Research Methods Key Terms

?
Hypothesis
A precise testable statement of what the researcher predicts will be the outcome of the study. Clearly operationalised independent/dependent variables.
1 of 117
Experimental hypothesis
If the investigation uses an experiment as its research method.
2 of 117
Alternative hypothesis
If the investigation uses a non-experimental research method, such as an interview, questionnaire or observation.
3 of 117
Null hypothesis
States that there will be no difference between the two variables being studied (one variable does not affect the other).
4 of 117
One-tailed/directional hypothesis
Predicts the nature of the effect of the independent variable on the dependent variable. Indicates which way it predicts the effect will go in.
5 of 117
Two-tailed/non-directional hypothesis
Predicts that the independent variable will have an effect on the dependent variable, but the direction of the effect is not specified.
6 of 117
Aim
What the purpose of the investigation is. What they are trying to find out by conducting the investigation.
7 of 117
Independent group design
Recruiting group of participants. Dividing in two. Two groups do experiment with different conditions (the IV). DV for each is measured. Results for the two groups compared.
8 of 117
Repeated measures design
Recruiting group of participants. Group does experiment with IV for condition 1 and IV for condition 2. Results are compared for the two conditions.
9 of 117
Matched pairs design
Recruiting group of participants. Find out what sorts of people in group. Recruit another group which matches them one for one. Treat experiment like an independent measures. Compare results for two groups.
10 of 117
Ecological validity
Refers to how well a study can be related to everyday, real life. High - can be generalised beyond the setting.
11 of 117
Standardisation
Consistency and objectivity of how tests are administered and scored.
12 of 117
Measure of central tendency
A single value that describes the way in which a group of data cluster around a central value. A way to describe the centre of a data set. (Mean, mode, median).
13 of 117
Measure of dispersion
Show the spread of variability of the variable being measured (range, interquartile range, standard deviation).
14 of 117
Standard deviation
A measure of variation that indicates the typical distance between the scores of a distribution and the mean.
15 of 117
Participant variables
Variation between participants can affect the DV. Could mask an effect or imply one where none exists.
16 of 117
Attrition
When participants drop out of a study, data are lost.
17 of 117
Counterbalancing
A type of experimental design in which all possible orders of presenting the variables are included.
18 of 117
Mundane realism
Describes the degree to which the materials and procedures involved in an experiment are similar to events that occur in the real world.
19 of 117
Laboratory experiment
An experiment conducted in a special environment where variables can be carefully controlled. IV manipulated.
20 of 117
Laboratory experiment advantages
Control is easier, extraneous variables minimised so higher internal validity (causal relationship). Can be easily replication for same results to support external validity.
21 of 117
Laboratory experiment disadvantages
Participants aware of study - likely to affect behaviour. Setting unlike everyday life - low mundane realism. IV or Dv may be operationalised in such a way that it doesn't represent everyday experiences & tasks set lack mundane realism. Less natural.
22 of 117
Field experiment
An experiment conducted in a more natural environment. Outside lab. IV manipulated.
23 of 117
Field experiment advantages
More natural, less artificial. Higher mundane realism, higher internal validity. Avoids participant effects (unaware of study) which may increase internal validity.
24 of 117
Field experiment disadvantages
Less control, harder to control EVs. Ethics - if participants unaware and difficult to debrief them, is it right to manipulate and record their behaviour?
25 of 117
Natural experiment
The environment is natural but the change in IV is also natural as it has not been directly manipulated by the researcher.
26 of 117
Natural experiment advantages
Allows research where IV can't be manipulated for ethical/practical reasons. Enables psychologists to study real problems e.g. effects of disaster on health. Increased mundane realism and validity.
27 of 117
Natural experiment disadvantages.
Can't demonstrate causal relationships - IV not directly manipulated. Inevitably many EVs threat to validity. Can only be used where conditions vary naturally. PPs may be aware - PP effects, demand characteristics.
28 of 117
Internal validity
Refers to whether the effects observed in a study are due to the manipulation of the IV and not some other factor.
29 of 117
External validity.
Refers to the extent to which the results of a study can be generalised to other settings (ecological validity), other people (population validity) and over time (historical validity).
30 of 117
Opportunity sampling
Using whoever is immediately available. E.g. o out and accost passersby. Adv - Easy, quick. Disadv - Inevitably biased, drawn from small part of target population.
31 of 117
Volunteer sampling
Use whoever puts themselves forward. E.g. advertise in the paper. Adv - Access to vanity of PPs, representative. Disadv - Biased - PPs more likely highly motivated with extra time on their hands.
