Resarch Methods Flashcards
What is an aim
An aim is a statement of a study’s purpose
What is a one tailed hypothesis
Also known as directional
States the direction of the differences or relationship
E.g.
People who drink red bull become more hyperactive than people who do not
What is a two tailed hypothesis
Sometimes known as non directional
States there is a difference between conditions or groups but not the nature of the difference
E.g. there is a difference between boys and girls
What is a Null hypothesis
Is what your going to assume is true during the study
E.g. there is no difference between eating behaviour and early exposure to media
What is bar chart
- used o display discrete data
- mean or frequency is on the y axis
- different from histogram as bars do not touch and do not differ in width
What is a histogram
- used to represent data on a continuous scale
- columns touch because each makes an individual score on the scale
- scores are placed on the x axis
- the height of the column shows the frequency of values
What is correlation analysis and the advantages and disadvantages of it
It is looking at relationships
+ can be used when carrying out a controlled experiment
+ gives ideas for future research
- can’t be established as cause and effect
- care mus be taken when interpreting correlation coefficients
What is a correlation coefficient
Number between 0 and 1 tells us how strong the correlation is. The closer to 1 the stronger the correlation. It has a plus or minus which shows us whether the relationship is positive or negative
- it is not possible to establish cause and effect off of the core ablation relationship.
- just because the have a strong correlation does not mean they are linked. You have just found a strong association
What is a scatter graph
Three types of correlation can be shown
- positive
- negative
- no correlation
- used for measuring the relationship between two variables
- data from one variable is presented on x and the other on y
Distributions
A normal distribution
- is symmetrical about the mean. The symmetry means the mean, median and mode are all the same
Negatively skewed
- more scores are at the higher end f the data set
- the tail is on the left side of the peak
- the mode is more than the median, the median is more than the mean
Positively skewed
- a cluster of scores at the lower end of the data set
- the curve has the tail on the right side of the peak
- the mode is less than the median . The median is less than the mean
What are the different types of variables
Independent variable: the variable that is changed
Dependant variable: the variable that is measured
Control: the variable that hat remains the same
What is meant by the term operationalisation
How a variable is clearly defined by the researcher
Can be applied to the IV and DV
What are the different types of control variables
Random allocation - means everyone has an equals chance of doing either condition e.g. picking names out of a hat
Counterbalancing - mixing up the order of tasks. Can solve order effects in repeated measures designs
Randomisation - when material is resented to the participants in a random order
Standardisation - standardised instructions should ensure experimenters act in a similar way with all participants
Types of validity
Validity - refers to how well a test measures what it claims to. For example an IQ test with only maths questions is not measuring IQ
Ecological validity - the stent to which the test reflect real life
Temporal validity - the stent to which the test provides results that can be generalised across time
Face validity - the extent which the test looks, to the participants, like it will measure what it is supposed to measure
Population validity -
What is reliability
Refer to how consistent or dependable a test is. A reliable test carried out in the same circumstances on the same participants should always give the same results
What are the British Psychological Society Code of Ethics and what does it involve
Th consideration of hat is acceptable or right behaviour in the pursuit or scientific goal
Informed consent - knowing aims and giving your permission to o take part in the study (Menges 1973)
Deception - deliberately misleading or withholding information if there is strong scientific justification
Right to withdraw - being able to leave when desired
Confidentiality - details should be kept private
Protection from harm - Booker harm than is daily life
Debrief - returning to the participant to the state they were before the research
Experimental design - independent groups
Each participant only takes part in one condition
+ no order effects as they only take part in one
+ 1 condition, so don’t get bored or practiced
- more participants are needed
- individual differences as the people talking part in each condition are different - one group might just be better
Experimental design - repeated measures
All participants do all of the conditions
+ no individual differences as the same person does all the conditions
- order effects- either boredom or practice
- demand characteristics - participants know what the experimenters are looking for
Experimental designers - Matched pairs
Involves the use of independent measures but each participant in group A is matched with one in group b based on key characteristics
+ no order effects
+ controls for individual differences can be more sure the IV causes differences in the DV rather than the differences between the groups
- can be difficult to make perfect matches
- is costly on money and time
Field Experiment
Conducted outside of the lab. Behaviour is measured outside the lab in a natural environment
+casual relationship
+ good ecological validity - less artificial
+ demand characteristics are less
- less control over confounding variables
Laboratory experiment
When variables are controlled within a lab. Conducted in an artificial setting
+ can control confounding variables easier
+ easier to replicate as controls are very strict
- artificial
- demand characteristics are high
- deception is often used so not very ethical
Demand characteristics
- What are they?
