Research methods Flashcards
1
Q
What is the aim of a study?
A
A general statement covering the topic/theory/concept that will be investigated.
2
Q
What does the aim of a study identify?
A
The purpose of the research.
3
Q
Provide an example of an aim in a study.
A
‘To investigate the effect of caffeine on memory.’
4
Q
What is a hypothesis?
A
A testable statement written as a prediction of what the researcher expects to find.
5
Q
How do hypotheses differ from aims?
A
Hypotheses must be precise and unambiguous, while aims are expressed in general terms.
6
Q
What are the two types of hypothesis?
A
- Null hypothesis (NH)
- Alternative hypothesis (AH)
7
Q
What should the alternative hypothesis include?
A
The independent variable (IV) and the dependent variable (DV).
8
Q
What does operationalising the IV involve?
A
Specifying how the independent variable is to be manipulated.
9
Q
What is the operational definition of the DV?
A
Specifying how the dependent variable is to be measured.
10
Q
What is a directional hypothesis?
A
A hypothesis that predicts the direction of the difference in conditions.
11
Q
What is a non-directional hypothesis?
A
A hypothesis that predicts that a difference will be shown without specifying the direction.
12
Q
What does the null hypothesis assert?
A
That the independent variable will not affect the dependent variable.
13
Q
What must all published psychological research include?
A
The null hypothesis (NH).
14
Q
What happens if results show no difference between conditions?
A
The null hypothesis must be kept/accepted.
15
Q
What are the two types of hypotheses for correlational investigations?
A
- Non-directional hypothesis
- Directional hypothesis
16
Q
What is the independent variable (IV) in an experiment?
A
The only variable that should be changed or manipulated.
17
Q
What is the dependent variable (DV) in an experiment?
A
The variable that is measured to determine the outcome of an experiment.
18
Q
Provide an example of an independent variable.
A
Whether participants learn a list of 20 words in silence or in the presence of loud music.
19
Q
What is required to observe the effect of the IV?
A
The dependent variable (DV).
20
Q
What type of data must the dependent variable be measured in?
A
Quantitative data.
21
Q
What does operationalising variables refer to?
A
How both the IV and the DV are implemented by the researcher.
22
Q
What are extraneous variables?
A
Any factors that intrude upon and adversely affect the DV.
23
Q
What can happen if extraneous variables are not controlled?
A
They can become confounding variables.
24
Q
What are confounding variables?
A
Extraneous variables that can affect the DV and negatively impact research findings.
25
What should researchers do to control extraneous variables?
Ensure they have the same effect across all conditions.
26
Fill in the blank: The IV must be _______ by the researcher.
[manipulated]
27
Fill in the blank: The DV is measured to assess the effect of the _______.
[IV]
28
True or False: Qualitative research collects data in the form of numbers.
False
29
What is the significance of operationalising the DV?
It enables relevant and appropriate data to be recorded per participant.
30
What are demand characteristics?
Demand characteristics are instances of interaction/interference between the research process and the participant that can adversely affect research findings.
31
How can demand characteristics affect participants?
Participants may pick up on cues about what is expected of them, leading to artificial or contrived performance on tasks.
32
What is a single-blind procedure?
A single-blind procedure is when participants do not know which condition they have been assigned to, preventing them from responding based on what they think is being tested.
33
What are investigator effects?
Investigator effects occur when the researcher's presence or behavior interferes with the research process, introducing bias.
34
How can a researcher's characteristics influence participants?
A researcher's characteristics, such as age, gender, and ethnicity, can influence how participants interact with them, affecting the research outcomes.
35
What is a double-blind procedure?
A double-blind procedure is when both participants and researchers do not know which condition each participant has been assigned to, minimizing bias.
36
What is randomisation in research?
Randomisation refers to the deliberate avoidance of bias by randomly assigning participants to conditions, ensuring objectivity.
37
What does standardisation mean in research?
Standardisation refers to maintaining identical procedures across all conditions and participants to ensure fairness and replicability.
38
What are pilot studies?
Pilot studies are small-scale trials conducted to test aspects of the proposed investigation before the main research.
