaluate secondary data
Data collected by someone other than the person doing the research
+ inexpensive
+ easily accessible, quick, requires minimal effort
- possibly out-dated or incomplete
- variation in quality and accuracy
- may not be specific to researcher’s needs
111
Define meta-analysis
This collates findings from several studies that have already been done
112
What does < mean
Less than
113
What does > mean
Greater than
114
What does ~ mean
Approximately equal to
115
What does << mean
A lot smaller than
116
What does >> mean
A lot greater than
117
What does CX mean
Proportional to
118
List and define the 3 measures of central tendency
(The average)
Mean - sum of all averages divided by the number of values there are
Mode - the most commonly occurring value
Median - the middle value
119
List and define the 2 types of measures of dispersion
(To find the spread of the data)
Range - highest value minus the lowest value
Standard deviation - calculates how far scores deviate from the mean
120
Evaluate the mean
+ more representative of data as a whole
| - includes extreme values
121
Evaluate the mode
+ can be used for qualitative and quantitative data
+ not affected by extreme values
- won’t always get an answer/more than one
- only uses most frequent data - this may not represent the data as a whole
122
Evaluate the median
+ not affected by anomalies/extreme values
+ can be used when data is not interval
- answer may not always be part of the data
123
Evaluate the range
+ includes all data pieces
- only takes 2 most extreme values - could be anomalies
- unrepresentative of data as a whole
124
Evaluate standard deviation
+ all data - more representative of data as a whole
| - affected by extreme values
125
Explain what a bar graph is and how and why it is used
Used for data in discrete categories. The bars are separated by a
gap to show they are not continuous.
A bar chart should not be used to plot individual participant scores
but the total or mean or percentage scores for each group.
The DV goes on the y axis and the IV goes on the x axis.
126
Explain what a histogram is and how and why it is used
Used for continuous frequency data.
The bars are touching to show that the data is continuous.
The x axis is made up of equal sized intervals of a single category. The y axis represents the frequency.
Sometimes a frequency polygon is drawn by joining the midpoints at the tops of the bars
127
Explain what a line graph is and how and why it is used
Used for continuous frequency data.
The x axis is made up of equal sized intervals of a single category. The y axis represents the frequency.
Useful for comparing two sets of frequency data on one graph would not be easy to see on a histogram.
128
Explain what a scatter graph is and how and why it is used
Used for correlational data
The co-variables go on the axes.
The dots are not joined but sometimes a line of best fit is drawn.
129
Explain normal distribution
Bell shaped curve.
The mean, mode and median all lie at the midpoint.
Most scores occur around the middle with fewer being clustered as they occur above and below the mean.
The tails of the curve, which extend outwards, never touch the horizontal x axis as more extreme scores are always theoretically possible.
130
Explain positive distribution
A positive skew is when the long tail is on the positive side of the
peak, and some people say it is "skewed to the right".
Most scores fall below the mean.
The mean, mode and median are not in the same place – the mean gets pulled to the right because it is affected by extreme values.
131
Explain negative distribution
A negative skew is when the long tail is on the negative side of the peak, and some people say it is "skewed to the left".
Most scores fall above the mean.
The mean, mode and median are not in the same place – the mean gets pulled to the left because it is affected by extreme values.
132
What are inferential statistics?
They draw conclusions about data and tell us whether our results are significant enough that we can generalise with any certainty.
They are based around probability, they assess the probability that the results could just be down to chance - if there is a low probability of this then we can generalise.
133
Discuss significance
If a test shows our results are significant we accept our alternative hypothesis, if not then we accept our null.
A test is significant if it meets the level of probability we have chosen.
134
What probability do we always use unless otherwise stated?
P =< 0.05
135
What are the steps in calculating the sign test (6)?
1. Determine whether the 2 variables result in -, + or 0 with each participant. Tally up how much for each sign.
2. The observed value is the lowest sign (S).
3. Determine if it is 1 or 2-tailed (N-D/D).
4. Total number of participants - 0 category = N
5. Use N in critical values table to determine CV. Use p =< 0.05 unless otherwise stated.
6. If S is =< CV, significant, use alt. hypothesis.
If S > CV, insignificant, use null.
136
Why might a researcher choose p =< 0.01 over p =< 0.05?
Used in medicine trials eg: drug testing
Tighter measure of significance
Consequences have a bigger impact - life and death
137
Give 2 different categories of extraneous variables
Participant reactivity
| Investigator effects
138
How do you improve the reliability of questionnaires?
