research methods Flashcards
aim
purpose of study
hypothesis
statement outlining the probable outcome of an investigation
It is hypothesised that the IV (experimental group) will affect (strength/direction) the DV compared with the IV (control group)
independent variable
variable that is manipulated/controlled/changed
dependent variable
the variable that is measured
extraneous variables
variables other than the iv that have unwanted effects on the dv and results
e.g
- individual differences between participants
- differences in experimental settings between groups
- experimenter influences
- practice
controlled variables
variables that are held constant to ensure that the only influence on the dependent variable is the independent variable
confounding variables
unwanted variables that affect the DV and results in an investigation, and it cannot be determined whether the IV or the confounding variable caused the change in the DV.
population
the wider group of people that a study is investigating
sample
the smaller group of people selected from the population who will be participants in the investigation
random sampling
selecting participants from the population in such a way that each member of the population has an equal chance of being selected
+/- of random sampling
strengths:
- a large enough random sample is likely to be representative of the population, improving external validity
limitations:
- small random samples may not be representative of the population, reducing external validity
- it may be difficult, time consuming, impossible or unethical to obtain names of all members of the population
stratified sampling
dividing the population into subgroups, then randomly selecting participants from each subgroup in the proportion that they appear in the population
+/- stratified sampling
strengths:
- a large enough stratified sample is likely to be representative of the population, improving external validity
- important subgroups of a population are ensured fair representation
limitations:
- it may be difficult, impossible or unethical to obtain names of all members of the population
- it is more time-consuming than using a random sampling technique because of the need to form subgroups and any pre-testing required
investigation methodology
type of research study
controlled experiment
investigation methodology that aims to test the effects of the IV on the DV with all other variables controlled
+/- controlled experiment
strengths:
- controlled experiments can identify a cause-and-effect relationship between an IV and a DV
- results may be generalised to the population of interest if the study is deemed to have good validity
- controlled experiments can be repeated to gather more data and test the reproducibility and repeatability of results
limitations:
- controlled experiments require strictly controlled conditions, which may be difficult to maintain, so results may be influenced by extraneous variables
- participant behaviour may be influenced by the artificial nature of the setting
- it may be unethical or impossible to conduct a controlled experiment on a particular variable
- external validity may be low if the conditions are too artificial to extrapolate results to the population of interest outside the experiment
random allocation
involves dividing the sample into groups in such a way that each participant has an equal chance of being placed into the experimental group or the control group
investigation design
involve different ways that participants experience the experimental and control conditions
between subjects design
participants are randomly allocated to either the control or experimental condition
+/- between subjects design
strengths:
- a between-subjects design is the most time efficient design because both groups can be tested at the same time and no pre-testing is required
- It has a lower rate of participant withdrawal than a within-subjects design because participants only complete one condition.
- There is better control of participant knowledge of the study and there is no effect of prior participation extraneous variables influencing results compared with a within-subjects design.
limitations:
- More participants are needed in a between-subjects design than a within-subjects design.
- There is less control over the extraneous variable of participant variables between groups, which may influence results in an unwanted way, lowering validity.
within-subjects design
all participants in the sample complete both the experimental and control conditions
+/- within subject design
strengths:
- In a within subjects design, there is no extraneous variable of participant variables between groups, improving validity.
- Fewer participants are needed than in a between subjects design.
limitations:
- There is less control over participant knowledge of the study. The extraneous variable of prior participation in the first condition may influence their behaviour while completing the second condition.
It is more time-consuming than a between-subjects design because both conditions cannot be tested at the same time.
- There is a higher rate of participant withdrawal from the study than in a between-subjects design because the DV has to be measured multiple times.
mixed design
combination of a between-subjects design and a within-subjects design
For example, in an investigation testing whether male or female students benefit from listening to classical music or pop music while studying for a test, the between subjects element is whether the student is male or female, and the within subjects element is listening first to classical music and then to pop music while studying.
+/- mixed
strengths:
- Differences in participant variables between groups are controlled in the within-subjects design element.
- Can test the effect of multiple independent variables on a dependent variable in one investigation.
- Testing multiple independent variables in one investigation can be time and cost-effective compared to completing two or more separate investigations
limitations:
- There is a higher rate of participant withdrawal from the study than using a between-subjects design alone, which can be detrimental to the internal validity.
- There is less control over participant knowledge of the study. Prior participation in the first condition may influence their behaviour while completing the second condition, than when using a between subjects design alone.
- There is less control over differences in participant variables between groups in the between subjects element, which may influence results in an unwanted way, lowering validity.
case study
Investigation of a particular activity, behaviour, event or problem that contains a real or hypothetical situation and includes real-world complexities.