39
What is a laboratory experiment?
A laboratory experiment is a research method where the researcher exerts high control over environmental factors to observe the effects of the independent variable on the dependent variable.
40
What are the strengths of laboratory experiments?
Laboratory experiments allow for easier establishment of cause-effect relationships and are high in internal validity due to controls.
41
What is a field experiment?
A field experiment is conducted in a natural setting, allowing for less control over extraneous variables compared to lab experiments.
42
What are the strengths of field experiments?
Field experiments have high external validity as they are conducted in real settings, making participants' behavior more reflective of real life.
43
What is a natural experiment?
A natural experiment involves research on naturally occurring phenomena where the researcher cannot manipulate the independent variable.
44
What are the strengths of natural experiments?
Natural experiments allow investigation of topics that would be unethical to study in a lab, providing high ethical and ecological validity.
45
What is a quasi-experiment?
A quasi-experiment is a research method that does not manipulate the independent variable but uses naturally occurring phenomena.
46
What are the strengths of quasi-experiments?
Quasi-experiments have higher external validity since they compare naturally occurring groups, providing insights into real-world effects.
47
What are the conditions of the independent variable (IV) in quasi-experiments?
Conditions of the IV can include factors such as young/old, female/male, trained/untrained.
48
What type of data do quasi-experiments collect?
Quasi-experiments collect quantitative data and can be run similarly to 'true' lab experiments.
49
What is the only variable that cannot be controlled by the researcher in a quasi-experiment?
The independent variable (IV) cannot be controlled by the researcher.
50
What is a strength of quasi-experiments regarding external validity?
The lack of manipulation of the IV may result in higher external validity.
51
How can comparing young versus older people on a memory test be beneficial?
It provides insight into the effect of age on recall.
52
What insight can be gained from comparing the ability to identify emotion based on empathy training?
It shows how empathy training might benefit other groups or professions.
53
What design do quasi-experiments follow?
Quasi-experiments follow a true experimental design, allowing for replication with similar demographic participants.
54
What is a limitation of quasi-experiments regarding participant allocation?
Participants cannot be randomly allocated to conditions, leading to participant variables that complicate causality.
55
What issue might arise in a study investigating the effect of age on recall?
A group may include participants with better memory than is representative of their population.
56
Why are quasi-experiments considered less reliable than true experiments?
Due to the inability to control for participant variables and other confounding factors.
57
What does the lack of internal validity in quasi-experiments imply?
There may be other factors that could explain the results.
58
How might the environment of trained teachers affect quasi-experiment results?
Trained teachers may work in schools where emotional intelligence is valued, influencing outcomes.
59
What are the four main types of experiment?
Laboratory, Field, Natural, Quasi
60
What are the three key experimental designs?
Independent groups, Repeated measures, Matched pairs
61
How are variables operationalised and controlled?
Operationalisation, Extraneous vs. Confounding variables, Randomisation, Standardisation
62
What defines a naturalistic observation?
Observing behaviour in real-world settings without manipulation; high ecological validity, low control
63
What is a controlled observation?
Researcher sets up a situation and observes behavior; more control and replicability, lower ecological validity
64
How do covert and overt observations differ?
Covert: participants unaware; Overt: participants aware, affects behaviour
65
What’s the difference between participant and non-participant observation?
Participant: researcher joins group; Non-participant: researcher detached
66
What are questionnaires, and what are their key strengths and limitations?
Written surveys; strengths: cost-effective, large samples; limitations: low response, bias
67
How do structured and unstructured interviews compare?
Structured: fixed questions; Unstructured: open-ended, flexible
68
What is a correlation, and how does it differ from an experiment?
Analysis of relationship between co-variables without manipulation; shows association not causation
69
How is the strength and direction of a correlation expressed?
Correlation coefficient (–1 to +1) and scattergram visualisation
70
What are the main strengths and limitations of correlational studies?
Strengths: large datasets, reliability; Limitations: no causation, third-variable problem
71
What is content analysis?
