Research Methods- Experimental Methods

Falsifiability

The possibility that a statement or hypothesis can be proven wrong

Objectivity

Measurement of data is not affected by the expectations of the researchers

Replicability

Recording procedures carefully in order for another researcher to repeat them and verify the original results

Empirical Methods

Methods of gaining knowledge which rely on direct observation or testing

Features of Science

Falsifiability, Objectivity, Replicability, Empirical Methods

Paradigm

A shared set of accepted methods and assumptions around a particular discipline

Laboratory Experiments

Carried out in a controlled environment where variables are carefully manipulated. Participants are aware they are taking part but may not know the true aims

Laboratory Experiments- Advantages

High internal validity
Easy to replicate

Laboratory Experiments- Disadvantages

Low ecological validity
Demand characteristics

Field Experiments

Conducted in a more natural setting, IV is still deliberately manipulated while measuring the effect on the DV. Participants may not be aware they are part of a study.

Field Experiments- Advantages

High ecological validity
Lack of demand characteristics

Field Experiments- Disadvantages

Low internal validity
Harder to replicate

Natural Experiments

Conducted when it is not possible to deliberately manipulate an IV. IV occurs naturally

Natural Experiments- Advantages

Allows research where IV can’t be manipulated
High ecological validity

Natural Experiments- Disadvantages

Lack of causal relationship
Lack of random allocation

Quasi-Experiments

IV is simply a difference between people that exists, a DV is still measured.

Quasi-Experiments- Advantages

Allows comparisons between types of people
Can be carried out in labs

Quasi-Experiments- Disadvantages

Low ecological validity
Lack of random allocation

Causal Relationship

When one variable directly causes another

Extraneous variables

Anything other than IV which might affect DV and can be controlled

Confounding Variables

Variables that aren’t controlled for in an experiment and affect the results

Aims

The stated intentions of what questions are planned to be answered

Hypothesis

A formal, unambiguous statment of what is predicted

Reliability

Consistency

Internal Reliability

Each participant in a study is treated the same way

External Reliability

Same or similar results founds after repeated test

Test-retest reliability

Test the same person twice

Inter-observer reliability

Compares observations from different observers

Validity

Accuracy(representativeness)

Internal Validity

Measures what it’s meant to measure

External validity

Generalisable beyond experimental setting

Ecological Validity

Realistic setting?

Population Validity

Applicable sample?

Temporal Validity

Does it stand the test of time?

Validity assessment: Face Validity

Whether it looks like it measure what it should

Validity Assessment: Concurrent Validity

Whether findings are similar to those on a well established test

Randomisation

Randomly assigning experimental subjects to one of the treatment goups

Pilot Study

Small scale study conducted to evaluate practical parts and improve upon study design

Pilot Study - Purpose

Minimises unnecessary effort from the research team

Ethical Guidelines

Informed consent, avoidance of deception, protection from harm, privacy/confidentiality

Types of Consent

Retrospective
Presumptive
Prior General

Retrospective Consent

Ppts can withdraw after true nature has been revealed

Presumptive Consent

Ask a similar group if they’d take part
If so, assume actual ppts would

Prior General

Agree to consent knowing they may be decieved

Parts of Consent Form

1. Basic aims and procedures, info about study

2. Information about right to withdraw without penalty

3. Assurance of confidentiality

4. Opportunity to ask any questions

5. A statement to sign saying they have read and understood and agree to take part

BPS Code of Conduct

Respect, Competence, Responsibility and Integrity

Cost-Benefit Analysis

Ethics committee weigh up harm to participants and value of research before deciding whether a study should go ahead

Qualitative Data

Non-numerical data expressed in words

Qualitative data- Evaluation

+ Rich in detail

+ Greater external validity

- Difficult to analyse

Quantitative data

Numerical data

Quantitative data evaluation

+ Easier to analyse & identify patterns

- Less detail

- May fail to represent reality

Primary data

'First-hand' data collected for the purpose of the investigation

Secondary data

Collected by someone other than the person who is conducting the research

Nominal

Frequencies (Discrete categories)

Ordinal

Scaled or ranked data (Often a score)

Interval

Ranked data with equal measurement intervals, arbitrary zero

Ratio

Ranked data with equal measurement intervals with absolute zero

Measure of Central Tendency

Any measures of average value in a data set

Measure of Dispersion

Based on the spread of scores

Normal Distribution

Bell shape curved. Mean, median and mode all in the centre

Negatively skewed distribution

Most values on the right, values on the right of the mean

Positively skewed distribution

Most values on left side of mean

Inferential statistics

Determining whether a study has significant findings so that you can generalise to population

P <= 0.05

Shows significant support for a theory but not proof

Significant at x

There is x probability that the results are up to chance

Tests

CSC, MWS, URP

Referencing

Author, Year, Title, Edition. Place, Publisher

Peer review

All aspects of the written investigation must be scrutinized by a small group of experts (peers)

Purposes of Peer Review

Allocation of research funding

Publication of research into academic journals and books

Assessing research rating of uni departments

Peer Review: Strength

Protects quality of published work, increasing credibility of psychology

Peer Review: Limitations

Competition for research funding may create ‘biased’ reviews by burying contradictory research
Publication bias may cause research that is deemed ‘uninteresting’ to be ignored or disregarded