Need To Know Research Methods Flashcards
(67 cards)
1
Q
Co- variables
A
- two measured variables in a correlational analysis
- variables must be continuous.
2
Q
Content analysis
A
- method used to analyse qualitative data
- Allows researcher to take qualitative data & turn it into quantitative data
3
Q
Aims
A
-statement of what researcher intends to find out in research study.
4
Q
Hypothesis
A
-precise & testable statement about assumed relationship between variables
5
Q
Directional hypothesis
A
-States direction of predicted difference between two conditions or two groups of participants
6
Q
Non directional hypothesis
A
- Predicts simply theres a difference between two conditions or two groups of participants without stating direction of difference.
- Two tailed predicts effect between variables but not which way eg therell be an effect between amount of energy drink consumed & number of words spoken in following 5 mins
7
Q
Sampling
A
- method used to select participants like:
- random sampling
- opportunity
- volunteer sampling
- sample behaviours in observation like event or time sampling.
8
Q
Population
A
- group of people that researcher is interested in
- group of people from whom sample is drawn.
- group of people about whom generalisations can be made
9
Q
Random sample
A
-sample of participants produced using random technique such that every member of target population being tested had equal chance of being selected
10
Q
Pilot study
A
- Small trial versions of proposed studies to test effectiveness and make improvements
- helpful in identifying potential issues early
11
Q
Qualitative data
A
- non numerical language based data collected through:
- interviews
- open questions
- content analysis
12
Q
Investigator effects
A
-Occur when researcher unintentionally or unconsciously influences outcome of research they’re conducting.
13
Q
Reliability of content analysis
A
- Analysis can be repeated
- reliability is measured using inter rater reliability
14
Q
Directional hypothesis
A
-researchers predicting direction or effect one variable will have on another be it positive or negative
15
Q
Evaluation - repeated measures
Strengths and weaknesses
A
- Strengths- no individual differences as peoples scores in one condition are compared to their scores in a different condition, fewer participants required
- Weaknesses- time consuming as all participants have to do both conditions
16
Q
Evaluation - independent groups
Strengths and weaknesses
A
- Strengths - quicker as two groups cans do task simultaneously
- no order effects;all participants start condition naive
- Weakness - individual differences can affect results
- eg people in one condition are better at maths than those in other condition
- requires more participants however many that researcher obtains has to be divided into 2 groups
17
Q
Evaluation- matched participants
Strengths and weaknesses
A
- Strengths- limits effect of individual differences
- as participants should be matched on important characteristics
- done quickly both groups can complete tasks simultaneously
- Weaknesses - hard to find people that are good match because there’ll still be differences
- requires large number of participants
18
Q
Laboratory experiment-
A
- experiment conducted in special environment (lab) where variables can be carefully controlled
- researcher manipulated IV
- measures DV
19
Q
Field experiment
A
- controlled experiment conducted in any environment outside of lab.
- Researcher manipulates IV
- measures DV
20
Q
Difference between lab and field experiment
A
- lab experiment conducted in special environment
- unlike field
- lab experiments-participants aware they’re taking part in an experiment
- field they’re not usually aware
21
Q
Similarity between lab and field experiment
A
- both IV is manipulated by experimenter
- Both make sure IV is manipulated deliberately to draw causal conclusions from it
22
Q
Example of lab experiment
A
- loftus and Palmer study of eyewitness testimony
23
Q
Example of field experiment
A
-Johnson and Scott’s 1976 study of weapon focus
24
Q
Advantages and disadvantages of lab experiment
A
- high degree of control - increases validity of study
- participants aware of being studied
- more likely to lead to demand characteristics
- reduces validity
25
Advantages and disadvantages of field experiment
- participants aren’t aware of being studied so behaviour is more natural
- less control
26
Sampling error
-amount of difference between sample and population
27
Theory
-Organised, testable explanation of phenomena
28
Hindsight bias
-Tendency of people to overestimate their ability to predict an event after it happened
29
Ordinal data
- data thats presented in rank order
| - e.g. places in a beauty contest, or ratings for attractiveness
29
Case studies A01
-in-depth investigations of single person, group, event or community.
30
Correlation
- Correlation means association
| - measure of extent to which two variables are related.
31
Covert observations A01
-researcher pretends to be an ordinary member of group and observes in secret.
32
Overt observations
- researcher tells group he/she is conducting research
| - i.e. they know theyre being observed
33
Meta analysis
- systematic review involves identifying an aim
- searching for research studies that have addressed similar aims/hypotheses.
- done by looking through various databases
- decisions are made about what studies are to be included/excluded.
34
Meta analysis strengths and weaknesses
- Strengths:
- Increases validity of conclusions drawn as they’re based on a wider range.
- Weaknesses:
- Research designs in studies can vary so they aren’t truly comparable.
35
Validity
- whether observed effect is genuine
| - represents what’s actually out there in the world.
36
Ecological validity
-extent to which findings from a research study can be generalised to other settings / real life.
37
Temporal validity
- extent to which findings from research study can be generalised to other historical times.