32 of 117
Quota/stratified sampling
Design a sample to reflect TP and recruit to order. According to frequency in population for representative sample. Adv - Representative of sub-groups. Disadv - May be biased in other ways, if by opportunity then only have access to certain people.
33 of 117
Random sampling
Every member of the target population has an equal chance of selection. E.g. Pulling names from a hat. Adv - Unbiased, equal chance. Disadv - May end up with biased sample because too small. E.g. More boys than girls.
34 of 117
Systematic sampling
Obtain representative sample by selecting every nth person. Adv - Quick, good for large lists, should be representative. Disadv - Not random, anybody not 'nth' person has no chance. Difficult, time, money. May not be representative if list ordered.
35 of 117
Brief
A short explanation read to participants which explains what the research aim is and what they will be expected to do.
36 of 117
Consent form
Outlines details of the tasks participants will undertake and contains their signed agreement that they consent to take part.
37 of 117
Standardised procedures
Guide other researchers on how to conduct your research. Step-by-step.
38 of 117
Debrief
Restatement of aims, explanation of use of findings, reminder that data can be withdrawn until published. Particularly important if you had to deceive PPs in the brief.
39 of 117
Right to withdraw
Participants should always be aware that they can leave the study at any time, regardless of whether or not any payment or inducement has been offered.
40 of 117
Informed consent
Participants should be informed of the study objectives and consent obtained.
41 of 117
Avoidance of deception
Withholding of info or misleading of participants unacceptable if they are likely to object once debriefed. Can be dealt with through presumptive, prior general and retrospective consent.
42 of 117
Presumptive consent
Gained from people of a similar background to participants. If they state they would be wiling to participant, it's likely the real participants will not be upset by it.
43 of 117
General prior consent
Involves participants agreeing to being deceived without knowing how. Might suspect and affect results.
44 of 117
Retrospective consent
Involves asking participants for consent after they have participated in the study. May not agree but have already taken part.
45 of 117
Observational research
Should only observe where people might expect to be seen by strangers
46 of 117
Colleagues
Investigators share responsibility for the ethical treatment of research. Should be encouraged to re-evaluate their research.
47 of 117
Protection of participants
Normally the risk of harm should be no greater than ordinary life.
48 of 117
Confidentiality
Participants data should be treated as confidential and not disclosed to anyone unless arranged in advance.
49 of 117
Pilot study
Small scale study conducted prior to administering a full scale experiment or study,
50 of 117
Interval data
Objective measurement with equal gaps. E.g. cm.
51 of 117
Ordinal data
Data ranked in order. E.g. 1st, 2nd, 3rd.
52 of 117
Nominal data
Categories. E.g. Driver, non-driver, learner driver.
53 of 117
Mean
Sum of all the numbers divided by number of numbers. Used for interval data. Adv - Uses all values so sensitive to variation. Disadv - Can be artificially raised/lowered by an extreme or skewed value. Need normal distribution, unskewed & no outliers.
54 of 117
Mode
Most frequently occurring. Used for nominal data. Adv - Only measure of central tendency suitable for summarising category data. Disadv - May be no modal value or several.
55 of 117
Median
Middle number. Used for ordinal data.Use median when can't use mean because of skew/outliers etc. Adv - Based on order of data not actual values so not distorted by extreme values. Disadv - Less sensitive to variations in data.
56 of 117
Range
Difference between the highest and lowest score. Adv - Easy, takes account of extreme values. Disadv - Can be greatly influenced by one score different from others. Ignores all but 2 scores.
57 of 117
Standard deviation
Calculates average distance from the mean of all scores. Adv - Takes account of all scores, sensitive. Describes spread of scores in a normal distribution with great precision. Disadv - Harder to work out.
58 of 117
Variance
Standard deviation squared.
59 of 117
Positive skew
Cluster of scores at lower end of data set. Bell curve has a tail on the right side of the peak.
60 of 117
Negative skew
More scores at the higher end of the data set. Tail on the left side of the peak.
61 of 117
Peer review
Before publication, research undergoes peer review. Fellow researchers criticise and evaluate work to assess quality. Ensures accuracy and indicates any required further work. Prevents publication of flawed/falsified work and maintains credibility.
62 of 117
Reliability
Refers to the consistency of a measure. Reliable if we get the same result repeatedly.
63 of 117
Test-retest reliability
The measure is administered to the same group of people twice. If the results on the two tests are similar, we can assume the test is reliable.
64 of 117
Split-half reliability
Splitting a test into two halves, and comparing the scores in both halves. If the results in the two halves are similar, we can assume the test is reliable.
65 of 117
Inter-rater reliability
