Research Methods Flashcards
Independent variable
The variable which the reserscher manipulates in order to determkne its effect on the dependent variable
Experimental conditions
conditions of an experiment that exposes participants to the treatment, that is, to one version of the independent variable
Control condition
To provide a standard against which experimental conditions can be compared
Dependent variable
The variable being measured
Extraneous variables
These are any other than the independent variable which could have an affect on the dependent variable
Confounding variables
These are any variables other than the independent variable that have affected the dependent variable
Operationalisation
Defining variables and stating how they will be measured
Lab experiment
Carrying out experiment under controlled environment, which a,lows the researcher to exert a high level of control over the indecent variable and eliminate any extraneous variables, the researcher is also able to observe and manipulate the change in the dependent variable caused by their manipulation of the independent variable
Field experiment
Experiments carried out in the real world or in a natural setting rather than in an artificial setting of a lab. The independent variable is still manipulated or controlled by the researcher to see the effect on the dependent variable e.g. observing people in the street
Natural experiment
The researcher takes advantage of a naturally occurring independent variable to see its effect on the dependent variable, a natural experiment is a study that measures variables that aren’t directly manipulated by the experimenter e.g. comparing behaviours in single sex and mixed schools, this means that the independent variable in naturally occurring. The researcher is finding participants who already meet the conditions of the experiment rather than allocating participants to conditions themselves
Quasi-experiment
They contain a naturally occurring independent variable, however, the naturally occurring independent variable is a difference between people that already exists e.g. gender, age. Usually take place in lab settings
Observations
When a researcher watches or listens to participants engaging in the behaviour which is being studied
Nonparticipant observation
When the research does not get directly involved with the interactions of the participants and does not take part in the activities e..g observing people in the gym the psychologist stands around and doesn’t get involved in any of the exercises
Participant observation
When the research is directly involved with the interactions of the participants and will engage in the activities that are being done by the participants e..g observing participants at the gym the psychologist actually engages in the exercise and uses the gym equipment
Covert observation
The psychologist goes undercover and does not reveal their true identity, they may even give themself a new identity. The group doesn’t know that they are being watched e.g. the psychologist introduces themself as Bob (fake name) and doesn’t tell people at the gym that he is really a psychologist trying to observer their behaviour
Overt observation
The psychologist reveals their true identity and tells the participants they they are being observed, this might lead to observer effects since participants might change their behaviour if they know they are being watched, leading to invalid results
Naturalistic observation
A reward gear observes the participants in their own natural environment and there is no deliberate manipulation of the independent variable
Controlled observations
A researcher observes participants in a controlled environment and this allows for the manipulation of the independent variable
Observer bias
If the observer knows the purpose of the study then they may observe behaviours that they think meet their aims and hypothesis, which can have an influence on how they record the data from the study which is innacurate and subjective
How can you overcome observer bias?
Inter-rater reliability: correlate and if the Kappa score is of +0.8 then the data gathered is reliable
Behavioural categories
Specific behaviour categories which are being looked for in the observation
Event sampling
The observer decides in advance the types of behaviour they are interested in and record all the occurrences of this behaviour
Time-interval sampling
Observer decides in advance that the observation will take place only during specified time periods
Self report techniques
Research methods in which participants give information about themselves without researcher interference
Structured interviews
All participants are asked the same questions in the same order, this produces quantitative data, usually consisting of closed questions that have restricted answers
Unstructured interview
An informal in depth conversational exchange between the interviewer and participant, the questions are not preplanned, and the data produced is qualitative, usually consists of open end questions
Semi structured interview
It is a mixture of a structured and unstructured interview producing both qualitative and quantitative data
Questionnaires
Participants are given a written set of questions and instructions about how to record their answers, questionnaires can be self-administered, delivered by post, internet or face to face
Correlation
A technique for analysing the strength of the relationship between two quantitative variables known as co-variables
Strength of correlations
It can be between -1 and +1, a strong positive correlation would be +1.