```
No leading questions
No jargon
Pilot questionnaire
Create closed questions
Alrernate direction of closed questions
```
139
How do you improve the reliability of interviews?
Standardised questions - structured interview
No leads questions - word them clearly
Use the same interviewer - emphasis on language / greenspoon effect
Train interviews
140
How do you improve the reliability of an experiment?
```
Test-retest
Control IV - same experience in each condition
Lab study
Pilot study
Standardising - procedure, IV, test DV
```
141
How do you improve the reliability of observations?
Test-retest - check for a correlation
Multiple observers
Behavioural categories - structured obs
Operationalise categories
142
Define population validity
The extent to which our sample is representative of the whole population
143
Define ecological validity
The extent to which the environment is accurate to real life
144
Define temporal validity.
| What is this also known as?
The extent to which the experiment is still accurate in today’s society.
Validity over time.
145
Define concurrent validity
The comparison to an existing test of questionnaire with the one you are interested in
146
Define face validity
The extent to which test items look like what the test claims to measure
147
How do you improve the validity of questionnaires and psychology tests?
Many include lie scales to measure social desirability bias (eg: Eysenck). Validity could also be increased by assuring them they’ll remain anonymous.
148
How do you improve the validity of case studies?
Control groups mean the researcher is better able to asses whether changes in the DV were due to the IV - respondent validation. Also, they can standardise procedures to minimise impact of participant reactivity, investigator effects and single and double-bind procedures does the same.
149
How do you improve the validity of observations?
Covert observations create high ecological validity.
Broad, overlapping, ambiguous behavioural categories decrease validity. This can be demonstrated as things such as the coherence of the researcher’s reporting and the inclusion of direct quotes from participants within the report.
Validity also improved by triangulation - the use of a number of different sources as evidence.
150
Define predictive validity
The extent to which future predictions are correct.
| It requires you to compare test scores to performance on some other measure in the future.
151
Describe and explain what case studies are
| Include examples
An in-depth investigation, description or analysis of a single individual, group, institution or event. They often involve analysis of unusual individuals or events. Eg: rare disorders/events, but they can also do typical cases.
They are longitudinal and create qualitative data. Researchers create a case history of the individual - this includes interviews, observations, questionnaires, or a combination of all 3. Researchers can also gather data from family and friends.
Eg: genie, Romanian twins etc.
152
Evaluate case studies
+ detail into unusual topics. They may be preferred to superficial data forms. They could also add to information on normal behaviour - ecological validity.
+ circumnavigate (avoid) ethics - researchers can study effects of unethical situations without being the cause eg: genie.
+ lays foundations for future hypothesis and experiments - application.
- low generalisability due to subjective researchers and individual differences.
- time consuming - GRAVE?
- ethics - could bring back bad memories - P.O.P. Lack of anonymity - lots of detail could result in the public figuring out who it is.
153
What is a content analysis? Give examples.
| What is the aim of a content analysis?
A type of observational research where people are studied indirectly via communications they produce eg: emails, letters, diaries, media transcribed conversations/interviews etc.
The aim is to summarise the communication in a systematic way so conclusions can be drawn.
154
What are the steps in content analysis?
Sampling method - does the researcher look at every page of a book or just every 5th?
Coding the data - researcher uses behavioural categories to count the number of times something occurs. Decisions about behavioural categories may involve a thematic analysis.
Represent the data - you could count instances (quantitative data - usually happens) or descriptions (qualitative data - less common).
155
Describe thematic analyses
These may be involved in decisions about behavioural categories.
A technique used when analysing qualitative data.
Themes or categories are identified and then data is organised according to these themes.
156
What are the 5 main intentions of thematic analyses?
Identifying themes and drawing conclusions.
Ensuring the order represents the participants’ perspective.
Imposing order on the data.
Summarising the data.
Ensuring no preconceptions emerge instead of the imposed data (no bias).
157
Briefly state evaluation points regarding content analysis
+ replicable - reliability
+ based on real communications - external validity
- interpretation can be affected by language - internal validity
- meaning can be interpreted differently - internal validity
158
Explain nominal data. Give examples.
Data grouped into separate categories eg: boy/girl, yes/no
159
Explain ordinal data. Give examples.
Data that is ranked; the difference between items is not the same. A set of data is said to be ordinal is the values/observations can be put in order or having a rating scale attached.
Eg: questions such as “is your general health poor, reasonable, good or excellent?” May have those answers coded respectively as 1, 2, 3 and 4.
160
Explain interval data. Give examples.