38
Reliability
- measure of consistency
- if particular measurement is repeated
- and same result is obtained then its described as being reliable.
39
Test-retest reliability
- Assessing same person on two different occasions
| - shows extent to which test produces same answers.
40
Empiricism
- Info is gained through direct observation of expriment
41
Objectivity
- personal expectations shouldn’t effect what findings are recorded
42
Replicability
- previously recorded methods
| - and procedures are retested to see if outcome is same
43
Control
- research attempts to find relationships through experimental methods which require degree of control eg we vary IV
- observe its effects on DV
- we must ensure all other conditions are same
44
Scientific method
- use of investigative methods that are:
- objective
- systematic
- replicable
- formulation
- testing
- modification of hypotheses based on these methods
45
Statistical tests levels of measurement Nominal data
-are in separate categories like grouping people according to their favourite football team
46
Statistical tests level of measurement interval data
- measured using units of equal intervals
| - like when counting correct answers or using any ‘public’ unit of measurement
47
Chi squared steps
1- calculated value of x^2
Eg 1.984 -> compare with critical value
2- draw up a contingency table
3-
4- find observed value of chi squared (x^2)
Add all values in final column in table above eg 1.984
5- find critical value of chi squared (x^2)
Calculate degrees of freedom (df) by multiplying (rows-1) x (columns -1 ) = 1
look up values in table of critical values (on the right)
For a two tailed test df = 1 critical value of x^2 = 3.84 (p \< 0.005)
6- state conclusion
As observed value (1.984) is less than critical value (3.84) we must accept null hypothesis (at p \< 0.05) & therefore we conclude there’s no difference between men & women in terms of digit ratio
48
Alternative hypothesis
-testable statement about relationship between two or more variables
49
Probability
- numerical measure of likelihood or chance that certain events will occur
- statistic test gives probability that a particular set of data didn’t occur by chance
50
Type 1 error
-occurs when researcher rejects a null hypothesis that’s true
51
Type 2 error
- occurs when researcher accepts a null hypothesis that was not true
52
What does a statistical test determine
- which hypotheses are true by either accepting or rejecting one of the hypotheses
53
Null hypothesis no tailed
- predicts therell be no effect between variables
- eg energy drink consumed will not effect amount of words spoken in following 5 mins so there’ll be no significant different
54
Chance
- refers to something with no cause as it just happens
- can’t be 100% certain that observed effect wasn’t due to chance but you can state how certain you are
- we used a statistical test to find whether results are significant or due to chance
55
Probability levels
- psychologists use level of probability of 95%
- expresses degree of uncertainty
- means 5% chance of results occurring if null hypothesis is true
- probability of 5% is recorded as p=0.05
- probability is 5% or less which is written as p
56
Significance
- ‘true’ isn’t exactly correct word because actually statistics tests employ level of significance
- means researcher can state that relationship between variables is due to more than just chance
- they can accept alternative hypothesis
- reject null hypothesis
57
What is the acronym for carrots should come mashed with swede under roast potatoes in relation to statistical tests?
- Chi-Square
- Sign Test
- Chi-Square
- Mann Whitney U
- Wilcoxon
- Spearman's rho
- Unrelated T-Test
- Related T Test
- Pearson's r
58
Evaluate Repeated Measures Design
- Counterbalancing is a way to deal with repeated measures
59
Evaluate independent groups design
- randomly allocate ppts into conditions
| - evenly distribute ppt variables
60
Evaluate matched pairs design
- restrict amount of variables to match
| - to make it easier or conduct pilot study to consider key variables that might be important to match
61
Explain counterbalancing
- Used to deal with extraneous factors caused by order effects when using repeated measures design
- Eg rather than all 30ppts completing both conditions, we would split them up
- 15 of them would complete condition A,then B and other 15 ppts would complete condition B, then A
- order effects would be balanced out by opposing half participants due to fact they were split up rather than all 30ppts doing same thing
62
What is lab experiment and how can we evaluate it ie strengths
- investigate casual relationship between IV and DV under controlled conditions
- well controlled, extraneous/confounding variables are minimised.
- High internal validity allowing easy replication demonstrating external validity
63
What is field experiment and how can we evaluate it
| strengths
- investigate casual relationship between IV and DV in more natural surroundings
- less artificial
- high in mundane realism
- ecological validity as ppts arent usually aware they're being studied
64
What is natural experiment and how can we evaluate it
| Strengths
- investigate casual relationship between IV and DV in situations where IV cant be directly manipulated.
- allows research where IV can't be manipulated for ethical reasons
- Allows studying of real problems
- high mundane realism
- ecological validity
65
What is quasi experiment and how can we evaluate it
| Strengths
- investigate casual relationship between IV and DV in situations where
- IV is a characteristic of a person (something we can't change e.g. gender)
- allows comparison of all types of people
66
Stratified sampling
- sampling technique where researcher divides or 'stratifies' target group into sections
- each representing a key group (or characteristic) that should be present in final sample.