Correlation coefficient
Strength of the correlation
Advantages of correlations
-establish the strength of the relationship between two variables and measure it precisely
-investigate the relationship between two variables which couldn’t have been otherwise due to ethical reasons
Disadvantages of correlations
-correlations can only measure linear relationships and not curvilinear ( linear positive to a point after which it becomes negative)
-can not demonstrate cause and effect
-even if there is a correlation this doesn’t ensure that the variables are actually related as there might be third variable
Aims
A precise statement about the purpose of the study and what it intends to find out, it should include what is being studied and what the study is trying to achieve
Hypothesis
A precise, testable statement about the expected outcome of an investigation
When conducting a research what are the three steps
- Aim
- Operationalisation of the independent and dependent variables
- Hypothesis
Non directional- two tailed hypothesis
Does not state the direction of the predicted differences between the conditions (e.g. eating chocolate will significantly affect a person mood)
Directional hypothesis, one tailed
States the direction of the predicted difference between the conditions (e.g. eating chocolate will increase a persons mood)
Target population
Describes the group who researchers are studying and want to generalise their results to
Sample
Should be representing of the population which it is drawn and should therefore have the same characteristics as the population
Random sampling
When every member of the population has the same chance of being selected, easiest method is to place all names from the target population in a hat
Systematic sampling
Sampling strategy where participants are selected by taking every Nth person from a list
Stratified sampling
Classifying the population into categories and then randomly choosing a sample which consists of participants from each category in the same proportion as they are in the population
Opportunity sampling
Selecting participants who are readily available and willing to take part also known as convenience sampling
Volunteer sampling
People volunteering to take part in a study
Pilot study
Initial run through of the procedure to be used in an investigation, it involves selecting a few people and trying out the study on them, it is possible to save time and money by identifying any flaws in the procedures designed by the researcher
Floor and roof effect
Floor- when participants aren’t able to score
Roof- when all participants score too high
Experimental designs
How the participants in a study are organised within the experiment
3 types of experimental designs
Independent groups, repeated measures and matched pairs
Controls
Randomisation, standardisation, random allocation
Independent group designs
Different participants are used in each of the conditions
Advantages of independent group designs
-no order effects
-less demand characteristics
Disadvantages of independent group design
-more participants needed
-chance of results being due to individual differences rather than manipulation of the independent variable
Repeated measures design
Each participants is tested in all conditions of the experiment
Advantages of repeated measures design
-no individual differences rather than
-half as many participants are needed
Disadvantages of repeated measures design
-order effects
-demand characteristics
Matched pairs design
Different participants are used in all of the conditions, just as with the independent groups design, however participants in the two groups are matched based on characteristics
Advantages of matched pairs design
-less chances of order effects
-individual differences less likely to occur
Disadvantages of matched pairs design
-time consuming
-hard to find a large number of similar participants
Reliability
Consistency of a research study especially when a study is repeated again and the same results are gained from both occasions
External reliability
Test-retest method: conduct a study once and then conducted again in the future, if the results are similar than the study can be said to be reliable
Internal reliability
Whether a test and the results gained are consistent within itself.
Split half technique
Validity
The study is measuring what it intends to measure when referring to the aims of the study
External validity
The extent to which the finding from a study can be generalised to the other settings
Internal validity
When the outcome of the study is the direct result of the manipulation of the independent variable upon the dependent variable and hasn’t been affected by any extraneous variables
Participant variables
Characterises of the participants which may affect the dependent variable
Situational variables
Factors in the environment which might affect the dependent variable
Experimenter variables
Factors to do with the experiment which might affect the dependent variable
Types of data
Nominal,ordinal, interval
Meta analysis
Combining of results from several studies on a particular topic to provide an overall view, it can have publication bias (the research may choose to leave out studies with negative or non significant results)
Mean
The mean is the most accurate measure and it takes into account all the score
However it can be distorted by a single extreme value
Median
Unaffected by extreme score, the median can be unrepresentative of the data if the scores are cluster around high and low levels
Mode
Unaffected by extreme values, but it tells us nothing about the other scores in the data set
Range
Quick and easy to calculate, but can be easily distorted by extreme values
Standard deviation
Slightly challenging and time consuming to work out, but it is representative of the data set as it takes in all the scores
Inferential statistics
If we find a sample of which than we can use to generalise/ infer about the larger population
Lebel of statistical significance
The level at which the decision is made to reject the null hypothesis in favour of the experimental hypothesis, it states how sure we can be that the indecent variable is having an affect on the dependent variable and this is not due to chance
Chance
Something has no real cause, it just happens,
Why use sign test
Difference between data
Paired or related (repeated or matched pairs design)
Nominal data
Content analysis
Systematic research technique for analysing data such as documents or texts, the data might be too large to analyse initially, so the researchers creates a coding system of predetermined categories that can be applied to the content . Generates quantitative data
Coding
Counting the number of times a word/phrase/behaviour appears in a source
Thematic analysis
This method is used quite often for analysing qualitative data.
This form of analysis involves the scientist looking over their data to familiarise themselves.
This allows them to establish the key themes within the data - themes they can define and name.
From there, they can write a report.
Concurrent validity
A way of establishing interval validity of a new test by comparing to the scores of a olde more established test, a positive correlation of +0.8
Face validity
A way to measure whether the test or instrument is measuring what it intends to (like a look over the test again)
Psychology is a science when
High element of control is shown
Confounding variables have been identified
Large samples have been used
Key words are operationalised
Empirical method
A method of gaining knowledge which relies on direct observation. This can help separate unfounded beliefs from. The truth
Paradigm
Shared set of assumptions and agreed methods that are found within a scientific disciplines
Paradigm shift
Result of a scientific revolution, a significant change in the dominant unifying theory of a scientific discipline occurs and causes a paradigm shift
Objectivity
Dealing with facts in a way that is unaffected by beliefs, opinions, feelings or expectations
Replicability
Extent n to which the findings of a research can be repeated in different contexts or circumstances
Falsifiability
The notion that scientific theories can potentially be disproved by evidence, it is the hallmark of a science. It refers to proving hypothesis wrong
Deductive reasoning to theory construction
-first have a theory
-then devise hypothesis
-then test this theory using empirical methods
-once tested conclusions are drawn
Inductive reasoning
-observation of a natural phenomenon
-then hypothesis
-then test hypothesis
-lastly drawn a conclusion
-from the conclusion a theory is generated about the topic being investigated