Equal units of data. They can have minus value.
| Eg: temperature, weight gain.
161
Define measures of dispersion.
| List them.
Finding the spread of data.
| Range, standard deviation.
162
Define measures of central tendency.
| List them.
Finding the average.
| Mean, median, mode.
163
Define descriptive statistics
Characterising the data
164
Define inferential statistics
Term for data that could not have arisen by chance, or is extremely unlikely to have arisen by chance, or is extremely unlikely to have arisen by chance.
165
What are parametric tests?
A category of statistical tests that make calculations using the mean and standard deviation of a data set, making them a more powerful test.
166
What are non-parametric tests?
A category of statistical test used to analyse data that is at nominal or ordinal level.
167
Define significant
Term used for data that could not have arisen by chance, or is unlikely to have arisen by chance.
168
What is a test statistic?
The observed value calculated using a specific inferential statistic to analyse the data collected.
169
What is a significance level?
Usually set at 0.05, meaning there is a 5% probability results didn’t occur by chance.
170
What is a critical value?
A value a test statistic must reach in order for the null hypothesis to be rejected.
171
What is a type I error?
| What is a type II error?
Where you accept the alternative hypothesis when you should have accepted the null hypothesis - this is a false positive.
Where you accept the null hypothesis when you should have accepted the alternative hypothesis - this is a false negative. This is more likely in medicine as the significance level is 0.01.
172
What do inferential tests do?
| Explain them.
They draw conclusions about our data and tell us whether our results are significant enough that we can generalise with any certainty.
They are based around probability and assess the probability that the results could just be down to chance - if there is a low probability of this then we can generalise.
173
Explain the 3 factors that are needed in order for the Chi squared test to be used.
Explain how the Chi squared test works and what is required for a significant result.
Testing for a difference in IV (or association)
Nominal data
Independent groups design
It starts with a contingency table, you’ll be told the observed value and asked to find the critical value. DoF = (row - 1) x (column - 1).
The test is significant (accept alt hyp) if the obs val > C.V.
174
What is the ranking order for levels of measurement?
Nominal
Ordinal
Interval
175
Explain the 3 factors that are needed in order for the Spearman’s Rho test to be used.
What is required for a significant result?
Ordinal data - non-parametric Test
Tests for a correlation
Correlational design
Rho = observed value > critical value
176
Explain the 3 factors that are needed in order for the Pearson’s R test to be used.
What is required for a significant result?
Interval data - parametric test
Tests for a correlation
Correlational design
R = observed value > critical value
177
How do you calculate the number used to check the critical value for Spearman’s Rho and Pearson’s R?
Spearman’s Rho: N = number of participants
| Pearson’s R: df = number of participants -2
178
What are the 6 tests that test for a difference?
```
Unrelated t test
Related t test
Mann Whitney U test
Wilcoxon t test
Sign test
Chi squared test (also association)
```
179
Explain the 3 factors that are needed in order for the unrelated t test to be used.
What is required for a significant result?
Tests for a difference
Interval data
Independent groups design
Observed value > critical value
180
Explain the 3 factors that are needed in order for the related t test to be used.
What is required for a significant result?
Tests for a difference
Interval data
Repeated measures design/matched pairs design
Observed value > critical value
181
Explain the 3 factors that are needed in order for the man whitney u test to be used.
What is required for a significant result?
Tests for a difference
Ordinal data
Independent groups design
Observed < critical value
182
Explain the 3 factors that are needed in order for the wilcoxon t test to be used.
What is required for a significant result?
Tests for a difference
Ordinal data
Repeated measures design/matched pairs design
Observed < critical value
183
Which tests have a significant result if observed > critical value?
Which tests have a significant result if observed < critical value?
How do you remember?
Observed > critical value:
Chi squared, Spearman’s Rho, Pearson’s R, Unrelated t, Related t.
Observed < critical value:
Man Whitney U, Wilcoxon t, Sign test.
If it has an R in it, then observed > critical value.
184
Explain the 3 factors that are needed in order for the sign test to be used.
What is required for a significant result?
Testing for a difference
Nominal data
Repeated measures design
Observed < critical value
185
List the stages to carry out the sign test
State the hypothesis; determine if it’s one-tailed or two-tailed.
Record each pair of data, working out the difference; record a + for a positive difference and a - for a negative difference. (It doesn’t matter which way you subtract them). Add all the +’s and -‘s and then select the smaller value - this value is the calculated value, S.
Find the C.V. of S in the C.V. table; check the result is in the right direction (for a directional hypothesis). If S =< C.V, the result is significant.
