research methods yr12 & yr13 Flashcards
What is an independent variable (IV)?
The variable that is manipulated by the researcher in order to test its effect on the depend variable
What is a dependent variable (DV)?
The variable that is measured by the researcher and influenced by the independent variables
What is an extraneous variable (EV)?
All of the variables, which are not the IV, but could affect the results (DV) of the experiment
What is a confounding variable?
Something that directly effects the DV
Define what is meant by an aim
A statement of what a researcher is trying to find out in a study
Define what is meant by a hypothesis
An operationalised, testable statement about the relationship between the IV and DV
A hypothesis should always have..?
- An explanation of what you expect to happen
- Be clear and understandable
- Be testable
- Be measurable
- Contain both IV and DV
What is a directional/one-tailed hypothesis?
Is a precise prediction where a positive or negative change/difference is established
What is a non-directional/two-tailed hypothesis?
A precise prediction that establishes there will be a change/difference but doesn’t state whether it is positive or negative
What is a quasi-experiment?
Strengths and Limitations
Is when the IV occurs naturally and isn’t created by anyone, the DV may be measured in a lab.
Strengths:
- High degree of control
- Easily replicated
Limitations:
- Participants may be aware the are being studied and perform demand characteristics
- Causality cannot be established
What is a laboratory experiment?
Strengths and Limitations
Is when an experiment is conducted under extremely controlled conditions and uses a standardised procedure
Strengths:
- High degree of control
- Easily replicated
- Causality
Limitation:
- Participants may be aware they are being studied and perform demand characteristics
What is a field experiment?
Strengths and Limitations
An experiment that is conducted in a real-life setting - reducing control over extraneous variables but improving ecological validity
Strengths:
- High ecological validity
- Reduction of demand characteristics
Limitations:
- Less control over IV, DV and EV
- Replication is difficult
- Sample bias (aren’t randomly chosen)
What is a natural experiment?
Strengths and Limitations
An experiment where the IV already exists but it can be measured in its natural environment
Strengths:
- High ecological validity
- Reduced demand characteristics
- Lack of direct intervention from researcher
Limitations:
- Less control over IV, DV and EV
- Replication is difficult
- Sample bias (aren’t randomly chosen)
What are the 6 main ethical issues?
- Protection from harm
- Confidentiality
- Privacy
- Deception
- Right to withdraw
- informed consent
What is the target population?
The total group of individuals from which the sample might be drawn
What is opportunity sampling?
Consists of selecting anyone who is available and willing to take part in the study
What is random sampling?
Every member of the target population has an equal chance of being selected - process is random
What is volunteer sampling?
Participants become part of a study by self-selecting in response to some sort of advert
What is stratified sampling?
Subgroups are identified within a population (male/female) and participants are then selected from each strata in proportion to the occurrence with the wider population
What is systematic sampling?
A predetermined system is used to select participants (using an nth term system for example)
What is independent measures?
Where different participants are used in each condition of the experiment
What is repeated measures?
The same participants take part in both conditions of the experiment
What is matched pairs?
Pairs of participants are matched in terms of key variables (age, gender, height, etc). And then one member is each placed in the two different conditions
What are the 3 order effects?
- Boredom (performance decreases)
- Fatigue (performance decreases)
- Practice effect (performance increases)
What is counterbalancing?
A way of combatting order effects.
Example:
- Group A will do the experiment, doing condition 1 and then 2
- Group B will do the experiment, doing condition 2 and then 1
What is an open question?
Example: “How do you feel when stressed?”
These questions allow respondents to explain their answer in as little or as much as they like
What is a closed question?
Example: “How many hours of sleep do you get a week? (A) 0 hours. (B) 1-20 hours. (C) 20+”
These questions don’t allow respondents to give in depth answers
What is a Likert scale?
Example: “Work is stressful. (A) strongly agree. (B) agree. (C) N/A. (D) disagree. (E) strongly disagree
These questions give a degree on how a person feels but someone may answer as they feel they should (demand characteristics) or may not know how to answer so answer however
What are forced choice questions?
Example: “(A) worst social sin is to be rude. (B) worst social sin is to be a bore”
These questions make you choose when you may not agree with either answer, giving wrong data
What is social desirability bias?
Is a distortion in the way that participants answer questions - they answer in a way that best portrays them
What is a structured interview?
- Preset questions
- Done remotely (phone/chat line) or face-to-face
-Done in real time
What is a semi-structured interview?
- May start with preset questions but others will be added throughout
- May have an aim but directed by the answers given at the time
What is an unstructured interview?
- Conversational and free-flowing
- Direction of the interview is determined by the information gained at the time
- Sometime called the clinical interview
What is large standard deviation?
When there is a lot of variation around the mean
What is small standard deviation?
When all the data is closely clustered around the mean
What is zero standard deviation?
When all the data is the same
What is nominal data?
Categories - male or female
What is ordinal data?
Order without equal measures - race positions
What is interval data?
Uses units of equal intervals - temp
What is ratio data?
Has a true zero point - height, weight, time, distance
What is another way to describe a correlation?
Relationship
What is quantitative data?
Numbers: which gives you easier, more precise answers/data but may lack some key parts as answers are closed
What is qualitative data?
Non-numerical: data which is much harder to interpret but gives you more in depth answers
What is an ethical implication?
The wider impact/consequence of findings from research on a wider group of people (people that didn’t take part in the study)
What is social sensitivity research (SSR) and who is linked to it?
Sieber and Stanley: describes studies where there are potential social consequences for the participants or the group of people represented by the research
What are the 4 guidelines that Sieber and Stanley proposed?