If the measure depends upon interpretation of behaviour, we can compare the results from two or more raters. If there is high agreement between the raters, the measure is reliable.
66 of 117
Validity
The extent to which a test measures what it claims to measure.There are three main aspects we investigate in psychological research: control, realism and generalisability.
67 of 117
Control
Refers to how well the experimenter has controlled the experimental situation. Allows establishment of cause and effect relationships. (Not EVs).
68 of 117
Realism
If an experiment is too controlled or artificial, PPs may act differently than they would in real life.
69 of 117
Generalisability
Aim is to produce results which can then be generalised beyond the experimental setting. If lacking in realism, we will be unable to generalise. Small group of similar people, low population validity, unable to generalise.
70 of 117
Internal validity
Concerned with whether we can be certain that it was the IV that caused the change in the DV. Can be affected by lack or mundane realism, causing PPs to act unnaturally, or extraneous variables.
71 of 117
Siturational variables
Anything to do with the environment of the experiment, time of day,temperature, noise levels etc.
72 of 117
How do situational variables affect validity?
Something about the situation could act as an EV if it has an effect on the DV. For example, poor lighting could affect participants' performance on a memory test.
73 of 117
How can situational variables be overcome?
By the use of standardised procedures which ensure that all participants are tested under the same conditions.
74 of 117
Participant variables
Anything to do with differences in the participants, age, gender, intelligence, skill, past, experience, motivation, education etc.
75 of 117
How do participant variables affect validity?
It may be that the differences between the participants cause the change in the DV. For example, one group may perform better on a memory test than another because they are younger, or more motivated.
76 of 117
How can participant variables be overcome?
Participant variables can be completely removed by using a repeated measures design *the same participants used in each condition) or matched pairs (participants in each group are matched).
77 of 117
Investigator effects
Refers to how the behaviour and language of the experimenter may influence the behaviour of the participants. The way in which an experimenter asks a question may act as a cue for the participant. Also known as experimenter bias.
78 of 117
How do investigator effects affect validity?
Leading questions from the experimenter may consciously or unconsciously alter responses. For example, the experimenter may provide verbal or non verbal encouragement when the participant behaves in a way which supports the hypothesis.
79 of 117
How can investigator effects be overcome?
Can be overcome by using a double blind technique. This is when the person who carries out the research is not the one who designed it.
80 of 117
Demand characteristics
Participants are often searching for cues as to how to behave in an experiment. There could be something about the experimental situation or the behaviour of the experimentwhich communicates to the participant what is "demanded" of them.
81 of 117
How do demand characteristics affect validity?
The structure of experiment could lead PPs to guess the study aim. E.g. PPs may perform a memory test,exercise, and then given another memory test. This may lead them to guess that it is about effect of exercise on memory causing change in behaviour.
82 of 117
How can demand characteristics be overcome?
When designing a study, it is important to try and create a situation where the participants will not be able to guess what the aim of the study is.
83 of 117
Participant effects
Participants are aware that they are in an experiment, and so may behave unnaturally.
84 of 117
How do participant effects affect validity?
They may be overly helpful and want to please the experimenter, leading to artificial behaviour. Alternatively, they may go against the experimenter's aims and act in a way which spoils the experiment - the "screw you" effect.
85 of 117
How can participant effects be overcome?
Again, by designing a study so that the participants cannot guess the aims, participant effects can be reduced.
86 of 117
Correlational research
Shows a relationship between two co-variables. May not be linked at all (zero correlation), increase together (positive correlation) or, as one increases the other decreases (negative correlation).
87 of 117
Strengths of correlational research
When unethical/impractical to manipulate variables. Make use of existing data. If correlation significant further investigation might be justified. If not, can be ruled out as a causal relationship. Procedures repeatable. Quantify relationships.
88 of 117
Weaknesses of correlational research
Pople misinterpret as cause and effect - not possible. May be other, unknown variables that can explain link. May lack internal/external validity in method/sample.
89 of 117
Co-efficient
Closer to -1 - strong negative correlation, closer to 1 - strong positive correlation.
90 of 117
Primary data
Gathered first hand directly by researchers.
91 of 117
Strengths of primary data
Careful operationalisation of variables/procedures. Should be valid - designed and carried out for purpose. More trustworthy, greater validity. Likely to be gathered for stated aim and at the time of study. More credible.