Systematic coding of qualitative data into quantitative categories; replicable, but risks coder bias
72
What defines a case study?
In-depth investigation of single individual/group; rich data, limited generalisability
73
How do aims differ from hypotheses?
Aim: general purpose; Hypothesis: testable prediction (directional or non-directional)
74
What are the five sampling techniques and their implications?
Random, Systematic, Stratified, Opportunity, Volunteer; trade-off between representativeness and bias/time
75
Why conduct pilot studies?
Small-scale trial to identify issues and refine procedures
76
What ethical issues must researchers address?
Informed consent, confidentiality, withdrawal, protection from harm, debriefing (BPS code)
77
What role does peer review play?
Expert evaluation pre-publication to ensure quality and validity
78
How can psychological research impact the economy?
Informs policy and practice, leading to cost savings and productivity gains
79
How is reliability assessed?
Test-retest and inter-observer checks for consistency
80
What are the key types of validity?
Face, Concurrent, Ecological, Temporal
81
What are nominal, ordinal, and interval levels?
Nominal: categories; Ordinal: ordered ranks; Interval: equal intervals
82
Which measures suit each level of measurement?
Mode: nominal; Median: ordinal/interval; Mean: interval; Range & SD: interval
83
How are quantitative data displayed?
Bar charts, histograms, line graphs, scattergrams, tables
84
How do normal and skewed distributions differ?
Normal: symmetric; Positive skew: right tail; Negative skew: left tail
85
When and how is the sign test used?
Paired nominal data differences; count signs and compare to critical values
86
What are Type I and Type II errors?
Type I: false positive; Type II: false negative
87
Which test for which data/design?
Spearman’s rho/Pearson’s r, Wilcoxon/Mann–Whitney, related/unrelated t-tests, Chi-squared
88
What characterises a scientific approach?
Objectivity, empirical, replicability, falsifiability, theory testing, paradigms
89
What are the standard sections of a psychological report?
Abstract, Introduction, Method, Results, Discussion, References
90
What is the purpose of inferential (statistical) testing in psychology research?
To determine whether observed differences or relationships in data are unlikely to have occurred by chance, allowing researchers to decide if results are statistically significant and meaningful beyond random variation.
91
What does a p-value represent in significance testing?
The probability that the observed results (or more extreme) would occur if the null hypothesis were true; e.g., p < 0.05 means there’s less than a 5% probability that chance alone produced the result.
92
Why might psychologists choose a more stringent significance level, such as p < 0.01?
In situations with high human cost (e.g., drug trials) or when previous findings are contradictory, a lower probability cutoff reduces the risk of false positives by demanding stronger evidence against chance.
93
How do researchers use critical values tables in statistical testing?
After calculating the test statistic (the “observed value”), they consult a critical values table—based on sample size/df, significance level, and tail type—to find the cutoff point; significance is determined by comparing observed and critical values.
94
What three key questions must be answered to select the correct critical value?
1) Is the hypothesis one-tailed or two-tailed? 2) What is the sample size or degrees of freedom? 3) What level of significance (e.g., p < 0.05) is being used?
95
How is the decision rule for significance stated?
The table specifies whether the observed value must be ≥ or ≤ the critical value to reject the null hypothesis (e.g., “calculated rho ≥ critical rho for significance”).
96
What details should be included when reporting a significance test result?
Whether the result is significant or not; the observed value and the critical value; the sample size (N); and the decision regarding the null/alternative hypothesis.
97
What is a Type I error, and when is it more likely?
Rejecting the null hypothesis when it is actually true (a false positive); more likely if the significance level is set too high (e.g., p < 0.10 instead of p < 0.05).
98
What is a Type II error, and when does it occur?
Accepting the null hypothesis when it is false (a false negative); more likely if the significance level is set too low (e.g., p < 0.01 instead of p < 0.05), reducing sensitivity to real effects.
99
How does using p < 0.05 guard against both Type I and Type II errors?
Setting α = 0.05 balances the risks: it is stringent enough to limit false positives while still sensitive enough to detect true effects, minimizing both error types in typical psychological research contexts.