- How can they be controlled?
- What is meant by a double/single blind
- A cue from the researcher or the situation that may reveal to the participants the purpose of the research and will therefore do what they think you want them to do
- Deception, not have the researcher in the room and the demographic of the researcher
- Double blind - neither the participants or the researchers are aware of the aims of the investigation
Single blind - participants are not aware of the condition you are in, attempts to control the confounding effects of demand characteristics
Natural experiment
Where the researcher looks at how an independent variable which isn’t manipulated by the experiment
+
Quasi experiment
The IV is a naturally existing characteristic between people and has not been changed by anyone or anything e.g. gender, skin colour
+ often carried out under controlled conditions
+ ecological validity - the research is often less artificial than cab studies
- participant allocations - you can’t randomly allocate participants
- casual relationships can be hard to establish
Controlled observation
When the researcher has some measure of control over the environment
Naturalistic observation
Studying behaviour in a natural setting where everything has been left as it is normally
Overt observation
The participants are aware they are being observed
+ they are much more ethically sound than other methods because the participants are aware of the research
- demand characteristics - people might change their behaviour if they know they are being observed
Participant observations
The observer acts as a part of the group being watched
+ insight
+ increased validity
+ experience the situation
- lose objectivity
- difficult to record information accurately
Non participant observation
The experimenter does not become part of the group being observed
\+ more ethical \+ more objective -less insight - not experiencing the same things - lower in validity
Structured, unstructured and semi structured interview
Structured - pre determined set of questions that are usually asked in a fixed order
+ easy to replicate
- cannot deviate topics, cannot elaborate on points
Unstructured - no set questions - general aims are discusssed and interaction is free flowing. Interviewees are encouraged to elaborate on points
+ flexibility
+ can ask follow up questions
+ can elaborate on responses
- analysis of data is time consuming
- irrelevant information
- social desirability
Semi - for example a job interview - there are a set list of questions but eh interviewer can also also follow up questions
What is inter rated reliability
Checking with an observer to check your consistency in the themes you have found in your research
Investigator effects
- What are they
- How to avoid them
- Any effect of the investigators behaviour (conscious or unconscious)on the research outcome.
- One way mirrors/ not being in the room. Getting an assistant to carry out the interviews/ research/ experiment
What is content analysis
Pos and negs
- qualitative data
- data is analysed as typologies, quotations and summaries
- hypothesis are grounded in data
+ a clear summary of the patterns in the data may be established
+ once coding system has been set up replication is easy
- can be subjective
- reducing the data coding units removes detail
Advantage and disadvantage of mean
Mean - by adding up all of the items and dividing by the numbers of data
+ very sensitive stat as it takes into account the exact distance between values.
+ representative of all data
- if the values are abnormal it will affect the data greatly and distort it
- therefore can misrepresent data
Pilot study
A small scale version of an investigation that takes place before the real investigation is conducted. The aim os to check the procedures
Self repot questionnaires
Design: open and closed
Open - does not have a fixed range of answers a participant can choose
Closed - fixed number of responses free to answer in their own way
+ cost effective, can gather large amounts of data, large samples, easy to distribute
- can lie, qualitative data is hard to analyse, response is bias, demand characteristics
What is social desirability
What someone will answer because that’s what they think they should answer