92 of 117
Weaknesses of primary data
Expensive - must start from the beginning of the study. Sample size - can't generalise. Done at one moment in time, in one location with small sample size.
93 of 117
Secondary data
Already been gathered by someone and are used by someone else for further research.
94 of 117
Strengths of secondary data
Cheaper - already exists. Larger sample size - able to generalise more. Different cultures, people, times etc.
95 of 117
Weaknesses of secondary data
May have been gathered for another purpose or unclear purpose. May not be valid for second purpose. If data gathered for one purpose used for another then this use may lack credibility. Might have been gathered some time ago - invalid?
96 of 117
Meta-analysis
Researchers pool data on a particular topic.
97 of 117
Strengths of meta-analysis
Allows funds to be diverted elsewhere, reduces complexity and breadth of research. Process made easier by database programmes. More rigorous. Wider, excellent for highlighting correlations and links between studies that may not be readily apparent.
98 of 117
Weaknesses of meta-analysis
Potential for publication bias and skewed data. If restricted to research with positive results (negative often unpublished), then validity compromised. Researcher must make sure all data quantitative and comparable for genuine stat. analysis.
99 of 117
Weaknesses of meta-analysis (2)
Important to pre-select the studies. Poorly conducted studies can affect results. Finding data.
100 of 117
Sign test
Ideal for working out the probability of different outcomes occurring. Work out the difference between each participant's two scores. Then indicate whether the change was positive or negative. Add up the number of positive signs and negative signs.
101 of 117
Sign test (2)
The smallest one is the test statistic.
102 of 117
Sign test (2)
The smallest one is the test statistic. The test statistic must be less than or equal to the critical value on a table to be significant.
103 of 117
Naturalistic observation
Behaviour observed in natural setting. Adv - Produces data with ecological validity. PPs may be unaware and so behave naturally. Disav - No EV control. PPs unaware - ethical issues of informed consent.
104 of 117
Controlled observation
Variables are controlled often in a 'false' environment (laboratory). Adv - Higher levels of control over EVs. Disadv - Lacks ecological validity - behaviour unnatural? If they know about observation may affect behaviour.
105 of 117
Covert observation
Participant unaware of observation. Adv - Less demand characteristics. Increase validity? Disadv - Raises ethical issue of informed consent. Distrust of psychologists in future.
106 of 117
Overt observation
Participants aware of observation. Adv - Reduced risk of ethical concerns, informed consent gained. Increase trust. Disadv - Participants know they are being observed - demand characteristics? Lack of validity?
107 of 117
Participant observation
The observer takes part in the situation they are studying. Adv - More valid/qualitative data. High ecological validity. Easier to understand behaviour. Trust. Disadv - Note taking difficult - rely on memory. Emotionally involved, subjective. Ethics.
108 of 117
Non-participant observation
The observer not part of group being observed, observes from distance. Adv - May not realise being observed. Observer less emotionally involved, more objective. Can take notes - reliable. Disadv - Behaviour unclear, distance? Demand characteristics?
109 of 117
Structured observation
Coding scheme, precise definition of how each category will be measured, pilot study.
110 of 117
Inter-observer reliability
Whether two or more observers are coding behaviour consistently in the same way.
111 of 117
Intra-observer reliability
Whether the same observer is coding behaviour consistently in the same way.
112 of 117
Coding system
Gives a code to represent each category of behaviour.
113 of 117
Behaviour checklist
Very similar to a coding system but may not give a code for each behaviour.
114 of 117
Rating system
Provides a list of behaviours or characteristics, asking observers to rate each one.
115 of 117
Quantitative
Information about quantities; that is, information that can be measured and written down with numbers.
116 of 117
Qualitative
Typically descriptive data and as such is harder to analyze than quantitative data. Qualitative research is useful for studies at the individual level, and to find out, in depth, the ways in which people think or feel.
117 of 117

Other cards in this set

Card 2

Front

If the investigation uses an experiment as its research method.

Back

Experimental hypothesis

Card 3

Front

If the investigation uses a non-experimental research method, such as an interview, questionnaire or observation.

Back

Preview of the back of card 3

Card 4

Front

States that there will be no difference between the two variables being studied (one variable does not affect the other).

Back

Preview of the back of card 4

Card 5

Front

Predicts the nature of the effect of the independent variable on the dependent variable. Indicates which way it predicts the effect will go in.

Back

Preview of the back of card 5
View more cards

Comments

markn_1

Report

very detailed and covers basically every thing

Similar Psychology resources:

See all Psychology resources »See all Research methods and techniques resources »