+/- case study
strengths:
- Case studies are useful when a limited number of participants are available.
- They can be used to study experiences where it would be unethical or impossible to design and conduct a controlled experiment.
- They can provide rich qualitative data.
- They can act as a basis for further research.
Limitations:
- One person or a small group of people cannot be representative of a population, so results from a case study cannot be generalised to the population, and there is a low external validity.
- Researcher bias may influence the recording, collation and treatment of data.
- They may not be repeatable to gain more data or to test reliability of results.
- They are typically time consuming.
classification and identification
involves two distinct components. Classification in research involves arranging phenomena, objects or events into manageable sets.
Identification involves recognising phenomena as belonging to a particular set or being part of a new or unique set.
+/- classification and identification
strengths:
- Classifications can allow for a narrowed focus of research.
- People identified as having a similar classification can feel a sense of belonging and support.
- Using classifications can allow for efficient processing of large amounts of information.
- Classifications can help make predictions and inferences.
limitations:
- Labelling through identification can lead to stereotyping, prejudice or discrimination.
- Classifications may be based on subjective criteria.
- Large amounts of information are required to create classifications.
correlational study
involves planned observation and recording of events and behaviours that have not been manipulated or controlled in order to:
- understand the relationships or associations existing between variables
- identify which factors may be of greater importance
- make predictions.
+/- correlational study
strengths:
- The direction and strength of a relationship between variables can be determined using a correlational study.
- They can be used to gather initial information that is investigated further or to research behaviours where controlled experiments cannot be used for practical or ethical reasons.
- Observation of real-life behaviours with no manipulation of variables may result in behaviours that are more natural.
- Secondary data can be used.
- If a relationship between two variables is determined, the value of one variable can then be used to predict the value of the other variable.
- They can be used to determine the repeatability, reproducibility and validity of measurements, and they are often high in external validity.
- Extra procedures to control for extraneous variables are not needed.
limitations:
- Correlation does not equal or imply causation, so even if a strong relationship is determined, you cannot assume that one variable causes a change in the other.
- The relationship is bi-directional, and you cannot determine which variable has more influence.
- A large amount of data is required.
- As extraneous variables are not controlled for, you cannot determine that there was not an influence of a third variable, meaning there is a low internal validity.
fieldwork
involves collecting information by observing and interacting with a selected environment
- direct observations and sampling
- participant observation
- interviews, questionnaires, focus groups and yarning circles
+/- field work
strengths:
- Information on sensitive topics can be obtained using fieldwork.
- A large amount of quantitative data can be gathered in a questionnaire in less time than for a controlled experiment.
- Participant anonymity in questionnaires can reduce dishonest or biased answers.
- Rich qualitative responses can be obtained in the participant’s own words.
- Natural settings are more likely to show behaviour that reflects real life.
- If participants are unaware that they are being studied, there is no change in their behaviour due to their belief of how they are expected to behave.
- Fieldwork can be used when it would be impossible or unethical to investigate by controlled experimental methods.
- Fieldwork can help to gain insight into existing data or behaviours that were not expected.
limitations:
- Observed behaviour is subjective and open to interpretation and bias by the researcher.
- Fieldwork is prone to social desirability bias, whereby participants respond in a way that they think they should respond, particularly if the researcher is present.
- In questionnaires, interviews, focus groups and yarning circles, participant responses may be inaccurate because of dishonesty, memory issues, difficulty communicating, language abilities or misunderstanding the question.
- Qualitative data can be difficult to summarise.
- Interviews, focus groups and yarning circles can be time-consuming.
- There is minimal control over extraneous variables and results may not be replicable.
- There are ethical concerns with the lack of informed consent in some cases.
literature review
involves collating and analysing secondary data findings and/or viewpoints.
+/- literature review
- A literature review can determine what is already known and whether there is a solid foundation of knowledge, based on multiple sources.
- They help introduce existing understanding and context for primary research.
- They can identify expert researchers in the field.
- They identify gaps in current understanding and areas for future research.
- They identify methodologies that have been successful or not successful at generating significant findings.
limitations:
- Key studies may be missed if the search criteria or focus of a review is too narrow, resulting in a review that lacks depth.
- A selection bias in the chosen studies may result in the review being unrepresentative of current understanding or provide unbalanced conclusions.
- A literature review may not comment on the validity of the original research or how the studies were selected, resulting in the reader being unable to determine the quality of each study within the review, or the review as a whole.
- Literature reviews may describe multiple studies but lack a deeper analysis of the individual studies.
- Only secondary data is acquired.
modelling and simulation
modelling involves constructing and/or manipulating a physical or conceptual model of a system. Once a model is made, a simulation uses the model to replicate and study the behaviour of a real or theoretical system.