- The Research Question: the research must consider their question carefully. Asking questions like “Are there racial differences in IQ?” may be damaging to a member of a particular group
- The Methodology Used: the researcher needs to consider the treatment of the participants and their right to confidentiality and anonymity. For example, if someone admits to committing a crime, should the researcher maintain confidentiality?
- The Institutional Context: the researcher should be mindful of how the data is going to be used and consider who is funding the research. If the research us funded by a private institution or organisation, why are they funding and how to they intend to use the findings?
- Interpretation & Application of Findings: finally, the researcher needs to consider how their findings might be interpreted and applied to the real-world. Could their data/results be used to inform policy?
What are the 10 issues relating to SSR identified by Sieber and Stanley?
- Informed consent
- Deception
- Privacy
- Confidentiality (Data Protection Act)
- Withdrawal from investigation
- Risk/benefit ratio
- Valid methodology
- Equitable treatment
- Ownership of data
- Values
What is content analysis?
The study of materials rather than people directly i.e. books, adverts, tweets, Instagram, ,media…
Looks at what messages are being portrayed. The aim? To systematically summarise communications and the drawing of conclusions
What are the stages of content analysis?
- Look at the content and get familiar with it
- Establish some behavioural categories (coding units) you are searching for
- Decide what data it is, either qualitative or quantitative
- Quantitative - counts the amount if times your category presents itself. OR. Qualitative - list the words describing your category which are commonly used (thematic analysis)
- Draw conclusion based on your findings
What is thematic analysis?
Strengths and Limitations
Is the type of content analysis used when analysing qualitative data. After observing the content data, it’s ordered into reoccurring themes.
Strengths:
- Ecological validity
- Reliability
- Methodology
Limitations:
- Biased due to subjectivity
- Causality
What does reliability mean?
Consistency
What is internal reliability?
When a test is consistent within itself. E.g. a set of scales should measure the same weight between 50g -100g as it does between 150g - 200g
What is external reliability?
If you test a participant more than once then their results should remain the same. And if a test measures consistent over time
What is the split-half method?
Measures the extent to which all parts of the test contribute equally to what is being measured. This is done by comparing one half of the test with the results from the other half. If the two halves of the test provide similar results this would suggest that the test has internal reliability
What is test-retest reliability?
A method that assesses the external consistency of a test. It measures the stability of a test over time. Involves the same participants taking the same test on different occasions and getting the same/similar results to show external reliability is established
How to improve reliability?
- Training observers in the observation techniques being used and making sure everyone agrees on them
- Ensuring behaviour categories have been operationalised (meaning they have been objectively defined) this improves inter-rater/observer reliability
What is validity?
Accuracy
What is internal validity?
Refers to whether the design and conduct of a study are able to support that a casual relationship exists between the independent and dependent variables
What is external validity?
Refers to the extent to which the results of a research study can be applied or generalised to another context - real world application
What is temporal validity?
Refers to the extent to which the findings and conclusions of the study are valid we consider the differences and progressions that come with time
What is population validity?
Refers to whether the findings from a sample can be reasonably generalised to a larger group of people (the population)
What is ecological validity?
Is the measure of how test performance predicts behaviours in real-world settings
What is mundane realism?
Is a measure of external validity, or the extent to which experimental findings can be generalised to the real world
How to improve validity?
- Experimental research, control groups, standardised procedures, single-double-blind procedures
- Questionnaires, lie scale (checks consistency by re-asking in different formats), promise anonymity
-Observations, covert, clear, operationalised behavioural categories - Qualitative methods (higher ecological validity), triangulation of data (multiple sources)
What is concurrent validity?
Does it relate well to similar tests? Would someone get the same results on an established test? (+ 0.8 or above to be good)
What is face validity?
Refers to whether a test appears to measure what it claims to measure based on face value
What is a paradigm shift?
A fundamental change in an individuals/societies views of how things in the world work
What is the process for the creation of science?
Immature science —> normal science —> crisis —> resolution —> new theory (once it gets to this stage it is classed as a “normal science” and the chart carries on
What are the features of science?
use the acronym THORE
T:heory construction
H:ypothesis testing
O:objectivity
R:eplicability
E:mpirical methods
What is empirical methods?
Using direct observation or experimenting, not rational argument or hearsay, and reported in detail so that other investigations can repeat and attempt to verify the work
What is hypothesis testing/falsifiability?
For a theory to be scientific is should be able to withstand the attempt to prove it fake. The more it does the stronger the theory
What does this statement apply to?
“All individuals whom you are attempting to make a statement about”
Population
What does this statement apply to?
“The individuals whom you are testing?”
Sample
What does this statement apply to?
“A prediction that there will be no effect”
Null hypothesis
What does this statement apply to?
“A prediction that there will be a difference between conditions”
Alternative hypothesis
What is the calculated value? Sometimes called the observed value
The value we calculate in the test
What is a critical value?
The number that tells us whether or not we can accept/reject the null hypothesis
What is the N value/DF value?
Number of participants in the study
How do you conduct a sign test? Make reference to the 5 steps
- Hypothesis: state your hypothesis and what direction it is
- Record & sign: record your data and work out the signs ( + or - )
- Calculate value: work out whether there are more + or -, S = calculated value (least frequent sign)
- Critical value: find total number of results, removing any neutral results. This is N = number of participants. Use table of critical value for S to establish significance; if S (<_) C in the table then we consider the results to be significant
- Accept/reject: if result is significant you can accept your hypothesis, reject the null. If it is not significant reject your hypothesis, accept the null
What is a parametric test?
Uses quantitative data and makes assumptions about the population characteristics (normally using the mean). More powerful than NP tests when assumptions are met