186
State the order of a psychological report
Abstract, introduction, aims and hypotheses, method, results, discussion, references, appendices.
187
What is a procedure?
Step by step instructions of how the experiment was carried out.
It is part of the method section.
188
What is an introduction?
A large section of writing that outlines background research and explains why this study is being conducted and how it relates to the background research. It also gives rationale to the study.
189
What is a discussion?
A larger part of writing that evaluates the study, links findings to background research, explains how findings can be used in everyday life (application) and suggests possible future experiments.
It also includes a summary of the results and explanation, considerations for methodology (suggestions for improvements) and implications for theory.
190
What is an appendix?
This contains any example questionnaires, consent forms, raw data, calculations etc. Anything which is needed for evidence but that doesn’t go in the body of the report. This is at the end of the report.
191
What is a method?
| What are the 4 parts to it?
A section that is divided into parts and explains how the experiment was carried out.
Design, participants, apparatus/materials, procedure - usually in that order.
192
What are inferential statistics?
| Give examples.
They explain whether the results can be generalised or not. They go in the results section.
All statistical tests - eg: chi squared, pearsons R, sign test.
193
What are descriptive statistics?
| Give examples.
They describe and characterise the findings. They go in the results section.
Measures of central tendency and measures of dispersion.
194
What is a reference?
A list of all the journal articles and books that have been mentioned in the body of the report.
195
What is an abstract?
A paragraph that goes at the start of the report and summarises the aims, method and findings. This is often written last.
196
What is a design?
This states the research method, IV, DV, research design, ethics and issues to do with validity and reliability.
This goes in the method section.
197
What are results?
| What are the 2 parts of the results section?
A medium section of writing explaining what the experiment shows.
Inferential and descriptive statistics.
198
What are materials?
They outline all of the items used in the experiment. This goes in the method section.
199
What are aim and hypotheses?
Statements that outline the topic to be studied and what the expectations are. They are often added to the end of the introduction.
200
What are participants?
| Give examples.
This states who is studied eg: number, age, gender, ethnicity, and who the experimenters are. This goes in the method section.
201
What is the correct order for a reference of a book?
| What is the correct order for a reference of a journal?
Surname.1st initial.(date).title.location of publishing.publisher.
Surname.1st initial.(date).title of article.name of journal.volume.pages.
202
List the 5 features of science
Objectivity, replicability, falsifiability, theory construction, paradigm shifts.
203
Define and explain objectivity
When all sources of personal bias are minimised so are not to distort or influence the research process. It is basis of the empirical method.
Researchers must keep a ‘critical distance’ during research. Lab exps. tend to suffer the most objectivity.
204
Explain the empirical method
The scientific process of gathering evidence through direct observation and experience. They emphasise the importance of data collection based on direct, sensory experience. The experimental method and observational method are both examples of the empirical method.
205
Define and explain replicability
The extent to which scientific procedures and findings can be repeated by other researchers.
This can further assess both validity and generalisability.
In order for replicability to be possible, it is vital that psychologists report their investigations with as much precision, rigour and detail as possible, so others can verify their work and findings.
206
Define falsifiability
The principle that a theory cannot be deemed scientific unless it admits the possibility of being proved untrue. If it can’t be proved false, it is a pseudoscience.
207
What is the theory of falsification?
When a scientific principle has been successfully and repeatedly tested, it is not necessarily true. It has simply not been proven false yet.
208
What is a theory?
| Define and explain theory construction.
A theory is a set of general laws or principles that have the ability to explain particular events or behaviours. It has to be able to be scientifically tested.
Theory construction occurs through gathering evidence via direct observation.
A researcher should be able to make predictions through studying theories.
209
Define deduction
The process of deriving new hypotheses from an existing theory.
210
What is a paradigm?
| Define and explain paradigm shifts.
A paradigm is a set of shared assumptions and agreed methods within a scientific discipline. Kuhn said that social sciences (psychology) lack a universally agreed paradigm. Psychology has too much internal disagreement and has too many conflicting approaches.
A paradigm shift is a significant change in the dominant unifying theory within a scientific discipline, brought about by new findings and understanding. Lots of these happen in psychology - eg: approaches.
211
What goes in a consent form?
```
Aim
Outline of what the participant will have to do
Right to withdraw
Confidentiality
Any questions?
Somewhere to sign
```
212
What goes in a debrief?
```
What the experiment aimed to do
How they were deceived
Confidentiality
Right to withdraw
Where they can access more info
Any questions?
```