+/- modelling and simulation
strengths:
- Modelling can allow unobservable events to be visualised.
- Once established, a computer simulation can run quickly with multiple trials in a short amount of time, including events that would usually be long-running.
- Modelling and simulation can be used to safely study new devices, therapies or treatments that would be too dangerous or unethical or logistically impossible to conduct in controlled experiments.
- Simulations can allow us to predict future events and ‘what if’ situations.
Modelling and simulations can test a product before it is created.
limitations:
- A large amount of valid source data may be needed in the creation of a model.
- Computer simulations require precise, consistent statistical analysis in order to function accurately as a valid, repeatable and replicable measure.
- A psychological theory may be well understood but difficult to apply as a working model.
- Simulations are not the real thing and people may respond differently in real life, so simulations involve assumptions about behaviour that lower external validity because of artificiality.
- Complex models and simulations may be expensive.
product, process and system development
involves the design of a product, a process or a system to meet a human need. These may involve technological applications in addition to scientific knowledge and procedures.
integrity
the commitment to searching for knowledge and understanding and the honest reporting of all sources of information and results.
justice
involves the moral obligation to ensure that competing claims are considered fairly, that there is no unfair burden on a particular group from an action, and that there is fair distribution and access to the benefits of an action.
beneficence
the commitment to maximising benefits and minimising the risks and harms
non-malificence
means to avoid causing harm
respect
involves considering the value of living things, giving due regard, and considering the capacity of living things to make their own decisions
confidentiality
means ensuring that the participants remain anonymous, and their personal information is kept private, protected and secure throughout the study.
voluntary participation
ensures that each participant freely agrees to participate in a study, with no pressure or coercion.
informed consent procedures
are conducted before a study begins, where participants agree to participate in the research after they have received all the details of the investigation including the nature and purpose, methods of data collection and potential risks
withdrawal rights
ensure that participants are free to discontinue their involvement in a study without receiving a penalty.
deception in research
involves withholding the true nature of the study from participants if their knowledge of the true purpose may affect their behaviour and the subsequent validity of the investigation.
debriefing
is conducted at the end of the study and is when participants are informed of the true aims, results and conclusions of the study
primary data
collected through first-hand experience for an intended purpose; for example, a researcher using a questionnaire to conduct their own study.
secondary data
obtained second hand through research conducted or data collected by another person for another purpose
qualitative data
describes characteristics and qualities. Qualitative data can be in the form of words, photographs, videos, audio and other recordings that are not measured with a number.
quantitative data
involves measurable values and quantities and can be compared on a numerical scale. Quantitative data can be in the form of measurements such as length, weight or time, or in the form of frequencies and tallies.
percentage change
calculation of the degree of change in a value over time. It allows you to compare an old value and a new value, and to see how the value has increased or decreased.
mean
average value of a set of data
- adding all values and dividing by the number of values in the data set
median
middle value in an ordered set of data. It is the value that splits the set of data in half.
mode
the value that occurs most frequently within a set of data.
standard deviation
hows the spread of the data around the mean. It shows how close each data value lies to the average, or how far spread out they are – in other words, how much the values vary.
true value
the value, or range of values, that would be found if the quantity could be measured perfectly.
accuracy
how close a measurement is to the true value of the quantity being measured.
precision
refers to how close a set of measurement values are to each other
repeatability
how close successive measurements of the same quantity are when carried out under the same conditions.
reproducibility
how close measurements of the same quantity are when carried out under different conditions
replicability
applied to studies aiming to answer the same scientific question, each with its own methods and data
validity
whether a measurement measures what it is supposed to be measuring.
internal validity
refers to a study investigating what it sets out or claims to investigate. Internal validity can be affected by the appropriateness of the investigation design, sampling and allocation techniques, and the effect of extraneous and confounding variables.
external validity
refers to whether the results of the research can be applied to similar individuals in a different setting. For example, an intelligence test might determine the intelligence of a white, middle-class person with reasonable accuracy, but if the test does not consider cultural diversity, then it is biased and it cannot be used to accurately describe the intelligence of people from the wider, diverse population.
personal errors
include mistakes, miscalculations and observer errors made when conducting research
measurement error
the difference between the measured value and the true value of what is being measured
systematic error
affect the accuracy of a measurement by causing readings to differ from the true value by a consistent amount or by the same proportion each time a measurement is made
random error
affect the precision of a measurement by creating unpredictable variations in the measurement process; they result in a spread of readings
uncertainty
lack of exact knowledge of the value being measured.
outliers
values that lie a long way from other results
